World Academy of Science, Engineering and Technology 56 2009

Fuzzy Controller Design for Ball and Beam

System with an Improved Ant Colony
Optimization
Yeong-Hwa Chang, Chia-Wen Chang, Hung-Wei Lin, and C.W. Tao

 problem [10].
Abstract—In this paper, an improved ant colony optimization In the literatures, some ACO-based fuzzy control strategies
(ACO) algorithm is proposed to enhance the performance of global have been proposed [11][12], however, only the conventional
optimum search. The strategy of the proposed algorithm has the ACO is utilized. In this paper we first propose an improved
capability of fuzzy pheromone updating, adaptive parameter tuning,
ACO algorithm with fuzzy pheromone updating. Then the
and mechanism resetting. The proposed method is utilized to tune the
parameters of the fuzzy controller for a real beam and ball system. proposed improved optimization algorithm is applied to a real
Simulation and experimental results indicate that better performance ball and beam system for the position balance control.
can be achieved compared to the conventional ACO algorithms in the Compared with other ACO related methods, the superiority of
aspect of convergence speed and accuracy. the proposed work can be evaluated from the simulation and
experimental results.
Keywords—Ant colony algorithm, Fuzzy control, ball and beam This paper is organized as follows. Section II the common
system. concepts of ACO algorithm are presented. The proposed
improved ACO algorithm is described in Section III. As for the
I. INTRODUCTION
ball and beam system, the simulation results, based on the

A NT colony optimization (ACO) algorithm is a

population-based evolutionary computation method,
inspired to mathematically simulate the social behaviors of ants
proposed algorithm, are addressed in Section IV. Experimental
set-up and measurement results are provided in Section V. The
concluding remarks are given in Section VI.
forage. Similar to genetic algorithms (GAs), ACO is also
initiated with a population of candidates that are randomly II. ANT COLONY OPTIMIZATION
moved in a multidimensional search space [1]-[3]. However, The ant colony optimization was developed in early 1990s
GA saves only the better generations, thus it may lead to local by Dorigo et al. [1]. The ACO technique is one of the meta-
optima rather than the global optimum. The ACO is a heuristic optimization methods and is inspired by the capability
multi-agent approach for solving difficult combinatorial of real ants to establish the shortest path from a food source to
optimization problems, such as the traveling salesman problem their nest. Ants lay the chemical substance or the trails of
(TSP) [4][5]. ACO algorithms have been successfully applied pheromone, on the ground when they move along paths. Each
to versatile combinational optimization problems, namely individual ant makes a decision of the moving direction based
vehicle routing [6], quadratic assignment problem (QAP) [8] on the strength of the pheromone trails. The better path is that
[9], and job-shop scheduling [7]. has higher amount of the pheromone trails on the ground.
Fuzzy rule-based systems (FRBSs) have been extensively While more and more ants track on the food source, the shorter
applied in many areas of interest, including the controller path accumulates the more pheromone trails. Thus, most of the
design, cluster analysis, and image processing. However, the ants are attracted to the shorter path, and this behavior of the
derivation of fuzzy rules is often difficult and requires expert path selection encourages the positive feedback effect. It is
knowledge. Many researchers have proposed optimization noted that the ants finally will find the shortest path. The ACO
methods for fuzzy systems using meta-heuristic algorithms algorithm is inspired by the aforementioned observation and
such as tabu search, genetic algorithms, simulated annealing can be named artificial ant. Although the ACO imitates the
(SA), and evolutionary algorithms (EAs) to overcome this behavior of real ant, the property of artificial ants is distinct
Y.-H. Chang is with the Department of Electrical Engineering, Chang Gung
from real ants, such as:
University, Taoyuan, Taiwan (corresponding author; phone: +886-3-2118800 z Artificial ants have the ability of memory; they can
ext. 5697; e-mail: yhchang@ mail.cgu.edu.tw). remember the nodes on the path such that the artificial ants
C.-W. Chang is with the Department of Electrical Engineering, Chang Gung can avoid selecting the same path.
University, Taoyuan, Taiwan (e-mail: [email protected]).
H.-W. Lin is with the Department of Electrical Engineering, Lee-Ming z Artificial ants are not completely blind; they have
Institute of Technology, Taipei County, Taiwan (e-mail: [email protected]) information of the heuristic function except the pheromone
C.W. Tao is with Department of Electrical Engineering, National ILang trail.
University, Ilan, Taiwan, (e-mail: [email protected]).

616
 World Academy of Science, Engineering and Technology 56 2009

z An environment is the discrete time; they lay the pheromone are significantly accumulated for the best path, and
pheromone trail on the sample time. the choosing probability is influenced by the pheromone trails.
The ant system (AS) was the first algorithm within the ACO In order to increase the range of solution space and decrease the
algorithms framework [2]. The AS algorithm was successfully number of iteration, the D can be undated by
applied to the traveling salesman problem, and it had
satisfactory results compared with traditional methods such as D D  'D (3)
GA, EA, and SA. The TSP is typically a combinational
optimization problem, which can be modeled as G (V , E ) , where 'D is a heuristic value.
where V {1,2,..., N } is a set of nodes and B. The Fuzzy Pheromone
E {(i, j ) | (i, j )  V u V } is a set of arcs. The object of the TSP The pheromone level is updated by (2) and 'W ij 1 / Lgb ,
is to find the minimum length Hamiltonian circle on G . The
Lgb is the length of the optimal global tour from the beginning
cost function is defined as the distance of edge (i, j ) . The
of the trail. In this paper, a modified pheromone updating is
distance between each pair of nodes ( xi , yi ) and ( x j , y j ) is given as follows
represented by d (i, j ) that is the Euclidean distance between
node i and j , where d (i, j ) d ( j , i ) . Let W ij be the value of W ij UW ij  f ( Lgb ) (4)

pheromone trails. In AS, the probability that an ant k ,

where f (˜) is a fuzzy function. The proposed fuzzy inference
currently located at the city i, chooses the city j as the next city
is given by system is represented as

Ri : IF X Ai1 THEN Y Bi (5)

­ [W ij ]D [K ij ]E
° , if j  N ik
pijk ® ¦lN k [W il ]D [K il ]E (1)
where Ri is the i th fuzzy relation, X , is the input variable, Y
° i

¯0, otherwise is the output variable, Ai1 is the fuzzy set in antecedent part,
and Bi is the fuzzy set in the consequent part. To calculate the
where K ij 1 / d ij is the heuristic value of moving from city i output Y , the centroid method is used for defuzzification. With
to city j , N ik is the set of cities remaining to be visited by the the fuzzy pheromone mechanism, the input and output
membership functions are shown in Fig. 1, and the fuzzy
ants, D and E are the relative weights of pheromone and
inference rules are developed in Table 1 with the fuzzy sets VS
visibility, respectively. The pheromone level of the selected (vary small), S (small), M (medium), L (large), and VL (very
element is updated by large).

W ij UW ij  'W ij (2)

where U is a parameter such that 1  U represents the

evaporation coefficient, 0  1  U  1 , and 'W ij is related to the
X Y
x5 x4 x3 x2 x1 y5 y4 y3 y2 y1
performance of each ant.
(a) (b)
Fig.1. Membership functions of the fuzzy pheromone
III. THE PROPOSED APPROACH (a) Input and (b) output membership functions.
For the complicated combinational problems, the
requirement of long convergence time and trapped in the local Table 1. Rule table of the fuzzy pheromone
optima are the typical drawbacks with conventional ACOs. In X VS S M L VL
this paper, an improved ACO algorithm, including the adaptive Y VL L M S VS
D parameter, the fuzzy pheromone and the clear mechanism, is
proposed to improve the convergence performance. In the rest
of this paper, the proposed optimization algorithm is named as C. The clear mechanism
FACO. Commonly, most of the optimization methods intend to find
the global optimal solution sooner. The behaviors to find the
A. The adaptive D parameter optimal solution include exploration and exploitation. The task
The parameters Į and ȕ are the weighing values of the of exploration is to search unknown regions of objective space
pheromone trails W ij , and the visibility K ij , respectively. In the and the purpose of exploitation is to find best solution in
early iterations, the pheromone trails on the path are not attractive areas of objective space. In practice, the exploration
significant, thus the path choice probability can be simply process can increase the probability to obtain the global
influenced by the visibility. In the later iterations, the trails of optimum and the convergent speed can be improved through

617
 World Academy of Science, Engineering and Technology 56 2009

the exploitation iterations. However, it is not easy to xk and ek xk*  xk is the error of state variable, k 1,...,4 .
simultaneously perform the exploration and exploitation
From the state equations in (1), it is indicated that there are two
procedures. In conventional ACO methods, the pheromone
dynamic objects, i.e. beam and ball. Therefore, the control of
trails arise quickly on the best path that can lead to most ants
the ball and beam system is decoupled into two subsystems, the
toward this path. The pheromone of the best path is much larger
position control of ball and the balance control of beam. Two
than other paths and the selection probability of the other paths
unique fuzzy control strategies are utilized to balance the beam
could be much smaller. Therefore, the phenomenon of
and to keep the ball in the designated position. The proposed
stagnation will be occurred. In this paper, a clear mechanism is
FACO optimized control scheme contains a fuzzy
proposed as follows
beam-balance controller, a fuzzy ball-position controller, and
the FACO tuning mechanism.
­0, if Prandom  Pclear
W ijmax ® max (6)
¯W ij , otherwise l
r o4
Wb
o3

where W ijmax is the pheromone of the best path, Prandom is L1

D
o2
Wg
randomly number, 0  Prandom  1 , and Pclear is parameter of L2

T
the clear mechanism. When the clear mechanism is performed, Wm o1
o0
the pheromone trails of the best path will be reset to zero.
d
Consequently, the ants can select other paths and deviate from
the local optimal solution. Fig. 2. Scheme diagram of ball and beam system.

IV. SIMULATION RESULTS

In this section, the proposed FACO is utilized for a ball and
C1 C4 P1 P6 B1 B6 kP1 k P6 k B1 k B6
beam control system. The configuration of the end-point driven
>x1d x2 d @ >e1 e2 @ >x1 x2 @
ball and beam system is shown in Fig. 2, where o0 is the small EP kP

u
gear that is mounted on a DC motor which provides the >e3 e4 @ C1 C 2 P1 P6 k P1 k P6
>x3 x4 @
necessary torque of interest, o1 represents the big gear that can >x3d x4 d @
kB
EB

control the angle of the beam, o2 , and o3 denote the link and kB1 kB6
C3 C4 B1 B6

beam, respectively, and o4 is the ball which rolls on the beam.

This system is an underactuated model, and the control Fig. 3. The control scheme of the ball and beam system with FACO
objective is to move the ball to the desired position on the beam.
Table 2. Parameters of ball and beam system.
The state vector of the ball and beam system is
Symbol Definition Value
x [ x1 x2 x3 x4 ]T , where x1 is the ball position, x2 is the mB mass of the ball 0.029 kg
velocity of the ball, x3 is the beam angle, and x4 represents mb mass of the beam 0.334 kg
the angular velocity of the beam. According to the l beam length 0.4 m
Euler-Lagrange method, the mathematical model of a ball and
d 0.04 m
beam system can be represented as follows (Detailed
derivations are discussed in the Appendix): rB radius of the ball 0.0095 m
JB pendulum length 0.11 m
x1 x2 Jb payload length 0.02 m
x2 Ax1 x42  Ag sin x3 Kb gear stand length 0.1491 V/(rad/sec)

x3 x4 (7) Kt gravity acceleration 0.1491 Nm/A

Ra radius of planet gear 18.91 ȍ
x 4 B ( x1 )[C cos x3 cos(ld 1 x3 )u  Dx4 cos x3 cos(ld 1 x3 )
r1 radius of sun gear 0.013 m
 E cos x3  Fx1 cos x3  Gx1 x2 x4 ]
In this paper, to reduce the design complexity, a single-input
where A (1  m B1 J B R 2 ) 1 , B( x1 ) ( J B  J b  mB x12 ) 1 , FLC (SFLC) is adopted. With this control scheme,
C 4.2 K b l ( Ra d ) 1 , D ( K b l ) 2 ( Ra d 2 ) 1 , E lmb g / 2 , E P c1e1  c2 e2 and E B c3e3  c4e4 are designed as the
F mB g , G 2mB , and u is the input voltage of the DC inputs of the fuzzy beam-balance controller and the fuzzy
ball-position controller, respectively, where c1 ~ c4 are the
motor. The parameters of the system are given in Table 2.
The schematic diagram of the ball and beam control system error constant. The input and output membership functions of
FBBC and FBPC are indicated in the Fig. 4, where E P and E B
with FACO is shown in Fig. 3, where xk* is the command of
represent the input vectors of FBPC and FBBC, respectively.

618
 World Academy of Science, Engineering and Technology 56 2009

The FFBPC and FFBBC are denoted as output vectors of FBPC Integral of Square Error (ISE)
N
and FBBC, respectively. For the output fuzzy sets, the
membership functions are defined to be fuzzy singleton
ISE ¦ (( x1* (t )  x1 (t )) 2 (11)
t 1
functions. The input variables ( E P and E B ) and output
variables ( FFBPC and FFBBC ) be fuzzily partitioned into nine Integral of the Absolute value of the Error (IAE)
N
fuzzy sets, negative very big (NV), negative big (NB), negative
medium (NM), negative small (NS), zero (ZO), positive small
IAE ¦ x1* (t )  x1 (t ) (12)
t 1
(PS), positive medium (PM), positive big (PB), positive very
big (PV). The fuzzy IF-THEN rules are expressed as
Integral of the time multiplied by the Absolute value of the
RBi : IF Γ
E B is MFBi , THEN FFBBC is OBi (8) Error (ITAE)
N
RPi : IF Γ
E P is MFPi , THEN FFBPC is OPi (9) ITAE ¦ t x1* (t )  x1 (t ) (13)
t 1

where the fuzzy sets MFBi , MFPi , OBi , OPi , i 1,2,...,9 are
defined in Table 3. The initial states of the ball and beam system are set to be
x >0 S 0 0@ and the disturbance is added at 10 sec. Fig. 5
indicates the responses of the ball and beam system with
1 conventional ACO and FACO fuzzy controllers. It can be seen
EP that, from Fig. 5(a) and Fig. 5(b), before 10 sec, the ball is
0 EB stopped as desired and the beam is also at the required angle,
1 P1 P2 P3 0 P4 P5 P6 1 respectively. In Fig. 5(a), the response of the proposed method
1 B1 B2 B3 0 B4 B5 B6 1
has no overshoot and quickly converges to he desired position.
1 In particular, with the disturbance added at 10 sec, the proposed
method still has the best performance among other
FFBPC
FFBBC conventional ACOs. The Table 5 presents the criteria with all
0
1 k P1 k P2 k P3 0 k P4 k P5 k P6 1
methods. It can be shown that the proposed algorithm is better
1 k B1 k B2 k B3 0 k B4 k B5 k B6 1 than other conventional ACO optimization methods.
Fig. 4. Membership functions for the FBPC and the FBBC.
Table 4. Parameter table
Table 3. Fuzzy rule base Membership Function
Error Constant, C j
i 1 2 3 4 5 6 7 8 9 Method MF Value, Pi , Bi , k Pi , kbi
i 1 i 2 i 3 i 4 i 5 i 6 j 1 j 2 j 3 j 4
E P ( MFPi )
input NV NB NM NS ZO PS PM PB PV E P -0.75 -0.57 -0.04 0.04 0.57 0.75
E B ( MFBi ) in
AS E B -0.76 -0.70 -0.25 0.25 0.70 0.76
13 8 12 0.85
FFBPC (OPi ) PV PB PM PS ZO NS NM NB NV [2] FFBPC -0.75 -0.54 -0.25 0.25 0.54 0.75
output out
FFBBC (OBi ) NV NB NM NS ZO PS PM PB PV FFBBC -0.75 -0.50 -0.21 0.21 0.50 0.75
E P -0.55 -0.54 -0.05 0.05 0.54 0.55
in
To show the effectiveness of the proposed method, the ACS E B -0.70 -0.54 -0.23 0.23 0.54 0.70
7 4 13 0.7
FACO is proposed to adjust the parameters of the mentioned [1] FFBPC -0.75 -0.54 -0.25 0.25 0.54 0.75
out
fuzzy controllers. The parameters of controllers contain the FFBBC -0.76 -0.50 -0.22 0.22 0.50 0.76
error constant, c1 ~ c4 , the parameters of the input membership in
E P -0.92 -0.80 -0.10 0.10 0.80 0.92
MMAS E B -0.85 -0.50 -0.15 0.15 0.50 0.85
functions, B1 ~ B6 , P1 ~ P6 , and the parameters of the output 14 7 11 0.6
[13] FFBPC -0.75 -0.50 -0.15 0.15 0.50 0.75
membership functions, k B1 ~ k B6 , k P1 ~ k P6 . In this case, the out
FFBBC -0.75 -0.5 -0.25 0.25 0.5 0.75
aim of optimization is that minimizes the cost function. The E P -0.76 -0.60 -0.05 0.05 0.60 0.76
in
cost function is the root mean square error (RMSE), and it is E B -0.97 -0.60 -0.25 0.25 0.60 0.97
FACO 10 7 8 1
defined as follows FFBPC -0.95 -0.50 -0.20 0.20 0.50 0.95
out
FFBBC -0.75 -0.55 -0.25 0.25 0.55 0.75
N
1
Cost
N
¦ (( x1* (t )  x1 (t )) 2  ( x3* (t )  x3 (t )) 2 ) (10)
Table 5. Simulation performance criterion with disturbance
t 1
IAE ISE ITSE
where N is the number of samples. The optimized parameters AS 4.05 u 10 4 4.53 u 105 7.99 u 108
are represented in Table 4. For evaluating the proposed method ACS 3.66 u 10 4 3.97 u 105 7.00 u 108
and other algorithms, some criteria are selected as MMAS 2.96 u 10 4 3.39 u 105 3.67 u 108
FACO 2.79 u 10 4 3.14 u 105 2.67 u 108

619
 World Academy of Science, Engineering and Technology 56 2009

40
Proposed proposed improved ACO algorithm is applied to optimize the
ACS
ball position (cm)

35

30
MMAS
AS
parameter settings of the input and output membership
25 Ȑaȑ functions. Simulation and experimental results illustrate that
20 the improved ACO algorithm can provide better control
15
0 2 4 6 8 10 12 14 16 18 20
performance subject to disturbance.
time (sec)
0.2
Proposed
ball velocity (m/sec)

ACS
0.1 MMAS
AS

0
Ȑbȑ
-0.1

-0.2
0 2 4 6 8 10 12 14 16 18 20
time (sec)
0.1
Proposed
ACS
beam angle (rad)

0.05 MMAS
AS

0
Ȑcȑ
-0.05

-0.1
0 2 4 6 8 10 12 14 16 18 20
time (sec)
beam angle velocity (rad/sec)

1
Proposed

0.5
ACS
MMAS
Fig. 6. Control scheme of the beam and ball control system.
AS

0
Ȑdȑ
-0.5

-1
0 2 4 6 8 10 12 14 16 18 20
time (sec)
20
Proposed
motor voltage (volt)

ACS
10 MMAS
AS

0
Ȑeȑ
-10

-20
0 2 4 6 8 10 12 14 16 18 20
time (sec)

Fig. 5. Simulation response: (a) ball position, (b) ball velocity, (c)
beam angle, (d) beam angle velocity, (e) controller output.

V. EXPERIMENT SETUP AND RESULTS

The experimental setup of a beam and ball control system is
shown in Fig. 6 and Fig. 7, where the control kernel is
Fig. 7. Experiment setup of the ball and beam system
embedded in a digital control platform that combines a DSP
(TMS320C6713) and FPGA (Flex EPF10k70) development
Table 6. Performance criterion ( x1 (0) 38cm, x3 (0) 0$ )
boards. The sampling time of the experiment is selected to be
1ms. Without loss of generality, two initial conditions are IAE ISE ITSE
considered, x3 (0) 0 $ and x3 (0) 1$ . Fig. 8 shows the AS 1.53 u 10 4
3.06 u 10 5
5.49 u 10 7
experiment responses of the beam and ball system with the ACS 1.25 u 10 4 2.52 u 105 3.28 u 107
initial ball position, x1 (0) 38cm , and the initial beam angle, MMAS 1.18 u 10 4
1.91 u 10 5
3.07 u 107
x3 ( 0 ) 1$ . The beam and ball system successfully balances FACO 1.12 u 10 4 1.42 u 105 2.30 u 107
the beam to 0 $ and positions the ball to desired position,
x1d 20cm . The results of experiment performance criterion Table 7. Performance criterion ( x1 (0) 38cm, x3 (0) 1$ )
are showed in Table 6 and Table 7. It can be shown that the IAE ISE ITSE
proposed method has better performance than other methods. AS 1.48 u 10 4
3.04 u 10 5
5.26 u 10 7
ACS 1.26 u 10 4 2.30 u 105 3.30 u 10 7
VI. CONCLUSION
MMAS 1.17 u 10 4 1.85 u 105 2.97 u 10 7
This paper presents an ACO-optimized fuzzy controller for a
beam and ball system. The proposed fuzzy-based ACO
FACO 1.08 u 10 4 1.36 u 105 2.19 u 107
algorithm has the enhanced capability of pheromone updating.
For the fuzzy controller design of a beam and ball system, the

620
 World Academy of Science, Engineering and Technology 56 2009

40
equation (A.1) yields
d ª wL º wL
ball position (cm)

35
J
WB  r(mB  B2 )  mB rD 2  mB g sin D (A.4)
dt «¬ wr »¼ wr
30

25 Ȑaȑ R
d ª wL º wL
20

Wb 
dt «¬ wD »¼ wD
15
0 1 2 3 4 5 6 7 8 9 10
ti ( )
1
l
ball velocity (m/sec)

0.5 ( J b  J B  m B r 2 )D  2m B rrD  (m B gr  mb g ) cos D

2
0
Ȑbȑ
-0.5
(A.5)
Due to W b is not directly provided by DC motor, the
-1
relationship between W b and the DC motor can be derived as
0 1 2 3 4 5 6 7 8 9 10
ti ( )
0.1
follows:
beam angle (rad)

0.05
K K K l
0
Ȑcȑ W b n( b Va  b t Tm ) cos D cos T (A.6)
-0.05
Ra Ra d
-0.1 In (A.4), there is no external force, i.e. W B 0 . From
0 1 2 3 4 5 6 7 8 9 10
ti ( ) (A.4)-(A.6), the state equation of the ball and beam system can
beam angle velocity (rad/sec)

1
be represented as (7)
0.5

0 Ȑdȑ ACKNOWLEDGMENT
-0.5
This work is partially supported by Ministry of Economic
-1
0 1 2 3 4 5 6 7 8 9 10 Affairs, Taiwan under Technology Development Program for
20
Academia (TDPA) in the project “Developing A Brain Medical
motor voltage (volt)

10 Augmented Reality System” with Grant No. 97-EC-17-A-19-

0 S1-035.
Ȑeȑ
-10

-20
REFERENCES
0 1 2 3 4 5 6 7 8 9 10
time(sec) [1] M. Dorigo, L.M. Gambardella, “Ant colony system : a cooperative
learning approach to the traveling salesman problem, ” IEEE Tran. on
Fig. 8. Experiment response ( x1 (0) 38cm, x3 (0) 1 ):
$
Evolutionary Computation, vol. 1, no. 1, pp. 53-66, 1997.
(a) ball position, (b) ball velocity, (c) beam angle, (d) beam angle [2] M. Dorigo, V. Maniezzo, and A. Colorni, “Ant system: optimization by a
velocity, (e) controller output. colony of cooperating agents,” IEEE Tran. on Systems, Man, and
Cybernetics, Part B: Cybernetics, vol. 26, no. 1, pp. 29-41, 1996.
[3] C. Blum, “Ant colony optimization: Introduction and recent trends, ”
Physics of Life Reviews, vol. 2, no. 4, pp. 353-373, 2005.
APPENDIX [4] Y. Li and S. Gong, “Dynamic ant colony optimisation for TSP, ” The
The ball and beam system is a classic underactuated International Journal of Advanced Manufacturing Technology, vol. 22,
pp. 528-533, 2003.
nonlinear system. The system parameters for the ball and beam [5] C.F. Tsai, C.W. Tsai, and C.C. Tseng, “A new hybrid heuristic approach
system model are listed in Table 2. To obtain the possible for sloving large travling salesman problem, ” Information Sciences, vol.
mathematical model of a ball and beam system, the associated 166, no. 1, pp. 67-81, 2004.
Euler-Lagrange dynamic equation is first addressed in (A.1). [6] S.C. Negulescu, C.V. Kifor, and C. O, “Ant colony solving multiple
constrains problem: Vehicle route allocation, ” International Journal of
d ª wL º wL Computers, Communications and Control, vol. 3, no. 4, pp. 366-373,
« » Q (A.1)
dt ¬ wq ¼ wq 2008.
[7] J. Heinonen and F. pettersson, “Hybrid ant colony optimization and
where q >r D @T Q >W B W b @T , L=(the kinetic energy, K)-(the visibility studies applied to a job-shop scheduling problem, ” Applied
Mathematics and Computation, vol. 187, no. 2, pp. 989-998, 2007.
potential energy, P), r is the position of the ball, D is the [8] L.Y. Tseng and S.C. Liang , “A hybrid metaheuristic for the quadratic
beam angle, W b is a torque provided by a DC motor to the beam assignment problem,” Computational Optimization and Applications, vol.
14, no. 1, pp. 85-113, 2006.
via gear and linker, and W B is an exogenous torque to the Ball. [9] S. Tsutsui, “Solving the quadratic assignment problems using parallel
It is noted that W B is physically considered as the disturbance to ACO with symmetric multi processing, ” Transactions of the Japanese
Society for Artificial Intelligence, vol. 24, no. 1, pp. 46-57, 2009.
the ball. As show in Fig. 1, to derive the dynamic equation of [10] A.P. Engelbrecht, Computational Intelligence: An Introduction, 2nd,
the ball and beam system, the kinetic energy K and P can be Wiley, 2007.
represented as follows: [11] C. Martinez, O. Castillo, and O. Montiel, “Comparison between ant
colony and genetic algorithms for fuzzy system optimization, ” Studies in
1 1 r 2 1 1 Computational Intelligence, vol. 154, no. 4, pp. 71-86, 2008.
K mB r 2  J B ( ) 2  ( J B  mB r 2 )D 2  J bD 2 (A.2) [12] C.F. Juang and C. Lo, “Zero-order TSK-type fuzzy system learning using
2 2 R 2 2
a two-phase swarm intelligence algorithm, ” Fuzzy Sets and Systems, vol.
l
P mb g sin D  mB gr sin D (A.3) 159, no. 21, pp. 2910-2926, 2008.
2 [13] T. Stutzle, H.H. Hoos, “Max-Min ant system, ” Future Generation
Computer Systems, vol. 16, no. 8, pp. 889-914, 2000.
Substituting (A.2) and (A.3) into Lagrange dynamic

621