See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/262411501

Evolutionary techniques in optimizing machining parameters: Review and

recent applications (2007–2011)

Article in Expert Systems with Applications · August 2012

DOI: 10.1016/j.eswa.2012.02.109

CITATIONS READS

269 1,299

3 authors:

Norfadzlan Yusup Azlan Mohd Zain

University Malaysia Sarawak Universiti Teknologi Malaysia
11 PUBLICATIONS 448 CITATIONS 166 PUBLICATIONS 4,583 CITATIONS

SEE PROFILE SEE PROFILE

Siti Z Mohd Hashim

Universiti Teknologi Malaysia
183 PUBLICATIONS 4,003 CITATIONS

SEE PROFILE

All content following this page was uploaded by Azlan Mohd Zain on 22 May 2014.

The user has requested enhancement of the downloaded file.

 Expert Systems with Applications 39 (2012) 9909–9927

Contents lists available at SciVerse ScienceDirect

Expert Systems with Applications

journal homepage: www.elsevier.com/locate/eswa

Review

Evolutionary techniques in optimizing machining parameters: Review and

recent applications (2007–2011)
Norfadzlan Yusup a,b, Azlan Mohd Zain a,⇑, Siti Zaiton Mohd Hashim a
a
Faculty of Computer Science and Information Systems, Universiti Teknologi Malaysia, 81310 UTM Skudai, Johor, Malaysia
b
Faculty of Computer Science and Information Technology, Universiti Malaysia Sarawak, 94300 Kota Samarahan, Sarawak, Malaysia

a r t i c l e i n f o a b s t r a c t

Keywords: In highly competitive manufacturing industries nowadays, the manufactures ultimate goals are to pro-
Machining duce high quality product with less cost and time constraints. To achieve these goals, one of the consid-
Evolutionary erations is by optimizing the machining process parameters such as the cutting speed, depth of cut, radial
Optimization rake angle. Recently, alternative to conventional techniques, evolutionary optimization techniques are
the new trend for optimization of the machining process parameters. This paper gives an overview
and the comparison of the latest five year researches from 2007 to 2011 that used evolutionary optimi-
zation techniques to optimize machining process parameter of both traditional and modern machining.
Five techniques are considered, namely genetic algorithm (GA), simulated annealing (SA), particle swarm
optimization (PSO), ant colony optimization (ACO) and artificial bee colony (ABC) algorithm. Literature
found that GA was widely applied by researchers to optimize the machining process parameters.
Multi-pass turning was the largest machining operation that deals with GA optimization. In terms of
machining performance, surface roughness was mostly studied with GA, SA, PSO, ACO and ABC evolution-
ary techniques.
Ó 2012 Elsevier Ltd. All rights reserved.

1. Introduction cesses are focusing on (i) modeling techniques and (ii)

conventional and non-conventional (evolutionary) optimization
In manufacturing, the process of removing unwanted segment techniques as illustrated in Fig. 1. This study also pointed out that
of metal workpiece in the form of chips is known as machining. modelling and optimization techniques have been applied in the
Machining is one of the five groups of manufacturing processes recent research due to the complexity of mathematical model to
which includes casting, forming, powder metallurgy and joining determine optimal machining process parameters. It was reported
(Nagendra Parashar & Mittal, 2007). The machining process will that evolutionary techniques such as GA, SA and ACO for optimiza-
shape the workpiece as desired and it is usually done using ma- tion process parameters have been applied in the traditional
chine and cutting tools. The machining cutting process can be di- machining due to likely to deal with highly nonlinear, multidimen-
vided into two major groups which are (i) cutting process with sional and ill-behaved complex engineering problem (Chandrasek-
traditional machining (e.g., turning, milling, boring and grinding) aran, Muralidhar, Krishna, & Dixit, 2010; Mukherjee & Ray, 2006).
and (ii) cutting process with modern machining (e.g., electrical dis- In the review paper by Benardos and Vosnaikos (2003), the authors
charge machining (EDM) and abrasive waterjet (AWJ)). From the provided an evaluation based on machining theory, experimental
early introduction cannon-borring machine by John Wilkinson in investigation, design of experiments (DOE) and artificial intelli-
1775 to a modern machine CNC (Computer Numeric Control) in gence (AI) techniques in optimizing machining process parame-
the 1960s, the machining processes continues to evolve where ters. In the literature review paper by Aggarwal and Singh
new techniques and modern tools have been discovered. There (2005), the authors discussed the various conventional techniques
are many researches that have been done in the areas of machining (e.g., geometric programming and goal programming) and evolu-
processes which mainly stressed on the tool, input work materials tionary techniques (e.g., GA) in optimizing traditional machining
and machine parameter setting (Mukherjee & Ray, 2006). In the pa- process parameters, turning operation.
per, a review on the optimization techniques in metal cutting pro- In optimizing the machining process parameters, the selection
of machining process parameters is a very crucial part in order
for the machine operations to be successful (Rao & Pawar,
⇑ Corresponding author. Tel.: +60 7 5532088; fax: +60 7 5565044. 2010b). To choose the process parameters, it is usually based on
E-mail addresses: ynorfadzlan@fit.unimas.my (N. Yusup), [email protected] the human (or manufacturing engineers) judgement and experi-
(A.M. Zain), [email protected] (S.Z.M. Hashim). ence. However, the chosen process parameters usually did not give

0957-4174/$ - see front matter Ó 2012 Elsevier Ltd. All rights reserved.
doi:10.1016/j.eswa.2012.02.109
9910 N. Yusup et al. / Expert Systems with Applications 39 (2012) 9909–9927

Optimization Tools and Techniques

Conventional Techniques [Optimal Solution] Non-Conventional Techniques [Near Optimal Solution(s)]

Meta- Problem
Design of Mathematical Iterative Search Heuristic Specific
Experiment Search Heuristic
(DOE) Search

Dynamic Non-Linear Linear

Programming Programming Programming
(DP)-based (NLP)-based (LP)-based
Algorithm Algorithm Algorithm

Taguchi Factorial Response Suface GA SA TS

Method-based Design-based Design
Methodology
(RSM)-based

Fig. 1. Conventional and non-conventional optimization tools and techniques (Mukherjee & Ray, 2006).

an optimal result. This is due to the fact that in machining process- Sharif, 2010a, 2011a). An overview of GA technique to optimize
ing; a number of factors also could interrupt thus preventing in the surface roughness in milling process and previous work of
achieving high process performance and quality (Benardos & Vos- machining optimizing problem for surface roughness can be found
naikos, 2003). In fact, tuning each machining process parameters in Zain, Haron, and Sharif (2008).
would give significant effects to others parameters as well.
In the current trends of optimizing machining process parame-
2.1. GA methodology
ters, various evolutionary or meta-heuristic techniques have been
used. Most of these techniques are inspired by nature or animal
The GA technique is based on the natural process of evolution to
behaviour such as GA, PSO ACO and ABC. According to Vob
solve optimization and search problems. There are three main
(2001), the definition of meta-heuristic technique is an iterative
operators in GA which are reproduction, crossover and mutation.
master process that guides and modifies the operation of subordi-
To apply GA in optimization of machining process parameters,
nate heuristics to efficiently produce high-quality solutions. It may
the process parameters are encoded as genes by binary encoding.
manipulate a complete (or incomplete) single solution or a collec-
The basic structure of GA optimization methodology is depicted
tion of solutions at each iteration. The subordinate heuristics may
in Fig. 2. It is important for the researcher to choose suitable GA
be high (or low) level procedures, or a simple local search, or just a
parameters apart from weighing factors and constraints in order
construction method. The family of meta-heuristics includes, but is
for the algorithm to perform efficiently. The steps to apply GA in
not limited to, adaptive memory procedures, tabu search (TS), ant
optimization of machining are as follows (Wang & Jawahir, 2004).
systems, greedy randomized adaptive search, variable neighbor-
hood search, evolutionary methods, GA, scatter search, neural net-
(i) The process parameters are encoded as genes by binary
works, SA, and their hybrids. The most recent research of
encoding.
evolutionary techniques in machining process parameters optimi-
(ii) A set of genes is combined together to form a chromosome,
zation have been demonstrated by Rai, Brand, Slama, and Xirou-
which is used to perform those basic mechanisms in the GA,
chakis (2011), Gao, Li, and Mao (2011), Rao and Pawar (2010b),
such as crossover and mutation.
Sultana and Dhar (2010), Wang, Yuan, Hu, and Dengn (2009) and
(iii) Crossover is the operation to exchange some part of two
Zhang and Chen (2009). In this paper, we discuss five evolutionary
chromosomes to generate new offspring, which is important
techniques (GA, SA, PSO, ACO and PSO) and basic methodology of
when exploring the whole search space rapidly.
each technique in optimizing machining process parameters for
(iv) Mutation is applied after crossover to provide a small ran-
both traditional and modern machining.
domness to the new chromosome.
(v) To evaluate each individual or chromosome, the encoded
2. Genetic algorithm process parameters are decoded from the chromosome and
are used to predict machining performance measures.
According to Ganesan, Mohankumar, Ganesan, and Ramesh Ku- (vi) The fitness or objective function is a function needed in the
mar (2011), GA and PSO is one the best population search tech- optimization process and the selection of the next genera-
niques. GA optimization technique has been used by a number of tion in the GA.
researchers to find the optimal surface roughness in various tradi- (vii) After a number of iterations of the GA, optimal results of
tional and modern machining (Maji & Pratihar, 2010; Pasam, Bat- process parameters are obtained by comparison values of
tula, Valli, & Swapna, 2010; Wang et al., 2009; Zain, Haron, & objective functions among all individuals.
 N. Yusup et al. / Expert Systems with Applications 39 (2012) 9909–9927 9911

Theoritical Experimental Numerical

Analysis Database Methods

Machining Performance
Prediction Model

GA Parameters GA Constraints of
and Objective Optimization Machining
Functions Methodology Performance
Measures

Optimal process parameters

Fig. 2. GA optimization methodology (Wang & Jawahir, 2004).

sign of experiments. GA optimization technique was used to

2.2. Application of GA optimize the process parameters of turning such as cutting speed,
feed and depth of cut. The experimental results obtained the min-
GA optimization technique was used by Palanisamy, Rajendran, imum tool wear of 0.244 mm with the optimal combination of pro-
and Shanmugasundaram (2007) to find the most optimal process cess parameters cutting speed = 31.5 m/min, feed = 0.3 mm/rev
parameters of end milling machining such as cutting speed, depth and depth of cut = 0.5 mm in the 33th generation with the popula-
of cut and feed rate. The objective function considered in this study tion size of 20. The results of the experiments are compared with
was machining time. By using GA, the results showed a fast conver- traditional technique like dynamic programming. Duran, Barrien-
gence and the estimated surface roughness value of 0.71 lm. From tos, and Consalter (2007) used non-dominated sorting GA (NSGA-
the experimental results also, the optimal process parameters have II) to find the optimal process parameters of turning operations
given a MRR of 6.0  103 mm3/min with less amplitude of vibra- such as cutting feed and feed rate. The machining performances
tion at the work piece support 1.66 lm maximum displacement. considered in this study were production rate and production cost.
The authors concluded that the optimized process parameters The technique of NSGA-II was employed to identify economic pro-
are capable of machining the work piece more efficiently with bet- cess parameters and to show the adaptive capability of Automated
ter surface finish. The optimization of turning, facing and under- Process Planning systems. Mahapatra and Patnaik (2007) em-
cutting process parameters using GA was considered by ployed GA technique to optimize the process parameters of WEDM
Saravanan and Janakiraman (2007). The objective of the research with multiple objectives such as discharge current, pulse duration,
is to find the minimum machining time of the machining opera- pulse frequency, wire speed, wire tension, and dielectric flow. The
tions by optimizing process parameters such as cutting speed machining performances measured in this study were metal re-
and feed rate. The GA parameters is set with the following values moval rate (MRR), surface roughness and cutting width (kerf).
where sample size = 30, crossover = 0.6, mutation = 0.05 and num- From the results of the experiments, the researchers suggested that
ber of generations = 100. The experimental results showed that GA the process parameters of WEDM can be adjusted to achieve im-
reduced machining time of 5.75 s per component with 19.2% proved machining performances simultaneously. In the research
reduction of machining time in the study. A modified GA (MGA) of Parent, Songmene, and Kenné (2007), GA optimization tech-
has been proposed by Sankar, Asokan, Saravanan, Kumanan, and nique was proposed to find the optimal process parameters of
Prabhaharan (2007) to optimize the process parameters of multi- end milling operation. The authors presented a generalised math-
pass turning, facing and drilling operation. The research is divided ematical programming model to optimize the process parameters
into two different modules where the first module focusing more of end milling. Then GA was employed to find the optimal process
on multi-pass turning operations. In the second module, three parameters. Jain, Jain, and Deb (2007) considered four types of ad-
machining operations such as turning, facing and drilling were vanced machining process (AMP) such as ultrasonic machining
used to find the optimal of average unit cost. The results of both (UM), abrasive jet machining (AJM), waterjet machining (WJM)
modules have been compared with other traditional and non-tra- and abrasive waterjet machining (AWJM). All process parameters
ditional techniques, such as float encoded GA (FEGA), SA, ACO, Hill were optimized using GA techniques with the objective to maxi-
Climbing (HC) and Newton’s method (NM). From the experimental mize the MRR value. According to the researcher, real coded GA
results, it showed that MGA technique outperforms other tech- was employed because traditional methods were found to be
niques where the most optimal average cost unit has been found unsuitable to solve the problems. In Jain and Jain (2007), the pro-
in both modules. The authors revealed that the modified genetic cess parameters of electro-chemical machining such as tool feed
operators such as crossover and mutation improved the search rate, electrolyte flow velocity, and applied voltage were optimized
more efficiently compared to the standard GA techniques. GA tech- using real coded GA. The objective of the research is to minimize
nique has been used by Prasad, Jayabal, and Natarajan (2007) to geometrical inaccuracy subjected to temperature, choking, and
minimize the tool wear in turning operation. A mathematical mod- passivity constraints. The results were compared with the past
el was developed using simple probabilistic considerations and de- work and showed an improvement in terms of geometrical
9912 N. Yusup et al. / Expert Systems with Applications 39 (2012) 9909–9927

accuracy. Lee, Nam, Choi, Kang, and Ryu (2007) presented an ap- is possible to select optimum for obtaining minimum cutting force
proach to optimize process parameters of milling machining and reasonably good material removal rate (MRR). In Pasam et al.
according to the required MRR. In the study, the researcher em- (2010), eight machining process parameters of wire electrical dis-
ployed 2-staged artificial neural network (ANN) as the objective charge machining (WEDM) were used such as ignition pulse cur-
function for the prediction of model surface roughness. GA was rent, short pulse duration, time between two pulses, servo speed,
used to optimize the problem with the additional surface quality servo reference voltage, injection pressure, wire speed and wire
criterion. From the experimental results, the optimized machining tension to find the minimum surface roughness. Taguchi technique
conditions can be selected to obtain the high-quality surface with- was used to learn the behaviour of machining process parameters
in allowable reliability while maintaining a high-quality surface, and regression analysis was developed to establish relationship be-
under the given desired MRR. In Singh and Rao (2007) the effect tween control parameters and surface finish. GA was used to pre-
of the tool geometry (effective rake angle and nose radius) and pro- dict the optimal surface roughness. The optimal values of
cess parameters (cutting speed and feed) on the surface finish dur- machining process parameters at level for the selected range and
ing the hard turning of the bearing steel has been investigated. In workpiece material are obtained. Ansalam Raj and Narayanan
the experiments, RSM technique was used to develop first- and Namboothiri (2010) proposed an improved GA, labelled as IGA. It
second-order mathematical models. Then the predicted surface was used to optimize machining process parameters such as feed,
roughness model was optimized by GA. The results showed that speed and depth of cut on surface roughness in dry turning ma-
GA gives optimal values of surface roughness and their respective chine. The authors noted that the main advantage of the IGA ap-
optimal conditions. proach is that the ‘‘curse of dimensionality’’ and a local optimal
In Gao, Zhang, Su, and Zhang (2008), parameter optimization trap inherent in mathematical programming methods can be
model was developed using both ANN and GA to optimize the pro- simultaneously overcome. The IGA equipped with an improved
cess parameters of EDM such as current, pulse on time and pulse evolutionary direction operator and a migration operation can effi-
off time. An ANN model which adapts Levenberg–Marquardt algo- ciently search and actively explore solutions. The proposed IGA is
rithm has been set up to represent the relationship between MRR more effective and applies the realistic machining problem more
and process parameters. Then, GA was used to optimize the pro- efficiently than the conventional GA. The research by Xu, Zhu,
cess parameters. After 250 generations, the results showed that Wu, Zang, and Zuo (2010) was carried out to optimize process
the model is shown to be effective, and MRR is improved using parameter of milling titanium alloy. The machining performances
optimized machining parameters. MRR values are 78.0370 mm3/ include cutting force, tool life and surface roughness. GA was used
min, where current, pulse on time and pulse off time are 18 A, to find the optimal milling process parameters for the maximum
416 ls, 59 ls, respectively. Mohanasundararaju, Sivasubramanian, metal removal rate of titanium alloy. The optimization results
and Alagumurthi (2008) employed two techniques, non linear pro- showed that the optimization system can improve the productivity
gramming and GA, to optimize the process parameters of grinding of milling Ti6Al4V. In Alam, Nurul Amin, Patwari, and Konneh
machining. The process parameters such as wheel speed, work (2010), machining process parameters of NC milling such as speed,
speed, traverse speed, in feed, dress depth and dressing lead using feed rate, and depth of cut were used to predict surface roughness.
Box–Behenken design matrix with six central points were consid- In the paper, quadratic prediction model was coupled with GA to
ered to give a desired surface finish and dimensional accuracy. RSM optimize the machining process parameters for the minimum sur-
technique was used to develop a second-order mathematical mod- face roughness. Saffar and Razfar (2010) presented a 3D simulation
el. The process parameters optimization of turn milling operation system to predict cutting forces during end milling operation. GA
has been investigated by Savas and Ozay (2008). In the experi- was employed to optimize the machining process parameters with
ments, the effects of process parameters on the surface roughness the objective of minimization of the tool deflection. Tool deflection
were optimized using GA optimization technique. The process is selected as the objective function, and the constraints are surface
parameters considered were depth of cut, workpiece speed, tool roughness and tool life. The results are compared with experimen-
speed and feed rate. The optimal surface roughness for the process tal and indicate that the optimized process parameters are capable
of tangential turn-milling was determined according to the process of machining the workpiece more accurately and with better sur-
parameters. face finish. Bharathi and Baskar (2010) used three evolutionary
In Zhang and Chen (2009), GA was used for the optimization of optimization techniques such as SA, GA and PSO to explore the
milling process parameters to enhance tool life and reduce pro- optimal machining process parameters for single pass turning
cessing costs. The four optimized process parameters were cutter operation, multi-pass turning operation and surface grinding oper-
speed, feed rate, milling depth and milling width. A mathematical ation. The most affecting machining parameters are considered
model was developed based on mathematical formula and produc- such as number of passes, cutting speed, feed, and depth of cut.
tion cost process. The results showed that by using GA, the most The machining performances considered in this study are the pro-
optimized milling parameters was obtained and the most optimal duction cost and the metal removal rate in turning operation. From
tool life = 79.7852 min and processing cost = 1.438 ¥. The authors the experiments, it was found that GA gave better results com-
concluded that GA is easy to use and can improve the tool life pared to SA. However, PSO has given a better result when com-
and reduce processing costs. pared to GA optimization. GA incorporated with gene repair
Sultana and Dhar (2010) considered the machining process technique were proposed by Xie and Pan (2010) to find optimal
parameters of turning operation such as feed rate, pressure, flow process parameters and to minimize unit production cost in mul-
rate and high pressure coolant to improve machining perfor- ti-pass turning operation. The selected process parameters of turn-
mances such as cutting temperature, chip reduction co-efficient ing were cutting speed, feed rate and depth of cut. In the study, the
and surface roughness. A predictive model was carried out using population and offspring are set to 200 while the crossover and
RSM, and multiobjective GA was used for the optimization. The re- mutation rates are set to 0.36 and 0.6, respectively. The algorithm
sults show that machining performance can be estimated by the stops after 400 generations. By incorporating vector constraints-
predictive models. Yongzhi, Jun, Xiuli, and Xing (2010) used GA encoding and gene repair method into GA, the number of infeasible
to optimize process parameters of high speed milling such as axial individuals in the evolutionary population was greatly reduced.
depth-of-cut, radial depth-of-cut and helical angle. A predictive Computer simulation results show that the proposed algorithm is
model was developed using a full-factorial experimental design efficient in searching the optimal machining parameters, which
and multi-linear regression technology. The result shows that it significantly reduce the unit production cost. Del Prete, De Vitis,
 N. Yusup et al. / Expert Systems with Applications 39 (2012) 9909–9927 9913

and Anglani (2010) developed a prediction model for surface In applying GA to solve the problems, the bound adjustment of
roughness in flat end mill operation using RSM. ANN was used to optimized variants method is used to represent the chromosome
predict surface roughness and GA was employed to optimize the in order to reduce the number of infeasible individual during evo-
surface roughness model. The process parameters considered in lution. Computer simulation results showed that the proposed
this study were feed, depth of cut, radial engage and speed. The optimization approach can find the better results than other algo-
developed RS model was further coupled with a developed GA to rithms proposed previously to significantly reduce the unit pro-
find the optimal process parameters leading to the minimum sur- duction cost. In Rai et al. (2011), the prediction of optimal
face roughness value. The predicted optimal process parameters machining process parameters such as axial depth of cut, radial
was validated with an experimental measurements showing that immersion, feed rate and spindle speed in multi-tool milling oper-
GA improved the surface roughness respect to non-optimized ation was done based on a model named GA-MPO (GA based mill-
experimental tests from 13% to 27% depending on the different ing parameter optimisation system). From the results, the
examined process parameters. By coupling developed RS model developed system enhanced functional capabilities and gives accu-
with GA, the optimization methodology is effective and can be rate prediction compared to other models. Zeng, E, Yang, and Li
effective if the developed RS model is accurate. In Zain et al. (2011) built a soft-sensing model for optimizing machining process
(2010a), GA was employed to find the optimal process parameters parameters such as rotate speed, speed and depth of cutting based
of end milling and abrasive waterjet operation. The machining pro- on support vector machines. Adaptive GA was used to optimize the
cess parameters selected for end milling are cutting speed, feed allowable error, positive aligned and the kernel function parame-
rate and radial rake angle. The results of GA are capable of estimat- ter. After being optimized 300 steps, the average relative error
ing the optimal process parameters in end milling operation com- tended to saturation training was 4.0%; the test error was less than
pared to experimental data, regression modelling and RSM by 27%, 2.6%; the average relative error between the Soft-sensing value for
26% and 50%, respectively. the roughness of machining surface under the numerical control.
Gao et al. (2011) established a model of stress and temperature Optimization of five machining processes in abrsive waterjet
field on nickel-based alloy cutting by finite element modeling and (AWJ) machining which are traverse speed, waterjet pressure,
dynamic numerical simulating, and combined high-speed machin- standoff distance, abrasive grit size and abrasive flow rate was pre-
ing test and orthogonality analysis method. The considered sented by Zain et al. (2011a). The results showed that GA found
machining performance is cutting force and tool wear. The tool optimal process parameters that lead to much lower surface
wear and cutting force prediction model has been obtained based roughness value compared to SA. Also in Zain, Haron, and Sharif
on the process parameters of cutting speed, feed per tooth and ax- (2012), the authors proposed the integration of ANN and GA tech-
ial depth of cut optimized by GA. According to An, Feng, and Lu niques to find optimal process parameters value (speed, feed and
(2011) machining process parameter optimization in multi-pass radial rake angle) of end milling machining that lead to minimum
milling operation involves optimal selection of cutting speed, feed value of surface roughness. The experimental results showed that
rate, depth of cut, and the number of passes. A non-linear mathe- the minimal surface roughness value achieved was 0.139 lm and
matical model based on minimum production cost for multi-pass the optimal process parameters were, feed = 167.029 m/min,
milling operations is presented. GA was used to find the optimal speed = (0.025 mm/tooth), and radial rake angle = 4.769°. The
values of the machining process parameters. The method yields authors stated that the surface roughness value achieved was
lower unit production costs compared with the results from the lit- much lower about 26.8%, 25.7%, 26.1% and 49.8%, compared to
erature and machining data handbook. In An (2011), mathematical the experimental, regression, ANN and RSM results, respectively.
model based on the minimum production cost criterion is devel- The experiments also reduced the mean surface roughness value
oped. The machining process parameters of multi-pass turning and number of iterations about 0.61% and 23.9%, respectively com-
operation are selected such as speeds, feed rates and depths of pared to the conventional GA results. Table 1 summarized the lat-
cut. The constraints of the models include tool life, surface rough- est researches in optimizing process parameters of traditional and
ness, cutting force and cutting power consumption. Optimal values modern machining using GA techniques.
of machining parameters were found by GA and two other meth-
ods which are integer programming and nonlinear programming.
The model generates lower unit production costs compared with 3. Simulated annealing
the results from the literature and machining data handbook.
Kilickap, Huseyinoglu, and Yardimeden (2011) employed three SA optimization technique is based on random numbers for the
machining process parameters which are cutting speed, feed rate, evaluation of the objective function that gives global optimum
and cutting environment is selected to find the optimal process solution (Bharathi & Baskar, 2010). SA was proposed by Kirkpa-
parameters in drilling operation. A mathematical model was devel- trick, Gelatt, and Vecchi (1983) to find the optimal global cost func-
oped; subsequently RSM and GA were used to determine the opti- tion that may possess several local optima (Bertsimas & Tsitsiklis,
mal process parameters for minimizing the surface roughness. The 1993; Cerny, 1985). SA technique imitates the process of gradual
predicted and measured results values were quite close, which cooling of metals in nature. Compared to other global optimization
indicates that the developed model can be effectively used to pre- such as GA and TS, SA is easier to put into practice and provide
dict the surface roughness. In the study of Kuruvila and Ravindra good solution for many combinatorial problems. The parameters
(2011), process parameters of modern machining Wire-cut Electro of standard SA include initial temperature and decrement (cool
Discharge (WEDM) were chosen such as pulse-on duration, cur- down) factor. In Rao, Pawar, and Davim (2010b), the researchers
rent, pulse-off duration, bed-speed and flushing rate. Taguchi’s employed SA techniques to optimize process parameters of
technique and GA were used to determine parametric influence mechanical type advanced machining and the result shows that
and optimal process parameters. The results confirmed the effi- SA outperformed the GA techniques.
ciency of the approach employed for optimization of process
parameters. Xie and Guo (2011) proposed a new approach by com-
bining GA with a pass enumerating method to minimize unit pro- 3.1. SA methodology
duction cost in multipass turning. In the pass enumerating method,
the number of all possible rough cuts is calculated in order to di- The SA optimization flowchart is shown in Fig. 3 and the SA
vide the whole complicated problem into several sub-problems. algorithms are as follows (Yang et al., 2009):
9914 N. Yusup et al. / Expert Systems with Applications 39 (2012) 9909–9927

Table 1
Summary of recent GA techniques in optimizing machining process parameters.

No Author/year Process parameters Machining Machining Remarks

process performance
1. Rai et al. (2011) Axial depth of cut, radial immersion, feed rate Multi-tool Machining time GA-MPO enhanced functional capabilities and
and spindle speed milling gives accurate prediction compared to other
models
2. Zeng et al. (2011) Rotate speed, speed and depth of cutting N/A Surface roughness The average relative error tended to
saturation training was 4.0%; the test error
was less than 2.6%
3. Gao et al. (2011) Bonding wear, feed per tooth and axial depth High speed Cutting force tool, The influence of cutting speed on cutting force
of cut machining tool life is smaller than feed per tooth and axial depth
(nickel-based of cut
alloy cutting)
4. An et al. (2011) Speed, feed rate, depth of cut, and the number Multi-pass Production costs The method yields lower unit production
of passes milling costs compared with the results from the
literature and machining data handbook
5. An (2011) Speed, feed rate and depth of cut Multi-pass Production costs Lower unit production costs compared with
turning the results from the literature and machining
data handbook
6. Kilickap et al. (2011) Cutting speed, feed rate, and cutting Drilling Surface roughness The developed model can be effectively used
environment to predict the surface roughness
7. Kuruvila and Pulse-on duration, current, pulse-off duration, WEDM Dimensional error, The results confirm the efficiency of the
Ravindra (2011) bed-speed and flushing rate surface roughness, approach employed for optimization of
volumetric MRR process parameters in this study
8. Ganesan et al. Depth of cut, cutting speed and feed Multi-pass Production time GA and PSO have been employed to find the
(2011) turning optimal machining parameters for the
continuous profile
9. Xie and Guo (2011) Depth of cut, cutting speed and feed Multi-pass Production costs The optimization approach can find the better
turning results than other algorithms proposed
previously to significantly reduce the unit
costs
10. Zain et al. (2010a) Cutting speed, feed rate and radial rake angle End milling Surface roughness GA is capable of estimating the optimal
process parameters compared to
experimental data, regression modelling and
RSM by 27%, 26% and 50%, respectively
11. Zain et al. (2011a) Traverse speed, waterjet pressure, standoff AWJ Surface roughness The results show that GA found optimal
distance, abrasive grit size and abrasive flow surface roughness value compared in
rate regression and experimental
12. Zain et al. (2012) Cutting speed, feed rate and radial rake angle End milling Surface roughness Compared to the conventional GA, the
proposed techniques showed good results
where it reduced the mean value of surface
roughness and number of iterations by 0.61%
and 23.9%, respectively
13. Zain et al. (2011c) Radial rake angle, cutting speed and feed End milling Surface roughness The proposed integration of SA and GA gives a
lower number of iterations compared to
conventional techniques of SA and GA
14. Sultana and Dhar Feed rate, pressure, flow rate and high Turning Cutting The results show that machining performance
(2010) pressure coolant temperature, chip can be estimated by the predictive models
reduction co-
efficient and surface
roughness
15. Yongzhi et al. (2010) Axial depth-of-cut, radial depth-of-cut and High speed Cutting force, metal The result shows that it is possible to select
helical angle milling removal rate optimum for obtaining minimum cutting
force and reasonably good metal removal rate
16. Pasam et al. (2010) Ignition pulse current, short pulse duration, WEDM Surface roughness The optimal values of machining process
time between two pulses, servo speed, servo parameters at level for the selected range and
reference voltage, injection pressure, wire workpiece material are obtained
speed and wire tension
17. Ansalam Raj and Feed, speed and depth of cut Dry turning Surface roughness The proposed IGA is more effective and
Narayanan applies the realistic machining problem more
Namboothiri (2010) efficiently than does the conventional GA
(CGA)
18. Alam et al. (2010) Speed, feed rate, and depth of cut NC milling Surface roughness It is observed that cutting speed has the most
significant influence on surface roughness
followed by feed and depth of cut
19. Xu et al. (2010) Feed rate, depth of cutting, cutting width Milling Cutting force, tool The optimization results show the
life and machined optimization system can improve the
surface roughness, productivity of milling Ti6Al4V
metal removal rate
20. Saffar and Razfar Cutting speed, feed rate and radial rake angle End milling Cutting force The obtained results indicate that the
(2010) optimized parameters are capable of
machining the workpiece more accurately and
with better surface finish
21. Bharathi and Baskar Number of passes, cutting speed, feed, and Single pass Production cost, From the experiments GA did not give better
(2010) depth of cut turning multi- metal removal rate results compared to PSO but not gives better
pass turning, results than SA in the three turning operation
 N. Yusup et al. / Expert Systems with Applications 39 (2012) 9909–9927 9915

Table 1 (continued)

No Author/year Process parameters Machining Machining Remarks

process performance
and surface
grinding
22. Jayabal and Bit diameter, spindle speed, and feed rate Drilling Thrust force, torque, minimum drill forces are obtained by
Natarajan (2010) and tool wear operating the machine at lower drill bit
diameter, higher speed, and lower feed rate
23. Xie and Pan (2010) Speed, feed rate and depth of cut Multi-pass Production costs The proposed algorithm is efficient in
turning searching the optimal machining parameters,
which significantly reduce the unit
production cost
24. Del Prete et al. Feed, depth of cut, radial engage and speed Flat end mill Surface roughness GA improved the surface roughness respect to
(2010) non-optimized experimental tests from 13%
to 27%
25. Maji and Pratihar Peak current, pulse-on-time and pulse-duty- EDM Surface roughness, The optimal results found to be satisfactory
(2010) factor MRR and Pareto-optimal front of solutions had
been obtained
26. Zhang and Chen Rotation speed, feed rate, depth of cutting, Milling Tool life, processing The most optimized milling parameters were
(2009) cutting width costs obtained
27. Wang et al. (2009) High speed Surface roughness, The authors stated that the MRR can be
milling MRR achieved in the certain range of surface
roughness by choosing the right cutting
parameters
28. Gao et al. (2008) Current, pulse on time and pulse off time EDM MRR MRR is improved by using optimized
parameters
29. Mohanasundararaju Wheel speed, work speed, traverse speed, in Grinding Surface roughness The two optimization approaches were used
et al. (2008) feed, dress depth and dressing lead namely non-linear programming and GA (GA)
30. Savas and Ozay Depth of cut, workpiece speed, tool speed and Turn milling Surface roughness the errors in measurement regions are smaller
(2008) feed rate than 7% and greater than 2%
31. Saravanan and Cutting speed and feed rate Turning, facing Machining Time GA technique helps the production engineers
Janakiraman (2007) and by maximizing the production rate and
undercutting minimizing the production cost
32. Sankar et al. (2007) Cutting speed, feed rate and depth of cut Multi-pass Production costs The modification in the genetic operators
turning, facing improves the search in a more effective way
and drilling than the classical genetic algorithm
33. Prasad et al. (2007) Cutting speed, feed rate and depth of cut Turning Tool wear The results of the experiments are compared
with traditional technique like dynamic
programming
34. Duran et al. (2007) Cutting feed and feed rate Turning Production rate and The Pareto front margins correspond to or are
production cost comparable to the limits of the high efficiency
cutting range
35. Mahapatra and Discharge current, pulse duration, pulse WEDM MRR, surface The process parameters of WEDM can be
Patnaik (2007) frequency, wire speed, wire tension, and roughness and adjusted to achieve improved machining
dielectric flow. cutting width (kerf). performances simultaneously
36. Parent et al. (2007) Cutting speed, feed rate and depth of cut End milling Production costs GA was proposed to find optimal machining
process parameters
37. Jain et al. (2007) UM Amplitude of vibration, frequency of UM, AJM, WJM, MRR GA was used for solving the formulated
vibration, mean diameter of abrasive grains, AWJM optimization models
volumetric concentration of abrasive particles
in slurry, static feed force
AJM Mass flow rate of abrasive particles,
mean radius of abrasive particles, velocity of
abrasive particles,
WJM Water jet pressure at the nozzle exit,
diameter of water jet nozzle, traverse rate of
the nozzle
AWJM Water jet pressure at the nozzle exit,
diameter of abrasive-water jet nozzle,
traverse or feed rate of the nozzle, mass flow
rate of water, mass flow rate of abrasives
38. Palanisamy et al. Cutting speed, depth of cut and feed rate End milling Machining time The optimized process parameters are capable
(2007) of machining the work piece more efficiently
with better surface finish
39. Jain and Jain (2007) Tool feed rate, electrolyte flow velocity Electro- Geometrical The results is compared with the past work
chemical accuracy and showed an improvement in terms of
machining geometrical accuracy
40. Lee et al. (2007) Rotation speed, feed rate, depth of cutting, Milling Surface roughness, It has been investigated that optimized
cutting width MRR machining conditions can be selected to
obtain the high-quality surface within
allowable reliability while maintaining a
high-quality surface, under the given desired
MRR
41. Singh and Rao Cutting speed and feed Hard turning Surface roughness The GA gives minimum values of surface
(2007) roughness and their respective optimal
conditions
9916 N. Yusup et al. / Expert Systems with Applications 39 (2012) 9909–9927

response, yp is the certain target value, UCLi is the upper control lim-
Initial Solution
it of i response, LCLi is the lower control limit of i response, l: mean
value of experimental data, and e is the standard deviation of exper-
Evaluate imental data.

3.2. Application of SA
No
Solution
accepted? Kolahan and Abachizadeh (2008) developed SA algorithm to
optimize machining process parameters in turning operation on
cylindrical workpieces. Three process parameters of turning oper-
Yes
Update the current ation were chosen which are cutting speed, feed rate and cutting
solution depth. The machining performance considered in this study is to
minimize the machining cost. The optimized process parameters
of cutting speed, feed rate and cutting depth are 145 m/min,
Change Generate a new 0.25 mm/rev, and 2.75 mm, respectively. The total cost achieved
temperature No solution is $37.58. The computational results clearly show that the pro-
posed optimization procedure has considerably improved total
Yes
operation cost by optimally determining machining parameters.
Decrease In Satishkumar and Asokan (2008), process parameters of CNC
multi-tool drilling system were optimized to minimize production
cost and incorporate various technological and machine tool con-
No
Terminate the straints. Three evolutionary techniques were considered such as
search GA, SA and ACO to find the optimal process parameters of the
machining operation.
Yes Yang (2009) proposed an optimization methodology for the
Optimal solution selection of best process parameters in electro-discharge machin-
ing. There are four process parameters selected for EDM machining
Fig. 3. SA optimization flowcharts (Zain et al., 2010b).
which are discharge current, source voltage, pulse-on time and
pulse-off time. Process parameters were optimized by SA technique
to maximize the MRR on top of minimize the surface roughness. The
(i) Choose a randomly generated initial point X0, a termination optimal surface roughness achieved is 2.07 lm and the maximum
temperature Tlow. Also set number of iterations (N) to be per- value of MRR is 54.93 g/h. Kolahan and Khajavi (2009) evaluated
formed at a particular temperature and iteration counter the influences of AWJ process parameters such as nozzle diameter,
t = 0. jet traverse rate, jet pressure and abrasive flow rate in cutting
(ii) Evaluate the value of objective function E1 = f(Xt). 6063-T6 aluminum alloy. The Taguchi method and regression mod-
(iii) Calculate a neighborhood point Xt+1 using random perturba- eling were used in order to establish the relationships between input
tion and evaluate objective function at Xt+1 as E2 = f(Xt+1). and output parameters. SA was used to optimize the AWJ process
(iv) Calculate DE = E2  E1. parameters. The settings of SA parameters in this study are as fol-
(v) If DE<0, accept the point. That is Xt = Xt+1 and E1 = E2. Set lows: initial temperature (T0) = 250, cooling rate (a) = 0.98 and the
t = t + 1 and go to step (vi) termination criteria = 500 iterations. The objective is to determine
(vi) If DE P 0, create random number r in the range (0, 1) and a suitable set of process parameters that can produce a desired depth
check whether r 6 exp(DE/T). If satisfied then set t = t + 1 of cut. The results confirmed the effectiveness of the proposed model
and go to step-6. Else begin with new initial point Xt and and optimization procedure where all the process parameters devi-
go to step-3. ate from their desired values by less than 0.5%.
(vii) If t > N go to step-7. In the study by Zain, Haron, and Sharif (2010b), three parameters
(viii) Reduce the temperature periodically by a factor k1 according of end milling were considered for minimizing surface roughness.
to T = k1T and go to step (iii) From the experiments, it was recommended that process parame-
(ix) If T 6 Tlow then terminate the process. ters should be set at the highest cutting speed, lowest feed and high-
est radial rake angle in order to achieve the minimum surface
In Chen, Lin, Yang, and Tsai (2010), to define fitness function of roughness of 0.1385 lm. The minimum surface roughness was
S(x), the formulation of using SA techniques is defined by the fol- much lower than the experimental sample data, regression model-
lowing formula: ling and RSM technique by 27%, 26% and 50%, respectively. Also in
Minimize, Zain et al. (2011a) five parameters of AWJ in cutting 6063-T6 alumi-
num alloy such as traverse speed, waterjet pressure, standoff dis-
X
k
tance, abrasive grit size and abrasive flow rate were selected to
SðxÞ ¼ ðyti  ypi Þ2 ð1Þ
find the optimal surface roughness. SA was used to optimize the
i¼1
AWJ process parameters and the computational results prove the
Subject to, effectiveness of the proposed model and optimization procedure.
The study of Chen et al. (2010) analyzed WEDM process param-
LCLi 6 ypi 6 UCLi ð2Þ eters during manufacture of pure tungsten profiles. The pulse on
LCL ¼ l  ne; n ¼ 1; 2; . . . ; N ð3Þ time, the pulse off time, arc off time, the servo voltage, the wire
UCL ¼ l þ ne; n ¼ 1; 2; . . . ; N ð4Þ feed rate, the wire tension and the water pressure were selected
as the WEDM process parameters. Three considered machining
where, is the x is the process parameters, K is the total number of performances are the cutting velocity, surface roughness and
response which is nominal the best type and has certain target, yt roughness maximum. Integrate BPNN/SAA approaches was
is the predicted value of i response that is a nominal the best type proposed and SAA techniques was used to find the most optimal
 N. Yusup et al. / Expert Systems with Applications 39 (2012) 9909–9927 9917

process parameters. The estimated optimal process parameters 4. Particle swarm optimization
are: pulse on time of 0.42 ls, pulse off time of =12.15 ls, arc off
time = 13.73 ls, servo voltage = 45.17 V, wire feed rate = 10.32 m/ PSO technique was introduced by Kennedy and Eberhart (1995)
mm, wire tension = 1751.07 gf, and water pressure = 15.21 kgf/ to solve continuous optimization problems (Li, Yao, Gao, Liu, &
cm2. The predicted machining performance cutting veloc- Yuan, 2008). The swarm is composed of volume-less particles with
ity = 7.8558 m/min, surface roughness = 1.1786 lm roughness stochastic velocities, each of which represents a feasible solution.
maximum = 10.7873 lm. Rao and Pawar (2010b) optimized the The algorithm finds the optimal solution through moving the par-
process parameters of multi-pass milling operation such as the ticles in the solution space.
number of passes, depth of cut, cutting speed and feed to minimize
the production time (i.e., maximization of production rate). SA was 4.1. PSO methodology
employed to find the optimal process parameters. The results of SA
were compared with the previously published results obtained by The implementation of PSO is very simple and needs only a few
using other optimization techniques, ABC and PSO optimization. lines programming code. The flow chart of the PSO algorithm is de-
Zain, Haron, and Sharif (2011b) proposed the integration of picted in Fig. 5. It requires uncomplicated mathematical operators;
ANN and SA techniques to optimize the process parameters of therefore it is computationally economical in terms of both memory
AWJ such as traverse speed, waterjet pressure, standoff distance, requirements and speed. PSO has features of both GA and evolution
abrasive grit size and abrasive flow rate. The machining perfor- strategies (Zŭperl, Cŭs, & Gecevska, 2007). The PSO framework for
mance measured in this study was surface roughness. In this study, process parameter optimization is depicted in Fig. 4. The steps of
the integration of ANN and SA techniques were divided into two optimizing process parameters of milling operation using PSO was
categories namely ANN-SA type1 and ANN-SA type 2. From the given by Zŭperl, Cŭs, and Gecevska (2007) as follows.
experimental results, the proposed integrations system has been
successfully optimized process parameters of AWJ and gave a min- (i) Generation and initialization of an array of 50 particles with
imal value of surface roughness = 1.523 lm. Also in Zain, Haron, random positions and velocities. Velocity vector has two
and Sharif (2011c), two soft computing techniques which are SA dimensions, feed rate and spindle speed.
and GA were integrated to find the optimal process parameters (ii) Evaluation of objective (cutting force surface) function for
of end milling machining that lead to the minimum value of sur- each particle.
face roughness. The integration of SA-GA was also divided into (iii) The cutting force values are calculated for new positions of
two categories which are SA-GA type1 and SA-GA type2. The re- each particle. If a better position is achieved by particle,
sults of the experiments showed that the proposed technique the pbest value is replaced by the current value.
was effective in optimizing the process parameters of end milling (iv) Determination if the particle has found the maximal force in
machining and the time for searching the optimal solution can also the population. If the new gbest value is better than previous
be made faster. The latest researches in optimizing process param- gbest value, the gbest value is replaced by the current gbest
eters of traditional and modern machining using SA techniques is value and stored. The result of optimization is vector gbest
shown in Table 2. (feedrate, spindle speed).

Table 2
Summary of recent SA techniques in optimizing machining process parameters.

No. Author/year Process parameters Machining process Machining Remarks

performance
1. Zain et al. Radial rake angle, cutting speed and feed End Milling Surface roughness The minimum surface roughness was much lower
(2010b) compared to experimental, regression and RSM
2. Zain et al. Traverse speed, waterjet pressure, standoff AWJ Surface roughness The optimal surface roughness value in SA is more
(2011a) distance, abrasive grit size and abrasive flow less compared to experimental, regression, and GA
rate
3. Zain et al. Traverse speed, waterjet pressure, standoff AWJ Surface roughness The results showed that an optimal values of
(2011b) distance, abrasive grit size and abrasive flow surface roughness and a lower number of
rate iterations are obtained using the proposed
techniques
4. Zain et al. Radial rake angle, cutting speed and feed End milling Surface roughness The proposed integration of SA and GA gives a
(2011c) lower number of iterations compared to
conventional techniques of SA and GA
5. Bharathi and Number of passes, cutting speed, feed, and Single pass turning Production cost, From the results SA did not give better results
Baskar depth of cut multi-pass turning, metal removal rate compared to PSO and GA in the three turning
(2010) and surface grinding operation
6. Yang et.al., Discharge current, source voltage, pulse-on EDM Surface roughness, The optimal surface roughness achieved is 2.07
(2009) time and pulse-off time metal removal rate and the maximum value of MRR is 54.93
7. (Chen et al., Pulse on time, the pulse off time, arc off WEDM Cutting velocity, From the results and conformation of experiments,
2010) time, the servo voltage, the wire feed rate, surface roughness, BPNN/SAA method is effective tool for the
the wire tension and the water pressure metal removal rate optimization of WEDM process parameters
8. Rao and Number of passes, depth of cut, cutting Multi-pass milling Production time The results are compared with the previously
Pawar speed and feed published results obtained by using other
(2010b) optimization techniques
9. Kolahan and Nozzle diameter, jet traverse rate, jet AWJ Depth of cut SA algorithms provide an effective and speedy
Khajavi pressure and abrasive flow rate optimization technique
(2009)
10. Kolahan and Cutting speed, feed rate and cutting depth Turning Machining cost The results improved total operation cost
Abachizadeh
(2008)
11. Satishkumar Cutting speed, feed rate, and cutting Multi-tool drilling Production cost GA and ACO also considered in this study in
and Asokan environment optimizing the machining process parameters
(2008)
9918 N. Yusup et al. / Expert Systems with Applications 39 (2012) 9909–9927

Given cutting Algorithm Objective

parameters(s) parameters

Cutting Prediction of
Optimization Constraints
database machining
methodology
performance

Best individual

Evaluation

Optimal process
parameters

Fig. 4. Framework PSO process parameter optimization methodology (Li et al., 2008).

(v) Computation of particles’ new velocity. the solution while speeding up the convergence process. A new
(vi) Update particle’s position by moving towards maximal cut- technique has been proposed by Huang, Li, and Lin (2007) by using
ting force. the combination of wavelet neural network (WNN) algorithm and
(vii) Steps (i) and (ii) are repeated until the iteration number modified PSO for solving tool wear detection and estimation. By
reaches a predetermined iteration. using the Daubechies-wavelet, the cutting power signal is decom-
posed into approximation and details. The energy and square-error
4.2. Application of PSO of the signals in the detail levels is used as characters which indi-
cating tool wear, the characters are input to the trained WNN to
Zŭperl, Cŭs, and Gecevska (2007) employed PSO to optimize estimate the tool wear. The results of the experiments were com-
process parameters of milling machining. A predictive model was pared with BP neutral network, conventional WNN and GA-based
developed using ANN to predict the cutting forces during machin- WNN. The results showed a faster convergence and more accurate
ing and PSO was used later to obtain optimal process parameters of estimation of tool wear.
milling machining such as cutting speed and feed rates. The results According to Rao, Pawar, and Shankar (2008), process parame-
were compared with other evolutionary techniques such as GA and ters of electrochemical machining (ECM) such as the tool feed rate,
SA and proved that the proposed technique improved the quality of electrolyte flow velocity, and applied voltage play a significant role
in optimizing the measures of process performance. PSO was used
to find the optimal combination of process parameters for an ECM
operation. There are three machining performance measured
Population generation
which includes dimensional accuracy, tool life, and the MRR. The
si = (feeding, speed); i = 1-50 results of the proposed algorithm are compared with the previ-
ously published results obtained by using other optimization tech-
niques. The process parameters of milling operation such as
Population evaluation
spindle speed and feed rate were considered to be optimized in
Fi (si) the study of Li et al. (2008). The considered machining perfor-
mances were cutting force, tool-life, surface roughness and cutting
power. An algorithm for process parameters optimization known
as cutting parameters optimization (CPO) was introduced and
Population evaluation Fi (si) > PSO technique was employed to optimize the process parameters.
pbesti From the experimental results, the authors concluded that PSO in
pbesti = Fi (si) & pbesti = si
Yes optimizing process parameters can converge quickly to a consis-
tent combination of spindle speed and feed rate. An application
No was build in Duran, Rodriguez, and Consalter (2008) to select suit-
able cutting tool geometry in a given combination of material work
Fk (sk) > v i = w⋅ v i + c1 ⋅ rand1 ⋅ (pbest piece and cutting tool material. PSO was employed to find the opti-
pbesti for − s i) + c2 rand2 ⋅ (gbest − s i) mal cutting tool geometry and evaluates a selected number of indi-
all i viduals (that represent a set of feasible tool angle) until a
termination criteria is satisfied. In the experiments, a range of sim-
Yes
ulations were carried out to confirm the performance of the algo-
rithm and to show the usefulness of the suggested approach.
Optimal process parameters si = si + v i
Chen and Li (2008) proposed an improved PSO with opposition
gbest = k
mutation (OMPSO) to select satisfied process parameter (depth of
cut, feed rate, grit size) of grinding process. According to the
Fig. 5. PSO optimization for optimal process parameters (Zŭperl, Cŭs, & Gecevska, researcher, OMPSO has the same tuning parameters as PSO and
2007). easy to use. The experiment result was compared to other
 N. Yusup et al. / Expert Systems with Applications 39 (2012) 9909–9927 9919

evolutionary techniques such as GA, PSO and landscape adaptive the paper resolves a complex, multi-constrained, nonlinear turning
PSO (LAPSO). It was obtained that the proposed technique was model into a single, unconstrained objective problem. The best
effective to solve grinding process optimization problem. The opti- solution in each generation is obtained by comparing the unit pro-
mization of process parameters for constant cutting force was dis- duction cost and the total non-dimensional constraint violation
cussed based-on virtual machining by Zhao, Li, Yao, and Liu (2008). among all of the particles.
PSO was employed to find the optimal process parameters (spindle Razfar, Asadnia, Haghshenas, and Farahnakian (2010) proposed
speed and feed rate). The framework of virtual machining based a PSO-based neural network to create a predictive model for the
cutting parameters optimization was established. Then two con- surface roughness level that is based on experimental data col-
trolled experiments were conducted to demonstrate the effective- lected on e face milling X20Cr13 stainless steel. The optimization
ness of cutting parameters optimization both with physical cutting problem is then solved using a PSO-based neural network for opti-
and computer simulation. The results of experiment showed that mization system (PSONNOS). A good agreement is observed be-
machining process with constant cutting force can be achieved tween the predicted surface roughness values and those obtained
via cutting parameters optimization based on virtual machining. in experimental measurements performed using the predicted
Tang, Landers, and Balakrishnan (2008) investigated two-tool par- optimal machine settings. The PSONNOS is compared to the GA
allel turning (single pass and multipass) process parameters opti- optimized neural network system (GONNS). PSO was used by
mization problem. PSO was employed to determine optimal Zheng and Ponnambalam (2010) to optimize the multipass turning
machining time. The results showed that the proposed technique process which has rough machining and then a finish machining.
performed better than exhaustive search algorithm in terms of The considered objective function is minimization of unit produc-
machining time and required computational time. tion cost. The performance is evaluated by comparing results of
Optimization of process parameters in turning operation was PSO with GA and SA that were reported by earlier researchers. Bha-
studied by Xi and Liao (2009). There are three objectives control rathi and Baskar (2010) used three evolutionary optimization tech-
parameters, which are machining time, machining accuracy and niques such as SA, GA and PSO to explore the optimal machining
machining cost. The model was established using multiple targets process parameters for single pass turning operation, multi-pass
nonlinear programming model. The process parameters were opti- turning operation, and surface grinding operation. The most affect-
mized using PSO. From the experimental results, the researchers ing machining parameters are considered such as number of
found the optimal process parameters (cutting speed and feed rate) passes, cutting speed, feed, and depth of cut. The machining perfor-
value is much smaller than the value calculated by the experience mances considered in this study are the production cost and the
of the objective function value. The optimized cutting parameters metal removal rate. The result of PSO is 4.7% and 1% better than
values are better meet the user’s optimization goals than obtained GA and SA, respectively. In multi-pass turning operation, the result
from the experience or manuals on the recommended values and of PSO is 12.5% and 19.8% better than GA and SA, respectively. In
more reference value. PSO was used in the research by Escamilla, grinding operation, the result of PSO is 6.2% and 1% better than
Perez, Torres, Zambrano, and Gonzalez (2009) to find optimal pro- GA and SA, respectively. PSO also gave better results compared to
cess parameters of the titanium’s machining process. For the mod- GA and SA in the three turning operations.
elling and prediction of the process outputs, ANN network was The machining performance considered in Bharathi and Baskar
employed for Vertical Machining Center Bridgeport VMC 760. (2011) are machining time and surface roughness. CNC turning
The machining the tool was an end mill coated with Aluminium machine was employed to conduct experiments on brass, alumin-
Titanium Nitride (AlTiN). The obtained surface roughness value ium, copper, and mild steel. PSO has been used to find the optimal
was 0.68 lm and the optimal process parameters values of speed, machining parameters for minimizing machining time subjected to
feed and depth of cut is 2798 m/min, 425 mm/rev and 0.5 mm, desired surface roughness. Physical constraints for both experi-
respectively. From the results of ANN modelling and PSO optimiza- ment and theoretical approach are cutting speed, feed, depth of
tion, it can be successfully applied to multi-objective optimization cut, and surface roughness. It is observed that the machining time
of titanium’s machining process. Modeling and optimizing process and surface roughness based on PSO are nearly same as that of the
parameters in pulsed laser micromachining is the main focused in values obtained based on confirmation experiments; hence, it is
Ciurana, Arias, and Ozel (2009). Selection of process operational found that PSO is capable of selecting appropriate machining
parameters is highly critical for successful laser micromachining. parameters for turning operation. In the research by Farahnakian,
The relation between process parameters and quality characteris- Razfar, Moghri, and Asadnia (2011), the effect of process parame-
tics has been modeled with ANN. Predictions with ANNs have been ters of high speed steel end mill such as spindle speed and feed rate
compared with experimental work. Multiobjective PSO of process are considered. Nanoclay (NC) content on machinability properties
parameters for minimum surface roughness and minimum volume of polyamide-6/nanoclay (PA-6/NC) nanocomposites was studied
error is carried out. This result shows that the proposed model and for modeling cutting forces and surface roughness by using PSO-
swarm optimization approach are suitable to identify optimum based neural network (PSONN). The results indicate that the nano-
process settings. In the research by Prakasvudhisarn, Kunnapap- clay content on PA-6 significantly decreases the cutting forces, but
deelert, and Yenradee (2009), process parameters of CNC end mill- does not have a considerable effect on surface roughness. The ob-
ing were selected such as feed rate, spindle speed, and depth of cut tained results for modeling cutting forces and surface roughness
to find the minimum surface roughness. Support vector machine also showed a remarkable training capacity of the proposed algo-
(SVM) was proposed to capture characteristics of roughness and rithm compared to the conventional neural network. Yang, Guo,
its factors. PSO technique is then employed to find the combination and Liao (2011a) proposed a methodology, fuzzy PSO (FPSO) algo-
of optimal process parameters. The results showed that coopera- rithm to distribute the total stock removal in each of the rough
tion between both techniques can achieve the desired surface passes and the final finish pass which based on fuzzy velocity
roughness and also maximize productivity simultaneously. Srini- updating strategy to optimize the machining parameters imple-
vas, Giri, and Yang (2009) proposed a methodology for selecting mented for multi-pass face milling. The optimum value of machin-
optimum machining parameters in multi-pass turning using PSO. ing parameters including number of passes, depth of cut in each
The considered machining performances are production cost and pass, speed, and feed are obtained to achieve minimum production
machining time. PSO was implemented to obtain the set of cutting cost. The proposed methodology for distribution of the total stock
parameters that minimize unit production cost subject to practical removal in each of passes is effective, and the proposed FPSO algo-
constraints. The dynamic objective function approach adopted in rithm does not have any difficulty in converging towards the true
9920 N. Yusup et al. / Expert Systems with Applications 39 (2012) 9909–9927

optimum. From the given results, the proposed schemes may be a (vii) Calculate the probability values Pi for the solutions xi by
promising tool for the optimization of machining process parame- means of their fitness values using Eq. (5):
ters. Also in Yang, Guo, and Liao (2011b), the researchers proposed
fuzzy global and personal best-mechanism-based multi-objective fit
P i¼ PSN i ð5Þ
PSO (F-MOPSO) to optimize the machining parameters. The pro- i¼1 fit i
posed algorithm was used to optimize the machining parameters
is developed to solve such a multi-objective optimization problem In order to calculate the fitness values of solutions, the following
in optimization of multi-pass face milling operation. It was found equation is employed (6):
that the F-MOPSO does not have any difficulty in achieving well- (
1
1þfi
; if f i P 0
spread Pareto optimal solutions with good convergence to true fiti ¼ ð6Þ
Pareto optimal front for multi-objective optimization problems. 1 þ abs f ðiÞ; if f i < 0
Costa, Celano, and Fichera (2011) used hybrid PSO for minimizing
(viii) Normalize Pi values into [0, 1]
the production cost associated with multi-pass turning problems.
(ix) produce the new solutions (new positions) vi for the onlook-
The proposed optimization technique consists of a PSO-based
ers from the solutions xi, selected depending on Pi, and eval-
framework wherein a properly embedded SA, namely an SA-based
uate them.
local search, aims both to enhance the PSO search mechanism and
(x) apply the greedy selection process for the onlookers
to move the PSO away from being closed within local optima. The
between xi and vi.
used process parameters are cutting speed, feed rate and depth of
(xi) determine the abandoned solution (source), if exists, and
cut. Five different test cases based on the multi-pass turning of a
replace it with a new randomly produced solution xi for
bar stock have been used for comparing the performance of the
the scout using Eq. (7):
proposed technique with other existing methods. In Ganesan,
Mohankumar, Ganesan, and Ramesh Kumar (2011), the machining xij ¼ minj þ randð0; 1Þ  ðmaxj  minj Þ ð7Þ
parameters in multipass turning such as depth of cut, cutting speed
and feed are considered. These process parameters were optimized (xii) Memorize the best food source position (solution) achieved
using GA and PSO for minimization of production time. In GA the so far
combination of optimal process parameters speed, feed and depth (xiii) cycle = cycle + 1
of cut achieved is 2185.714 m/min, 0.22 mm/rev and 0.87 mm, (xiv) until cycle = Maximum Cycle Number (MCN)
respectively with minimum production time = 3.131 min. In PSO,
combination of optimal process parameters speed, feed and depth 5.2. Application of ABC
of cut achieved is 3500.000000 m/min, 0.367393 mm/rev and
0.010000 mm, respectively with minimum production The abilities of ABC algorithm have been previously discussed
time = 0.000180 min. It was found that PSO gave better results by a few of researchers. In the research of Rao and Pawar
compared to GA. Table 3 summarized the latest researches in opti- (2010b), the researchers employed seven steps to optimize the
mizing process parameters of traditional and modern machining process parameters of multi-pass milling operation. The steps in
using PSO techniques. ABC optimization of process parameters are (i) parameter selec-
tion, (ii) calculate the nectar amount of each food source, (iii)
determine the probabilities by using the nectar amount, (iv) calcu-
5. Artificial bee colony optimization late the number of onlookers bees, which will be sent to food
sources, (v) calculate the fitness value of each onlooker bee, (vi)
ABC is the recent swarm-based algorithm that mimics the for- valuate the best solution and (vii) update the scout bee. Various
aging behaviour of swarm honey bee. Similar to the concept of WEDM parameters such as pulse-on time, pulse-off time, peak cur-
ACO and PSO, this exploration algorithm is capable of tracing good rent, and servo feed setting were optimized. A mathematical model
quality of solutions. was developed using RSM and the machining performance mea-
sured is machining speed and surface roughness. ABC was em-
5.1. ABC methodology ployed to find the optimal combination of process parameters
with an objective of achieving maximum machining speed for a de-
There are three control parameters that perform significant role sired value of surface finish.
in the ABC which is the number of colony, the value of limit and the Optimization of process parameters of advance machining pro-
maximum loop for searching. The abilities of ABC algorithm have cess known as ultrasonic machining (USM) was considered in the
been discussed by Rao et al. (2008), Karaboga (2009), Benala, Jam- study of Rao, Pawar, and Davim (2010a). The machining perfor-
pala, Villa, and Konathala (2009), Akay and Karaboga (2010), mance is MRR. Five process parameters, amplitude of ultrasonic
Karaboga and Akay (2009) Rao and Pawar (2010b) and Akay and vibration, frequency of ultrasonic vibration, mean diameter of
Karaboga (2009). The flowchart of ABC is shown in Fig. 6. The de- abrasive particles, volumetric concentration of abrasive particles,
tailed pseudocode to solve the optimization is as follows (Karaboga and static feed force, and three evolutionary optimization tech-
& Akay, 2009): niques, ABC, PSO and harmony search (HS), were considered in
the study. The results of the presented algorithms are compared
(i) initialize the population of solutions xi,j with the previously published results obtained by using GA. In
(ii) evaluate the population the study of (Rao & Pawar, 2010a), process parameters of grinding
(iii) cycle = 1 process were considered for optimization such as wheel speed,
(iv) repeat workpiece speed, depth of dressing, and lead of dressing. The
(v) produce new solutions (food source positions) vi,j in the machining performances are production cost, production rate,
neighbourhood of xi,j for the employed bees using the for- and surface finish subjected to the constraints of thermal damage,
mula vi,j = xi,j + Uij(xi,j  xk,j) (k is a solution in the neighbour- wheel wear, and machine tool stiffness. ABC, PSO and HS optimiza-
hood of i, U is a random number in the range [1, 1]) and tion techniques were used in this study. The results of the algo-
evaluate them rithms were compared with the previously published results
(vi) apply the greedy selection process between xi and vi obtained by using other optimization techniques.
 N. Yusup et al. / Expert Systems with Applications 39 (2012) 9909–9927 9921

Table 3
Summary of recent PSO techniques in optimizing machining process parameters.

No. Author/year Process parameters Machining Machining Remarks

process performance
1. Bharathi and Cutting speed, feed, depth of cut Turning Machining time, PSO is capable of selecting appropriate
Baskar (2011) surface machining parameters for turning operation.
roughness
2. Farahnakian, Cutting speed, feed, depth of cut End milling Cutting forces A very good training capacity of the proposed
Razfar, Moghri, and surface PSONN algorithm
and Asadnia roughness
(2011)
3. Yang et al. Number of passes, depth of cut in each pass, Multi-face Production cost The proposed schemes may be a promising tool
(2011a) speed, and feed milling for the optimization of machining process
parameters
4. Yang et al. Number of passes, depth of cut in each pass, Multi-pass face Production cost The F-MOPSO does not have any difficulty in
(2011b) speed, and feed milling achieving well-spread Pareto optimal solutions
with good convergence to true Pareto optimal
front for multi-objective optimization problems
5. Costa et al. Cutting speed, feed, depth of cut Multi-pass Production cost The performance of the proposed technique was
(2011) turning compared with other existing methods
6. Ganesan et al. Depth of cut, cutting speed and feed Multi-pass Production time PSO produce better results than GA
(2011) turning
7. Razfar et al. Cutting speed, feed, depth of cut, engagement Face milling Surface A good agreement is observed between the
(2010) roughness values predicted by the PSONNOS algorithm
and experimental measurements
8. Zheng and Feed rate, cutting speed, depth of cut Multi-pass Production cost PSO performs better than GA and SA
Ponnambalam turning
(2010)
9. Rao et al. (2010a) Amplitude of ultrasonic vibration, frequency of USM MRR The results of the presented algorithms are
ultrasonic vibration, mean diameter of abrasive compared with the previously published results
particles, volumetric concentration of abrasive obtained by using GA
particles, and static feed force
10. Rao and Pawar Number of passes, depth of cut, cutting speed and Multi-pass Production time The results are compared with the previously
(2010b) feed milling published results obtained by using other
optimization techniques
11. Bharathi and Number of passes, cutting speed, feed, and depth Single pass Production cost, From the results PSO give the best results
Baskar (2010) of cut turning multi- MRR compared to GA and SA in the three turning
pass turning, and operation
surface grinding
12. Xi and Liao Feed rate, cutting speed Turning Machining time, The optimized cutting parameters values are
(2009) machining better meet the user’s optimization goals
accuracy and
machining cost
13. Escamilla et al. Speed, feed and depth of cut End milling Surface PSO optimization it can be successfully applied
(2009) roughness to multi-objective optimization of titanium’s
machining process
14. Ciurana et al. Laser fluence, position of focal plane, laser spot Pulsed laser Surface The proposed models and swarm optimization
(2009) size. translation distance between subsequent micro machining roughness, approach are suitable to identify optimum
laser pulses volume error process settings
15. Prakasvudhisarn Speed, feed and depth of cut CNC end millling Surface Both techniques can achieve the desired surface
et al. (2009) roughness roughness and also maximize productivity
simultaneously.
16. Srinivas et al. Feed rate, cutting speed, depth of cut Multi-pass Production cost, The best solution in each generation is obtained
(2009) turning machining time by comparing the unit production cost and the
total non-dimensional constraint violation
among all of the particles
17. Rao et al. (2008) Tool feed rate, electrolyte flow velocity, and ECM Dimension The proposed algorithm are compared with the
applied voltage accuracy, tool previously published results obtained by using
life, metal other optimization techniques
removal rate
18. Li et al. (2008) Spindle speed, feed rate Milling Cutting force, PSO in optimizing process parameters can
tool-life, surface converge quickly to a consistent combination of
rougness and spindle speed and feed rate
cutting power
19. Duran et al. Cutting speed, power, feed speed, depth of cut Various Tool geometry The selection of the appropriate cutting tool
(2008) geometry is possible in real world environments
20. Chen and Li Depth of cut, feed rate, grit size Grinding MRR The proposed algorithm is an effective method
(2008) for grinding process optimization problem
21. Zhao et al. (2008) Spindle speed and feed rate Milling Cutting forces The machining process with constant cutting
force can be achieved via process parameters
optimization based on virtual machining
22. Liu and Huang Feed and cutting N/A Cost PSO is relevant for solving complicated
(2008) performance nonlinear problem
23. Tang et al. (2008) Spindle speed, feed, and depth of cut Single and Machining time The proposed algorithm is superior to the latter
multipass not only in terms of computational time but
turning also in terms of performance
24. Zŭperl, Cŭs, and Cutting speeds and feed rates Milling Cutting forces Compared with GA and SA the proposed

(continued on next page)

9922 N. Yusup et al. / Expert Systems with Applications 39 (2012) 9909–9927

Table 3 (continued)

No. Author/year Process parameters Machining Machining Remarks

process performance
Gecevska (2007) algorithm can improve the quality of the
solution while speeding up the convergence
process
25. Huang et al. Spindle, Feed rate, width End milling Tool wear The MPSO-trained WNN has a superior
(2007) performance than BP-NN, conventional WNN,
and GA-based WNN

ABC was employed by Samanta and Chakraborty (2011) to find affected zone. The review of the latest researches in optimizing pro-
the optimal combinations process parameters of modern machining cess parameters of traditional and modern machining using ABC
such as ECM, electrochemical discharge machining (ECDM) and techniques was summarized in Table 4.
electrochemical micromachining (ECMM) processes. The results ob-
tained while applying the ABC algorithm for parametric optimiza- 6. Ant colony optimization
tion of these three NTM processes are compared with those
derived by the past researchers, which prove the applicability and ACO algorithm was inspired by the behaviour of the ants in
suitability of the ABC algorithm in enhancing the performance mea- searching of their food sources. The original concept of ant system
sures of the considered NTM processes. The machining performance is introduced by Marco Dorigo in 1992. In ACO, the ant search for
measure include metal removal rate, radial overcut and heat the foods and evaluates the food sources and brings it back to the

Initial food source

position

Calculate the nectar amount

Determine the new food positions

for the employed bees

Calculate the nectar amount

Determine a neighbour food source
position for the onlooker

All onlookers
Select a food source for the onlooker
distributed?

Memorize position of the best food

source

Find the abandoned food source

Produce new position for the exhausted

food source

Is the termination
criteria satisfied?

Yes

Final food position

Fig. 6. Flow of ABC optimization (Karaboga, 2009).

 N. Yusup et al. / Expert Systems with Applications 39 (2012) 9909–9927 9923

Table 4
Summary of recent ABC techniques in optimizing machining process parameters.

No. Author/year Process parameters Machining Machining Remarks

process performance
1. Samanta and Electrolyte concentration, electrolyte flow rate, ECM, Metal removal It is shown that the ABC algorithm can also efficiently
Chakraborty applied voltage Inter-electrode gap ECDM, rate, radial solve the multi- objective optimization problems of
(2011) EMM overcut, heat the modern machining processes
affected zone
2. Rao et al. Amplitude of ultrasonic vibration, frequency of USM Metal removal The results of the presented algorithms are compared
(2010a) ultrasonic vibration, mean diameter of abrasive rate with the previously published results obtained by
particles, volumetric concentration of abrasive using GA
particles, and static feed force
3. Rao and Wheel speed, workpiece speed, depth of dressing, and Grinding Production cost, The results of the algorithms were compared with the
Pawar lead of dressing production rate, previously published results obtained by using other
(2010a) and surface optimization techniques
roughness
4. Rao and Number of passes, depth of cut, cutting speed and Multi-pass Production time The results are compared with the previously
Pawar feed milling published results obtained by using other
(2010b) optimization techniques
5. Rao and Pulse-on time, pulse-off time, peak current, and servo WEDM Machining speed ABC was employed to to find the optimal combination
Pawar feed setting and surface of process parameters with an objective of achieving
(2009) roughness maximum machining speed for a desired value of
surface finish

nest. The ant then leaves a substance named pheromones as their DaemonAction( ). ACO has been used to solve many combinato-
move back to the nest. The quantity of pheromone deposited, which rial optimization problems and other problems which have been
may depend on the quantity and quality of the food, will guide other demonstrated by Martens et al. (2007), Baucer, Bullnheimer,
ants to the food source (Dorigo & Blum, 2005). The other ants tend to Hartl, and Strauss (2000), Stützle (1997) and Hu, Zhang, Xiao,
follow the paths where pheromone concentration is higher. and Li (2008). According to Venayagamoorthy and Harley
(2007), ACO has an advantage compared to GA and SA when
6.1. ACO methodology the graph may change dynamically, since the ant colony
algorithm can be run continuously and adapt to changes in
There are three main function in the ACO technique, which are real time. The computational flowchart of ACO is depicted in
(i) Autosolution construct( ), (ii) PheromoneUpdate( ) and (iii) Fig. 7.

Start

Set current position

Find the best point for the next

move based on ACO

No
ending point?

Yes
Yes
Store path Best path so Back to starting point
far?

No

Pheromone evaporation

Update path pheromones

No
Max iteration

Yes

Stop

Fig. 7. Computational chart of ACO (Brand, Masuda, Wehner, & Yu, 2010).
9924 N. Yusup et al. / Expert Systems with Applications 39 (2012) 9909–9927

Table 5
Summary of recent ACO techniques in optimizing machining process parameters.

No Author/year Process parameters Machining Machining Remarks

process performance
1. Kadirgama et al. Speed, feed rate, axial depth End milling Surface roughness The feed rate was the foremost factors affecting the surface roughness
(2010) and radial depth
2. Cŭs, Balic, and Speed, feed rate and depth of Turning Production cost The proposed ANFIS-ACO approach outperforms GA and SA with
Zŭperl (2009) cut Production rate 16.02% and 23.08% improvement, respectively
3. Wu and Yao Speed, feed rate and depth of Multi-pass Production cost The researchers suggested the proposed technique for rapid cutting
(2008) cut turning parameter selection

Fig. 8. Numbers of researches in machining optimization using various evolution-

ary techniques (2007–2011).
Fig. 10. Machining process considered in SA.

In Kadirgama, Noor, and Alla (2010), the researchers applied the

combinatorial optimization problems (COP) model to find optimal
surface roughness of end milling machining which consists of:

(i) a search space S defined over a finite set of discrete decision

variables;
(ii) a set X of constraints among the variables;
þ
(iii) an objective function f : S ! R to be minimized.
0

The main features are the updated pheromone values by all the
ants that have completed the trip. The pheromone update for sij
(edge joining cities i and j), is calculated by Eq. (8):
X
m
Tij ð1  qÞ  Tij þ DT kij ð8Þ
k¼1
Fig. 11. Machining process considered in PSO.
where q is the evaporation rate, m is the number of ants, and DTij k
is the quantity of pheromone per unit length laid on edge (i, j) by
the kth ant (Dorigo, Maniezzo, & Colorni, 1991) as shown in Eq. (9):
6.2. Application of ACO
(
Q;
if any k used edge ði; jÞ in its tour
DT kij ¼ Lk
ð9Þ ACO technique has been considered by Cŭs, Balic, and Zŭperl
0; otherwise
(2009) to optimize the process parameters of turning process. In
where Q is a constant and Lk is the tour length of the kth ant. this study, the modelled machining performances were production

Fig. 9. Machining process considered in GA.

 N. Yusup et al. / Expert Systems with Applications 39 (2012) 9909–9927 9925

cost and to maximize production rate (which represented by man- (2008), the researchers presented a cutting optimization model
ufacturing time and cutting quality). The process parameters in- for multi-pass turning operation. A meta-heuristic technique, mod-
clude cutting speed, feed rate and depth of cut. The proposed ified continuous ACO (MCACO), has been proposed to find the opti-
approach uses adaptive neuro-fuzzy inference system (ANFIS) sys- mal machining parameters such as cutting speed, feed rate and
tem and an ACO algorithm to obtain the optimal objective value. depth of cut in order to minimize the unit production cost. From
From the experiment, it was found out that PSO outperforms all the experiment results, it was found that the proposed technique
other algorithms compared to SA, GA, and ANFIS-ACO with the improved the unit production cost compared to other such as float
minimal production cost = $12.235. However, the proposed AN- encoded GA (FEGA), SA, ant’s colony optimization technique (ACO),
FIS-ACO approach outperforms GA and SA with 16.02% and hill climbing (HC) and Newton’s method (NM). By using the pro-
23.08% improvement, respectively. In the research of Wu and Yao posed approach, the researchers also found out that the best pro-
duction cost was $2.203707.
The technique of RSM and ACO was employed by (Kadirgama
et al., 2010) to find the optimal surface roughness in milling mould
aluminium alloys (AA6061-T6). The process parameters chosen in
this study were cutting speed, feed rate, axial depth and radial
depth. From the experiments, the researchers found out that the
feed rate was the foremost factors affecting the surface roughness.
The errors of surface roughness are 4.65%. The optimal combina-
tion of process parameters htat were obtained for minimizing sur-
face roughness are cutting speed = 100 m/min; feed rate = 0.2 mm/
rev, axial depth = 0.1 mm and radial depth = 5 mm. The latest re-
searches in optimizing process parameters of traditional and mod-
ern machining using SA techniques is shown in Table 5.

7. Discussions and conclusions

Fig. 12. Machining process considered in ABC.
From review, we found that GA optimization evolutionary tech-
nique is widely used in optimizing machining process parameters
followed by PSO, SA, ABC and ACO as depicted in Fig. 8. The re-
searches in machining optimization using latest optimization tech-
niques such ABC only started in 2009 and mostly focused on
optimizing process parameters of modern machining such as
WEDM, ECM and as illustrated in Fig. 12. For ACO, we discovered
there is not as much of researches in machining optimization using
this technique from 2007 to 2011. The use of GA and PSO, the most
machining operation employed was Multipass-turning as depicted
in Figs. 9 and 11, respectively. Fig. 10 confirmed that the most
machining process considered in SA technique were end milling
and AWJ. For ACO technique, there were three machining pro-
cesses considered; end milling, turning and multipass turning as
depicted in Fig. 13. In Fig. 14, the most machining performances
considered by the researchers are surface roughness followed by
Fig. 13. Machining process considered in ACO.
machining/production costs and MRR. The application of

Fig. 14. Machining performance considered in GA, SA, PSO, ABC and ACO.
9926 N. Yusup et al. / Expert Systems with Applications 39 (2012) 9909–9927

evolutionary techniques in optimizing machining process parame- Dorigo, M., Maniezzo, V., & Colorni, A. (1991). Positive Feedback as a Search
Strategy, Technical report 91-016. Dipartimento di Elettronica, Politecnico di
ters positively gives good results as proven from the literature.
Milano: Milan, Italy.
Duran, O., Rodriguez, R., & Consalter, L. A. (2008). PSO for selecting cutting tools
geometry. Lecture Notes in Computer Science, 5271, 265–272.
Acknowledgements Duran, O., Barrientos, R., & Consalter, L. (2007). Multi objective optimization in
machining operations. Analysis and Design of Intelligent Systems using Soft
The authors wish to thank the Research Management Center, Computing Techniques, 455–462.
Escamilla, I., Perez, P., Torres, L., Zambrano, P., & Gonzalez, B. (2009). Optimization
UTM and Ministry of Science, Technology and Innovation of Malay-
using neural network modeling and swarm intelligence in the machining of
sia (MOSTI) for financial support through Grant Exploratory Re- titanium (Ti 6Al 4V) alloy. In Paper presented at the 8th Mexican international
search Grant Scheme (ERGS) No. Q.J13000078284L003. conference on artificial intelligence – proceedings of the special session (pp. 33–38),
MICAI 2009.
Farahnakian, M., Razfar, M. R., Moghri, M., & Asadnia, M. (2011). The selection of
References milling parameters by the PSO-based neural network modeling method.
International Journal of Advanced Manufacturing Technology, 1–12.
Ganesan, H., Mohankumar, G., Ganesan, K., & Ramesh Kumar, K. (2011).
Aggarwal, A., & Singh, H. (2005). Optimization of machining techniques – A
Optimization of machining parameters in turning process using genetic
retrospective and literature review. Sadhana – Academy Proceedings in
algorithm and particle swarm optimization with experimental verfification.
Engineering Sciences, 30(6), 699–711.
International Journal of Engineering Science and Technology (IJEST), 3, 1091–1102.
Akay, B., & Karaboga, D. (2010). Artificial bee colony algorithm for large-scale
Gao, D. Q., Li, Z. Y., & Mao, Z. Y. (2011). Study of high-speed machining parameters
problems and engineering design optimization. Retrieved from http://
on nickel-based alloy GH2132. Advanced Materials Research, 189–193,
www.springerlink.com/index/10.1007/s10845-010-0393-4.
3142–3147.
Alam, S., Nurul Amin, A. K. M., Patwari, A. U., & Konneh, M. (2010). Prediction and
Gao, Q., Zhang, Q., Su, S., & Zhang, J. (2008). Parameter optimization model in
investigation of surface response in high speed end milling of ti-6Al-4V and
electrical discharge machining process. Journal of Zhejiang University SCIENCE A,
optimization by genetic algorithm. Advanced Materials Research, 1009–1015.
9(1), 104–108.
An, L. (2011). Optimal selection of machining parameters for multi-pass turning
Hu, X. M., Zhang, J., Xiao, J., & Li, Y. (2008). Protein folding in hydrophobic-polar
operations. Advanced Materials Research, 156–157, 956–960.
lattice model: A flexible ant-colony optimization approach. Protein and Peptide
An, L., Feng, L., & Lu, C. (2011). Cutting parameter optimization for multi-pass
Letters, 15(5), 469–477.
milling operations by genetic algorithms. Advanced Materials Research, 160–162,
Huang, H., Li, A., & Lin, X. (2007). Application of PSO-based wavelet neural network
1738–1743.
in tool wear monitoring. In Proceedings of the IEEE international conference on
Ansalam Raj, T. G., & Narayanan Namboothiri, V. N. (2010). An improved genetic
automation and logistics (pp. 2813–2817).
algorithm for the prediction of surface finish in dry turning of SS 420 materials.
Jain, N. K., & Jain, V. K. (2007). Optimization of electro-chemical machining process
International Journal of Advanced Manufacturing Technology, 47(1-4), 313–324.
parameters using genetic algorithms. Machining Science and Technology, 11(2),
Akay, B., & Karaboga, D. (2009). Parameter tuning for the artificial bee colony
235–258.
algorithm. Lecture Notes in Computer Science (5796/2009), 608–619.
Jain, N. K., Jain, V. K., & Deb, K. (2007). Optimization of process parameters of
doi:10.1007/978-3-642-04441-0_53.
mechanical type advanced machining processes using genetic algorithms.
Baucer, A., Bullnheimer, B., Hartl, R. F., & Strauss, C. (2000). Minimizing total
International Journal of Machine Tools and Manufacture, 47(6), 900–919.
tardiness on a single machine using ant colony optimization. Central European
Jayabal, S., & Natarajan, U. (2010). Optimization of thrust force, torque, and tool
Journal for Operations Research and Economics, 8(2), 125–141.
wear in drilling of coir fiber-reinforced composites using nelder-mead and
Benala, T., Jampala, S., Villa, S., & Konathala, B. (2009). A novel approach to image
genetic algorithm methods. International Journal of Advanced Manufacturing
edge enhancement using Artificial Bee Colony optimization algorithm for
Technology, 51(1–4), 371–381.
hybridized smoothening filters. Nature & Biologically Inspired Computing (pp.
Kadirgama, K., Noor, M. M., & Alla, A. N. A. (2010). Response Ant Colony
1071–1076). NaBIC 2009. World Congress.
Optimization of End Milling Surface Roughness. Sensors, 10, 2054–2063.
Benardos, P. G., & Vosnaikos, G. C. (2003). Predicting surface roughness in
doi:10.3390/s100302054.
machining: a review. International Journal of Machine Tools and Manufacture,
Karaboga, D., & Akay, B. (2009). A comparative study of artificial bee colony
43, 833–844.
algorithm. Applied Mathematics and Computation, 214, 108–132.
Bertsimas, D., & Tsitsiklis, J. N. (1993). Simulated Annealing. Statistical Science, 8(1),
Karaboga, N. (2009). A new design method based on artificial bee colony algorithm
10–15.
for digital IIR filters. Journal of the Franklin Institute, 346(4), 328–348.
Bharathi, R. S., & Baskar, N. (2010). Optimization techniques for machining
Kennedy, J. & Eberhart, R. C. (1995). Particle swarm optimization. In Proceedings on
operations: A retrospective research based on various mathematical models.
IEEE international conference on neural networks, IV (pp. 1942–1948).
International Journal of Advanced Manufacturing Technology, 48(9–12),
Piscataway, NJ: IEEE Service Center.
1075–1090.
Kilickap, E., Huseyinoglu, M., & Yardimeden, A. (2011). Optimization of drilling
Bharathi, R. S., & Baskar, N. (2011). Particle swarm optimization technique for
parameters on surface roughness in drilling of AISI 1045 using response surface
determining optimal machining parameters of different work piece materials in
methodology and genetic algorithm. International Journal of Advanced
turning operation. International Journal of Advanced Manufacturing Technology,
Manufacturing Technology, 52(1–4), 79–88.
54(5–8), 445–463.
Kirkpatrick, S., Gelatt, C. D., Jr., & Vecchi, M. P. (1983). Optimization by simulated
Brand, M., Masuda, M., Wehner, N., & Yu, X. H. (2010). Ant colony optimization
annealing. Science, 220(4598), 671–680.
algorithm for robot path planning. 2010 International Conference on Computer
Kolahan, F., & Abachizadeh, M. (2008). Optimizing turning parameters for
Design and Applications (ICCDA 2010), vol. 3 (pp. 436–440).
cylindrical parts using simulated annealing method. World Academy of
Cerny, V. (1985). Thermodynamical approach to the traveling salesman problem:
Science, Engineering and Technology, 46, 437–439.
An efficient simulation algorithm. J. Opt. Theory Appl., 45(1), 41–51.
Kolahan, F. & Khajavi, A. H., (2009). A statistical approach for predicting and
Chandrasekaran, M., Muralidhar, M., Krishna, C. M., & Dixit, U. S. (2010). Application
optimizing depth of cut in AWJ machining for 6063-T6 al alloy. In Proceedings of
of soft computing techniques in machining performance prediction and
world academy of science, engineering and technology, vol. 59 (pp. 142–145).
optimization: A literature review. International Journal of Advanced
Kuruvila, N., & Ravindra, H. V. (2011). Parametric influence and optimization of wire
Manufacturing Technology, 46(5–8), 445–464.
edm of hot die steel. Machining Science and Technology, 15(1), 47–75.
Chen, H., Lin, J., Yang, Y., & Tsai, C. (2010). Optimization of wire electrical discharge
Lee, W. S., Nam, S. H., Choi, H. Z., Kang, E. G., & Ryu, K. Y. (2007). Optimized
machining for pure tungsten using a neural network integrated simulated
machining condition selection for high-quality surface in high-speed finish
annealing approach. Expert Syst. Appl., 37(10), 7147–7153. doi:10.1016/
milling of molds. Key Engineering Materials, 329, 711–718.
j.eswa.2010.04.
Li, J. G., Yao, Y. X., Gao, D., Liu, C. Q., & Yuan, Z. J. (2008). Cutting parameters
Chen, Z. & Li, Y. (2008). An improved particle swarm algorithm and its application in
optimization by using particle swarm optimization (PSO). Applied Mechanics
grinding process optimization. In Proceedings of the 27th Chinese Control
and Materials Vols., 10-12, 879–883.
Conference (pp. 2–5).
Liu, H., & Huang, W. (2008). Computer numerical control machining parameter
Ciurana, J., Arias, G., & Ozel, T. (2009). Neural network modeling and particle swarm
optimization based on particle swarm optimization. Tongji Daxue Xuebao/
optimization (PSO) of process parameters in pulsed laser micromachining of
Journal of Tongji University, 36(6), 803–806.
hardened AISI H13 steel. Materials and Manufacturing Processes, 24(3), 358–368.
Mahapatra, S. S., & Patnaik, A. (2007). Optimization of wire electrical discharge
Costa, A., Celano, G., & Fichera, S. (2011). Optimization of multi-pass turning
machining (WEDM) process parameters using taguchi method. International
economies through a hybrid particle swarm optimization technique.
Journal of Advanced Manufacturing Technology, 34(9–10), 911–925.
International Journal of Advanced Manufacturing Technology, 53(5–8), 421–433.
Maji, K., & Pratihar, D. K. (2010). Modeling of electrical discharge machining process
Cŭs, F., Balic, J., & Zŭperl, U. (2009). Hybrid ANFIS-ants system based optimization of
using conventional regression analysis and genetic algorithms. Journal of
turning parameters. Journal of Achievements in Materials and Manufacturing
Materials Engineering and Performance, 1–7.
Engineering, 36(1), 79–86.
Martens, D., De Backer, M., Haesen, R., Vanthienen, J., Snoeck, M., & Baesens, B.
Del Prete, A., De Vitis, A. A., & Anglani, A. (2010). Roughness improvement in
(2007). Classification with ant colony optimization. IEEE Transactions on
machining operations through coupled metamodel and genetic algorithms
Evolutionary Computation, 11(5), 651–665.
technique. International Journal of Material Forming, 3(SUPPL. 1), 467–470.
Mohanasundararaju, N., Sivasubramanian, R., & Alagumurthi, N. (2008).
Dorigo, M., & Blum, C. (2005). Ant colony optimization theory: A survey. Theoretical
Optimisation of work roll grinding using response surface methodology and
Computer Science, 344(2–3), 243–278.
 N. Yusup et al. / Expert Systems with Applications 39 (2012) 9909–9927 9927

evolutionary algorithm. International Journal of Manufacturing Research, 3(2), Tang, L., Landers, R. G., & Balakrishnan, S. N. (2008). Parallel turning process
236–251. parameter optimization based on a novel heuristic approach. Journal of
Mukherjee, I., & Ray, P. K. (2006). A review of optimization techniques in metal Manufacturing Science and Engineering, Transactions of the ASME, 130(3),
cutting processes. Computers and Industrial Engineering, 50(1–2), 15–34. 0310021-03100212. Engineering, 53(6), 354-368.
Nagendra Parashar, B. S., & Mittal, R. K. (2007). Elements of manufacturing processes. Venayagamoorthy, G.K. and Harley, R.G. (2007). Swarm intelligence for
Prentice-Hall of India Private Limited. transmission system control, Power Engineering Society General Meeting,
Palanisamy, P., Rajendran, I., & Shanmugasundaram, S. (2007). Optimization of IEEE, pp. 1-4.
machining parameters using genetic algorithm and experimental validation for Vob, S. (2001). Meta-heuristics: The state of art. Lecture Notes in Computer Science,
end-milling operations. International Journal of Advanced Manufacturing 2148, 1–23.
Technology, 32(7-8), 644–655. Wang, X., & Jawahir, I. S. (2004). Web based optimization of milling operations for
Parent, L., Songmene, V., & Kenné, J. (2007). A generalised model for optimising an the selection of cutting conditions using genetic algorithms. Proc. Inst. Mech.
end milling operation. Production Planning and Control, 18(4), 319–337. Eng., 218, 212–223.
Pasam, V. K., Battula, S. B., Valli, P. M., & Swapna, M. (2010). Optimizing surface Wang, Z. H., Yuan, J. T., Hu, X. Q., & Dengn, W. (2009). Surface roughness prediction
finish in WEDM using the Taguchi parameter design method. Journal of the and cutting parameters optimization in high-speed milling AlMn1Cu using
Brazilian Society of Mechanical Sciences and Engineering, 32(2), 107–113. regression and genetic algorithm. In International Conference on Measuring
Prakasvudhisarn, C., Kunnapapdeelert, S., & Yenradee, P. (2009). Optimal cutting Technology and Mechatronics Automation (vol. 3, pp. 334–337).
condition determination for desired surface roughness in end milling. Wu, J. and Yao, Y. (2008). A Modified Ant Colony System for the Selection of
International Journal of Advanced Manufacturing Technology, 41(5–6), 440–451. Machining Parameters, 2008 Seventh International Conference on Grid and
Prasad, C. F., Jayabal, S., & Natarajan, U. (2007). Optimization of tool wear in turning Cooperative Computing, pp89-94, DOI 10.1109/GCC.2008.64.
using genetic algorithm. Indian Journal of Engineering and Materials Sciences, Xi, J. and Liao, G. (2009). Cutting parameter optimization based on particle swarm
14(6), 403–407. optimization. Paper presented at the 2009 2nd International Conference on
Rai, J. K., Brand, D., Slama, M., & Xirouchakis, P. (2011). Optimal selection of cutting Intelligent Computing Technology and Automation, ICICTA 2009, 1, 255-258.
parameters in multi-tool milling operations using a genetic algorithm. Xie, S., & Guo, Y. (2011). Intelligent Selection of Machining Parameters in Multi-pass
International Journal of Production Research, 49(10), 3045–3068. Turnings Using a GA-based Approach. Journal of Computational Information
Rao, R. V., & Pawar, P. J. (2009). Modelling and optimization of process parameters of Systems, 7(5). 1714-172.
wire electrical discharge machining. Proceedings of the Institution of Mechanical Xie, S. and Pan, L. (2010). Selection of machining parameters using genetic
Engineers, Part B: Journal of Engineering Manufacture, 223(11), 1431–1440. algorithms. Paper presented at the ICCSE 2010–5th International Conference
Rao, R. V., & Pawar, P. J. (2010a). Grinding process parameter optimization using on Computer Science and Education, Final Program and Book of Abstracts,
non-traditional optimization algorithms. Proceedings of the Institution of 1147–1150.
Mechanical Engineers, Part B: Journal of Engineering Manufacture, 224(6), Xu, F., Zhu, J. J., Wu, X., Zang, X. J., & Zuo, D. W. (2010). Parameter optimization of
887–898. milling Ti6Al4V using GA approach. Key Engineering Materials, 426–427, 1–4.
Rao, R. V., & Pawar, P. J. (2010b). Parameter optimization of a multi-pass milling Yang, S., J. Srinivas, Sekar Mohan, Dong-Mok Lee, Sree Balaji, (2009). Optimization of
process using non-traditional optimization algorithms. Applied Soft Computing, electric discharge machining using simulated annealing. Journal of Materials
10(2), 445–456. ISSN 1568-4946, DOI: 10.1016/j.asoc.2009.08.007. Processing Technology, Volume 209(9) (pp. 4471–4475). ISSN 0924-0136, DOI:
Rao, R. V., Pawar, P. J., & Davim, J. P. (2010a). Parameter optimization of ultrasonic 10.1016/j.jmatprotec.2008.10.053.
machining process using nontraditional optimization algorithms. Materials and Yang, W., Guo, Y., & Liao, W. (2011a). Optimization of multi-pass face milling using
Manufacturing Processes, 25(10), 1120–1130. a fuzzy particle swarm optimization algorithm. International Journal of Advanced
Rao, R. V., Pawar, P. J., & Davim, J. P. (2010b). Optimisation of process parameters of Manufacturing Technology, 54(1–4), 45–57.
mechanical type advanced machining processes using a simulated annealing Yang, W., Guo, Y., & Liao, W. (2011b). Multi-objective optimization of multi-pass
algorithm. International Journal of Materials and Product Technology, 37(1–2), face milling using particle swarm intelligence. International Journal of Advanced
83–101. Manufacturing Technology, 1–15.
Rao, R. V., Pawar, P. J., & Shankar, R. (2008). Multi-objective optimization of Yongzhi, P., Jun, Z., Xiuli, F., & Xing, A. (2010). Optimization of surface roughness
electrochemical machining process parameters using a particle swarm based on multi-linear regression model and genetic algorithm. Advanced
optimization algorithm. Proceedings of the Institution of Mechanical Materials Research, 97–101, 3050–3054.
Engineers, Part B: Journal of Engineering Manufacture, 222(8), 949-958. Zain, A. M., Haron, H., & Sharif, S. (2008). An overview of GA technique for surface
Razfar, M. R., Asadnia, M., Haghshenas, M., & Farahnakian, M. (2010). Optimum roughness optimization in milling process. Paper presented at the Proceedings -
surface roughness prediction in face milling X20Cr13 using particle swarm International Symposium on Information Technology 2008, ITSim, 3.
optimization algorithm. Proceedings of the Institution of Mechanical Engineers, Zain, A. M., Haron, H., & Sharif, S. (2010a). Application of GA to optimize cutting
Part B: Journal of Engineering Manufacture, 224(11), 1645-1653. conditions for minimizing surface roughness in end milling machining process.
Saffar, R. J., & Razfar, M. R. (2010). Simulation of end milling operation for predicting Expert System with Applications, 37, 4650–4659.
cutting forces to minimize tool deflection by genetic algorithm. Machining Zain, A. M., Haron, H., & Sharif, S. (2010b). Simulated Annealing To Estimate The
Science and Technology, 14(1), 81–101. Optimal Cutting Conditions For Minimizing Surface Roughness In End Milling
Samanta, S., & Chakraborty, S. (2011). Parametric optimization of some non- Ti-6Al-4V. Machining Science and Technology, 14, 43–62.
traditional machining processes using artificial bee colony algorithm. Zain, A. M., Haron, H., & Sharif, S. (2011a). Genetic Algorithm and Simulated
Engineering Applications of Artificial Intelligence, 24(6), 946–957. Annealing to estimate optimal process parameters of the abrasive waterjet
Sankar, R. S., Asokan, P., Saravanan, R., Kumanan, S., & Prabhaharan, G. (2007). machining. Engineering with Computers, 27(3), 251–259.
Selection of machining parameters for constrained machining problem using Zain, A. M., Haron, H., & Sharif, S. (2011b). Estimation of the minimum machining
evolutionary computation. International Journal of Advanced Manufacturing performance in the abrasive waterjet machining using integrated ANN-SA.
Technology, 32(9–10), 892–901. Expert Systems with Applications, 38(2011), 8316–8326.
Saravanan, R. and Janakiraman, V. (2007). Study on reduction of machining time in Zain, A. M., Haron, H., & Sharif, S. (2011c). Integration of simulated annealing and
CNC turning centre by genetic algorithm. Paper presented at the Proceedings - genetic algorithm to estimate optimal solutions for minimising surface
International Conference on Computational Intelligence and Multimedia roughness in end milling Ti–6AL–4V. International Journal of Computer
Applications, ICCIMA 2007, 1, 481-486. Integrated Manufacturing, 24(6), 574–592.
Satishkumar, S., & Asokan, P. (2008). Selection of optimal conditions for CNC Zain, A. M., Haron, H., & Sharif, S. (2012). Integrated ANN-GA for estimating the
multitool drilling system using non-traditional techniques. International Journal minimum value for machining performance. International Journal of Production
of Machining and Machinability of Materials, 3(1–2), 190–207. Research, 50(1), 191–213.
Savas, V., & Ozay, C. (2008). The optimization of the surface roughness in the Zeng, H. Y., Qiang E, J., Yang, X. P., & Li, H. M. (2011). Soft-sensing model on the
process of tangential turn-milling using genetic algorithm. International Journal roughness of machining surface under the numerical control and its application.
of Advanced Manufacturing Technology, 37(3–4), 335–340. Applied Mechanics and Materials, 48–49, 1077–1085.
Singh, D., & Rao, P. V. (2007). Optimization of tool geometry and cutting parameters Zhang, C. & Chen, J. (2009). Methods of optimization of milling parameters based on
for hard turning. Materials and Manufacturing Processes, 22(1), 15–21. genetic algorithm. Paper presented at the ICEMI 2009 – Proceedings of 9th
Srinivas, J., Giri, R., & Yang, S. -. (2009). Optimization of multi-pass turning using International Conference on Electronic Measurement and Instruments, 1382–
particle swarm intelligence. International Journal of Advanced Manufacturing 1385.
Technology, 40(1-2), 56-66. Zhao, H., Li, J. G., Yao, Y. X., & Liu, C. Q. (2008). Cutting parameters optimization for
Stützle, T. (1997). An ant approach to the flow shop problem’’, Technical report constant cutting force in milling. Applied Mechanics and Materials, 10–12, 483.
AIDA-97-07, 1997. Zheng, L. Y. & Ponnambalam, S. G. (2010). Optimization of multipass turning
Sultana, I. and Dhar, N. R. (2010). GA based multi objective optimization of the operations using particle swarm optimization. Paper presented at the ISMA’10 –
predicted models of cutting temperature, chip reduction co-efficient and 7th International Symposium on Mechatronics and its Applications, 1–6.
surface roughness in turning AISI 4320 steel by uncoated carbide insert under Zŭperl, U., Cŭs, F., & Gecevska, V. (2007). Optimization of the characteristic
HPC condition. Paper presented at the Proceedings of the 2010 International parameters in milling using the PSO evolution technique. Journal of Mechanical
Conference on Mechanical, Industrial, and Manufacturing Technologies, MIMT Engineering, 6(2007), 354–368.
2010, 161-167.

View publication stats