Vol-4 Issue-2 2018 IJARIIE-ISSN(O)-2395-4396

A Survey Approach of Optimization of

Injection Moulding Process Parameter
Navin Kumar1, Mayur Thombre2
1
PG Students, 2Assistant Professor, Department of Mechanical Engineering, SSITM Bhilai, INDIA.

ABSTRACT
This review paper found the better optimization techniques which the effects degree of different moulding process
parameters for shrinkage. The mold design can fasten the mold developing schedule, thus shorten the cycle of product
development, and improve the quality of products and the competitive ability of enterprise. Injection molding is one of
the most important and common plastic formation methods. Combination of modeling tools and optimization algorithms
can be used in order to determine optimum process conditions for the injection molding of a special part. Using the trail
and error approach parameters for injection moulding no longer good enough. So, this work research has been finding
optimizations of processing parameters for robust parameter design. In this study has been taken Artificial neural
network method for solving the problem which are give useful result.
Keywords: Injection moulding, optimization, Process parameter, ANN tool, Shrinkage.

I. INTRODUCTION
Plastics has become the fundamental drivers of innovations and new product development. Uses of plastics are
intertwined in every part of our contemporary life style and have become indispensable; products made out of
plastics range from sophisticated medical implants to disposable household implements. Intelligent and
innovative use of plastics have opened up new avenues in the polymer-electronics sector; from organic light
emitting diodes to electro-optical and bioelectrical complements, from low-cost plastics chips to flexible solar
cells. Some of the plastics can conduct even electricity and emit light, leading to development of creative
applications. Great popularity in use of plastics can be observed in automobiles and in a wide variety of
industrial applications.

Fig 1. Injection Molding Process [2]

Injection Molding (IM) is considered the most prominent process for mass production of plastic parts. More than one
third of all plastic products are made by injection molding, and over half of the world’s polymer processing equipment’s
are used for the injection molding process [Osswald et al. 2002]. Injection molding has been a challenging process for
many manufacturers and researchers to produce products meeting requirements at the lowest cost. Its complexity and the
enormous amount of process parameter manipulation during real time production create a very intense effort to maintain

7497 www.ijariie.com 343

Vol-4 Issue-2 2018 IJARIIE-ISSN(O)-2395-4396

the process under control. Complexity and parameter manipulation may cause serious quality problems and high
manufacturing costs [Cabrera et al. 2002].

Fig 2. Cause-and-effect diagram shown in fishbone schematics [3]

II. LITERATURE SURVEY

The various literature survey detailed in below:
Chang and Tsaur (1995). Based on the rheological properties of polymers, an integrated theory and computer program
was developed in this study for simulation of such behavior. Hybrid finite-element and finite-difference methods were
employed for simulating the injection moulding filling, packing, and cooling processes. A control volume method was
applied towards both finding the melt front position and also calculating the temperature and pressure profile at any
instant during the filling process. A modified Tait equation provides a description of the pressure-volume-temperature
relationship of crystalline polymers. The Malkin’s kinetics model was employed to describe the behavior of polymer
crystallization. The flow induced and thermal induced-residual stresses employed as the initial conditions in the solid
mechanics analysis were obtained with the linear thermoviscoelastic model. The displacements, including the thickness
direction of part, which could not be calculated by the traditional bending moment method, were solved by using the
numerical solid mechanics analysis with the three-dimensional finite element methods. The theoretical results were also
correlated using commercial FE flow simulation software. Though the integrated program was able to simulate shrinkage
and warpage on moulded products, the sink simulation was not modelled conclusively.
Substantial numbers of research studies, using physical experiments, were made to understand the injection
moulding process for various objectives. Some of which are meant to validate the FE flow simulations. Practical
experimental studies on injection moulding process are prohibitively costly and time consuming. Complexity and cost
increases, if one needs modification on moulds on a continuous basis to conduct any useful study. Hence, practical
studies had rather limited scopes. However, few investigators conducted practical experimental studies for the study of
sink marks.

Dan and Bistany (2000) investigated the possibility of reducing sinks with beryllium copper as mould material using
laboratory level experiments. It was found that material with higher thermal conductivity aids in the reduction of sink.

Ernst et al (2003), An approach for design of mould elements like core and cavity inserts of the injection moulds was
attempted by iteratively coupling structural analysis with FE flow simulations. The developed approach was reported to
have resulted in quicker realization of the parts. Using suitable rheological data even new materials can be simulated in
FE flow simulation packages.

Turng et al (2002), In spite of the virtual advantages of FE flow simulation, if one needs to understand a system from the
standpoint of “input-output” relationships one may have to resort to computationally intensive trial and error iterations.
To bridge the gap, few researchers attempted integration of FE simulation tool with some optimization routines. Few
other researchers coupled DOE, Taguchi, Artificial Neural Network (ANN), fuzzy control, etc. with FE flow simulations.

Dubey et al (2005), a unique cooling control system was developed and implemented to control the plastic part average
cavity temperature inside the mold cavity on plastic injection molding machine by utilizing coolant flow as the
manipulated variable. An algorithm was developed to automatically conduct open loop experiments, perform system
identification, controller tuning and perform control simulations. The tuning parameters were then downloaded to another
controller for real time control of part cavity temperature. The PI controller demonstrated good performance for both
control simulations and when implemented practically on machine. This approach can be readily applied on industrial

7497 www.ijariie.com 344

Vol-4 Issue-2 2018 IJARIIE-ISSN(O)-2395-4396

machines and it creates the foundation for implementing more advanced control schemes such as model based predictive
control and quadratic regulator types.

Erzurumlu and Ozcelik (2006), he objective of this paper consists of minimization of the warpage and sink index in
terms of process parameters of the plastic parts have different rib cross-section types, and rib layout angle using Taguchi
optimization method. Considering the process parameters such as mold temperature, melt temperature, packing pressure,
in addition to rib cross-section types, and rib layout angle, a series of mold analyses are performed to exploite the
warpage and sink index data. The polymeric materials were selected PC/ABS, POM, and PA66. Taguchi optimization
method was used by exploiting mold analyses based on three level factorial design. Orthogonal arrays of Taguchi, the
signal-to-noise (S/N) ratio, the analysis of variance (ANOVA) are utilized to find the optimal levels and the effect of
process parameters on warpage and sink index. Confirmation analysis test with the optimal levels of process parameters
are carried out in order to demonstrate the goodness of Taguchi method. From this, it can be concluded that Taguchi
method is very suitable to solve the quality problem occurring the injection-molded thermoplastic parts.

Fang et al (2005), The response surface methodology (RSM), which typically uses quadratic polynomials, is
predominantly used for metamodeling in crashworthiness optimization because of the high computational cost of vehicle
crash simulations. Research shows, however, that RSM may not be suitable for modeling highly nonlinear responses that
can often be found in impact related problems, especially when using limited quantity of response samples. The radial
basis functions (RBF) have been shown to be promising for highly nonlinear problems, but no application to
crashworthiness problems has been found in the literature. In this study, metamodels by RSM and RBF are used for
multiobjective optimization of a vehicle body in frontal collision, with validations by finite element simulations using the
full-scale vehicle model. The results show that RSM is able to produce good approximation models for energy
absorption, and the model appropriateness can be well predicted by ANOVA. However, in the case of peak acceleration,
RBF is found to generate better models than RSM based on the same number of response samples, with the multiquadric
function identified to be the most stable RBF. Although RBF models are computationally more expensive, the
optimization results of RBF models are found to be more accurate.

Pujari and Naik (2015), in the present study, the simulation for optimization of plastics injection molding processing
parameters Based on The Minimization of Sink Marks have been performed by Taguchi method & Moldflow software.
The following conclusions were obtained.
(1) The simulation considering the sequence of effects degree of different molding process parameters for surface sink
marks ranked in the holding pressure; melt temperature, cooling time and injection pressure. The holding pressure is the
most important effect.
(2) The optimized parameter combinations of different factors are considered as melt temp 235°c; injection pressure 80
bar; holding pressure 55 bar & cooling time 50 sec, and its sink marks index is 2.674, which is the best data compared
with other parameter combinations.

Meiabadi et al (2013), he purpose of this research was to obtain the process parameters that ensure the accurate part
weight, less process cycle time, and injection pressure. The research results indicate that the proposed approach can
effectively help engineers determine optimal process parameters setting and achieve competitive advantages of product
quality and costs. The efficiency of the method depends on the selection of appropriate process parameters, process
parameter ranges and accuracy of Moldflow simulations and neural network predictions. In this study, the process
parameters were determined within constraints of machine tools and mold steel. Thus, some parameters could not be
considered as the parameters for optimizing the injection process. Because of the fixed mold constraint, the gate location
and coolant point could not change their locations. For future study, the researcher should perform the experiments using
this methodology before producing new products and its mold.

Bharti and Khan (2010), his article presents a review of research in the determination of the process parameters for
injection molding. A number of research works based on various approaches including mathematical model, Taguchi
technique, Artificial Neural Networks (ANN), Fuzzy logic, Case Based Reasoning (CBR), Genetic Algorithms (GA),
Finite Element Method(FEM), Non-Linear Modeling, Response Surface Methodology, Linear Regression Analysis, Grey
Rational Analysis and Principle Component Analysis using cavity pressure signals have been described. A review of
literature on optimization techniques has revealed that there are, in particular, successful industrial applications of design
of experiment-based approaches for optimal settings of process variables. Taguchi methods and response surface
methodology are robust design techniques widely used in industries for making the product/process insensitive to any
uncontrollable factors such as environmental variables. Taguchi approach has potential for savings in experimental time
and cost on product or process development and quality improvement. There is general agreement that off-line
experiments during product or process design stage are of great value. Reducing quality loss by designing the products
and processes to be insensitive to variation in noise variables is a novel concept to statisticians and quality engineers.

7497 www.ijariie.com 345

Vol-4 Issue-2 2018 IJARIIE-ISSN(O)-2395-4396

ANN, GA, and CBR are emerging as the new approaches in the determination of the process parameters for
injection molding. A trained neural network system can quickly provide a set of molding parameters according to the
results of the predicted quality of molded parts. However, the time required in the training and retraining for a neural
network could be very long. By using GA approach, the system can locally optimize the molding parameters even
without the knowledge about the process. In practical use, the convergence rate to an optimal set of process parameters
could be very slow in some occasion. CBR systems can determine a set of initial process parameters for injection
molding quickly based on the similar case(s) without relying heavily on the expert molding personnel.

III. CONCLUSION

The study was focused on the application of the ANN optimization techniques to find the optimum levels and response of
injection moulding plastic components. Injection molding has been a challenging process for many manufacturers and
researchers to produce products meeting requirements at the lowest cost. By using this method, it can optimize the
process parameters and achieving the minimum shrinkage, which improve the quality and overall in production.
Artificial neural networks (ANNs) are defined as mathematical models which represent the biological process of a human
brain. There are three main components in the ANNs; neurons or processing elements (PE), interconnections, and
learning rules.

REFERENCES
[1] Chang R.Y. and Tsaur B. D. (1995), ‘Experimental and theoretical studies of shrinkage, warpage, and sink marks of
crystalline polymer injection molded parts’, Polymer Engineering and Science, Vol.35, No.15, pp.1222-1230.
[2] Chen S.C., Chang Y.P., Chang C.Y., Hung H.W. and Yang W.H. (2008b), ‘Simulation and verification on part
surface quality using external gas-assisted injection molding process’, SPE ANTEC Tech papers, pp.1504-1508.
[3] Dan T. and Bistany S. P. (2000), ‘Process and tooling factors affecting sink marks for amorphous and crystalline
resins’, Journal of Injection Molding Technology, Vol. 4,
[4] Ernst S. and Marco T. (2003), ‘Approach for a mechanical design of plastics injection molds by means of FEA’,
SPE ANTEC Tech. Papers, pp.915-918.
[5] Adam K., Ryan C., Donald E., Zhongbao C. and Turng L.S. (2005), ‘Quantitative study of shrinkage and warpage
behavior for microcellular and conventional injection moulding’, Polymer Engineering and Science, Vol. 45,
pp.1408-1418.
[6] Dubay R., Pramujati B. and Hernandez J. (2005), ‘Cavity temperature control in plastic injection molding’,
International Conference on Mechatronics and Automation, Vol. 2, 2005.
[7] Erzurumlu T. and Ozcelik B. (2006), ‘Minimization of warpage and sink index in injection-molded thermoplastics
parts using Taguchi optimization method’, Materials and Design, Vol. 27, pp.853–861.
[8] Fang H., Rais R.M., Liu Z. and Horstemeyer M.F. (2005), ‘A comparative study of metamodeling methods for
multiobjective crashworthiness optimization’, Computers and Structures, Vol. Vol. 83, Issues 25–26, pp 2121-2136,
2005.
[9] Franca D.R., Wen S.S.L., Jen C.K., Nguyen K.T. and Hebert H. (1997), ‘Advances in on-line monitoring of
polymer injection molding process’, IEEE Ultrasonics Symposium,
[10] G. V. Pujari, Prof. Dr. V. R. Naik, “Optimization of Parameters & Minimization of Defect by Applying Taguchi &
Moldflow Method for Injection Molding Component”, International Journal of Advanced Technology in
Engineering and Science, Vol. No.03, Issue No. 01, 2015.
[11] Mohammad Saleh Meiabadi, Abbas Vafaeesefat, Fatemeh Sharifi, “Optimization of Plastic Injection Molding
Process by Combination of Artificial Neural Network and Genetic Algorithm”, Journal of Optimization in Industrial
Engineering, Vol. 13, pp 49-54, 2013.
[12] Bharti, P.K. and Khan. , M. I. (2010). Recent methods for optimization of plastic injection molding process –a
retrospective and literature review. International Journal of Engineering Science and Technology, 2(9), 4540-4554.

7497 www.ijariie.com 346