IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICSPART B: CYBERNETICS, VOL. 33, NO.

3, JUNE 2003

489

Robust Control for Nonlinear Motor-Mechanism

Coupling System Using Wavelet Neural Network
Rong-Jong Wai, Member, IEEE

AbstractA robust controlled toggle mechanism, which is

driven by a permanent magnet (PM) synchronous servo motor
is studied in this paper. First, based on the principle of computed torque control, a position controller is developed for the
motor-mechanism coupling system. Moreover, to relax the requirement of the lumped uncertainty in the design of a computed
torque controller, a wavelet neural network (WNN) uncertainty
observer is utilized to adapt the lumped uncertainty online.
Furthermore, based on the Lyapunov stability a robust control
system, which combines the computed torque controller, the WNN
uncertainty observer and a compensated controller is proposed
to control the position of the motor-mechanism coupling system.
The computed torque controller with WNN uncertainty observer
is the main tracking controller, and the compensated controller is
designed to compensate the minimum approximation error of the
uncertainty observer. Finally, simulated and experimental results
due to a periodic sinusoidal command show that the dynamic
behaviors of the proposed robust control system are robust with
regard to parametric variations and external disturbances.
Index TermsComputed torque control, permanent magnet
synchronous servo motor, robust control, toggle mechanism,
uncertainty observer, wavelet neural network.

I. INTRODUCTION

OMPUTED torque or inverse dynamics technique is a special application of feedback linearization of nonlinear systems. A number of works related to computed torque control of
robotic manipulators have been published [1]. The computed
torque controller is utilized to linearize the nonlinear equation
of robot motion by cancellation of some, or all, nonlinear terms
[1]. However, the objection to the real-time use of such control
scheme is the lack of knowledge of uncertainties, which include
parametric variations and external disturbances of the system.
The adaptive control technique is essential for providing a stable
and robust performance for a wide range of applications (e.g.,
robot control, process control, etc.), and most of the applications
are inherently nonlinear with uncertainties [2][4]. Therefore,
several computed torque controllers have tried to circumvent the
problem of uncertainties using adaptive techniques [5][7].
Recently, much research has been done on applications of
wavelet neural networks, which combine the capability of
artificial neural networks in learning from processes [8][11]
and the capability of wavelet decomposition [12][15] for identification and control of dynamic systems [16][20]. In Zhang
Manuscript received May 28, 2000. This work was supported by the National
Science Council of Taiwan, R.O.C., under Grant NSC 90-2213-E-155-014. This
paper was recommended by Associate Editor P. E. Borne.
The author is with the Department of Electrical Engineering, Yuan Ze University, Chung-Li 32026, Taiwan, R.O.C. (e-mail: rjwai@saturn.yzu.edu.tw).
Digital Object Identifier 10.1109/TSMCB.2003.811125

and Benveniste [16], the new notation of wavelet network was

proposed as an alternative to feedforward neural networks
for approximating arbitrary nonlinear functions based on the
wavelet transform theory, and a backpropagation algorithm
was adopted for wavelet network training. Zhang et al. [17]
described a wavelet-based neural network for function learning
and estimation, and the structure of this network was similar to
that of the radial basis function network except that the radial
functions were replaced by orthonormal scaling functions.
Zhang [18] presented wavelet network construction algorithms
for the purpose of nonparametric regression estimation. From
the point of view of function representation, the traditional
radial basis function (RBF) networks can represent any function
that is in the space spanned by the family of basis functions.
However, the basis functions in the family are generally
not orthogonal and are redundant. This means that the RBF
network representation for a given function is not unique and is
probably not the most efficient. In this study, the family of basis
functions for the RBF network is replaced by an orthogonal
basis (i.e., the scaling functions in the theory of wavelets) to
form a wavelet neural network [17], [19].
The toggle mechanism has many applications, for example,
clutches, rock crushers, truck tailgates, vacuum circuit breakers,
pneumatic riveters, punching machines, forging machines, and
injection modeling machines, etc. On the other hand, a permanent magnet (PM) synchronous servomotor has some merit
of compact structure, high air-gap flux density, high power
density, high torque-to-inertia ratio, and high torque capability.
Moreover, compared with an induction servomotor, a PM synchronous servomotor has such advantages as higher efficiency,
due to the absence of rotor losses and lower no-load current
below the rated speed, and its decoupling control performance
is much less sensitive to the parameter variations of the motor.
Thus, the PM synchronous servomotor plays a vitally important
role in motion-control applications in the low-to-medium power
range. In the past year, a fuzzy neural network (FNN) control
and a variable structure model-following control (VSMFC) on
the toggle mechanism actuated by a PM synchronous servomotor have been presented in [21], [22]. In Lin et al. [21], an
FNN controller with adaptive learning rates was implemented
to control a motor-toggle servomechanism. However, this
control strategy lacks a stability analysis, and many rules and
a pre-training process are needed for the FNN to achieve the
best control performance. In Wai et al. [22], a VSMFC system,
which was designed based on the principles of the adaptive
model-following control and the variable structure control,
was developed to control the position of a slider of the toggle
mechanism servo system. Although the stability property of

1083-4419/03$17.00 2003 IEEE

490

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICSPART B: CYBERNETICS, VOL. 33, NO. 3, JUNE 2003

Fig. 1. Toggle mechanism driven by PM synchronous servo motor.

the VSMFC system can be guaranteed, some prior knowledge

about the controlled plant must be known, e.g., the bound of the
variation of system parameters and external load disturbance.
Therefore, the motivation of this study is to design a control
scheme to cope with the disadvantages mentioned above. Not
only is the stability property guaranteed, but also, no prior
knowledge of the controlled plant is required.
A toggle mechanism actuated by a PM synchronous servo
motor drive using a robust control system is described in this
study. First, based on the principles of computed torque control,
a position controller is developed. However, the general problem
in the design of a computed torque controller for the mechanical
systems is that the exact lumped uncertainty of the mechanical
system are difficult to be obtained in advance for practical applications. Therefore, an WNN uncertainty observer is utilized
to adapt the lumped uncertainty on line. Furthermore, based on
the Lyapunov stability a robust control system, which combines
the computed torque controller with the WNN uncertainty observer and a compensated controller, is proposed to control the
position of a slider of the motor-toggle servomechanism. The
computed torque controller with the WNN uncertainty observer
acts as the main tracking controller, and the compensated controller is designed to compensate the minimum approximation
error of the uncertainty observer. Finally, simulated and experimental results due to a periodic sinusoidal command are provided to validate the effectiveness of the proposed robust control
scheme.
II. MOTOR-MECHANISM COUPLING SYSTEM
A toggle mechanism driven by a PM synchronous motor is
depicted in Fig. 1 [21], [22], in which the most important parameters that affect the control performance of the toggle mechand the parameter variation of
anism are the external force
. Moreover,
,
, and
the mass of slider , known as
are the mass of links 2, 3 and 5, respectively; , , and
are the length of link 2, respectively;
and
are the length
are the angle of
of links 3 and 5, respectively; , , and
and
are the forces acting
links 2, 3 and 5, respectively;
on sliders and , respectively; is the height between the

two horizontal guides where sliders and move along; is

an offset between links 2 and 3. Hamiltons principle and the
Lagrange multiplier have been used in [21] and [22] to derive
the differential-algebraic equation for the toggle mechanism.
The implicit method must be employed to solve the differential-algebraic equation of mechanical motion. The result is a set
of differential equations with only one independent generalized
coordinate.
The motor-mechanism coupling system shown in Fig. 1 can
be represented by the following equation:
(1)
is a variable vector,
denotes a
where
is a control gain,
nonlinear dynamic function,
represents disturbance and friction function, and
is the con,
and
include
trol effort. Moreover,
the uncertainties introduced by system parameters and external
is a constant
disturbance. In addition, the control gain
negative-sign function and invertible [21]. Now, assume that the
parameters of the system are well known and rewrite (1) as
(2)
and
are the nominal values of
and
, and
is the nominal value of
, in which the external disturbance
. If the
uncertainties occur, i.e., the parameters of the system are
deviated from the nominal value or an external disturbance is
added into the system, the dynamic equation of the coupling
system can be modified as

where

(3)
,
and
denote uncertainties, and
where
called the lumped uncertainty and is defined as

is
(4)

WAI: ROBUST CONTROL FOR NONLINEAR MOTOR-MECHANISM COUPLING SYSTEM

491

Fig. 2. Block diagram of motor-toggle servomechanism using robust control system.

III. ROBUST CONTROL SYSTEM

The proposed robust control system is depicted in Fig. 2,
,
,
, and
are the command slider position,
where
slider position, command angle of link 2, and angle of link 2,
is the desired control objective and is
respectively. Since
and
the state of the motor-mechanism coupling system, the
should be transformed to
and
using the one-to-one
relationship [21], [22] as follows:

If the lumped uncertainty of the controlled system is well

known, the computed torque control law can be defined as
follows:

(8)
, and
and
are
where the control gain
positive constants. Substituting (8) into (3) and using (7), it can
be obtained that
(9)

(5)
A linear scale detects the position signal of the slider
the robust control law is defined as follows:

. Now,

(6)
is a computed torque controller and
is a comwhere
pensated controller. The computed torque controller with the
WNN uncertainty observer is the main tracking controller, and
the compensated controller is designed to compensate the minimum approximation error of the WNN uncertainty observer.

If the control gain is selected properly such that all roots of

the polynomial (9) are in the open left-half complex plane, it im, that is, the state can track the desired
plies
asymptotically. Since the lumped uncertainty
trajectories
is unknown in practical applications, a WNN uncertainty observer is proposed to adapt the value of the lumped
uncertainty . The purpose of the uncertainty observer is to
for the computed torque controller to
determine a value of
under
compel the state to follow the desired trajectories
the occurrence of uncertainties. From (8), the computed torque
controller is now defined as

(10)

A. Computed Torque Controller

The control problem is to find a control law such that the state
can track the desired trajectories
in the presence of the
uncertainties. Let the tracking error vector be
(7)

B. WNN Uncertainty Observer

A four-layer WNN [17], [19], which is comprised of an input
(the layer), a mother wavelet (the layer), a wavelet (the
layer), and an output layer (the layer), is adopted to implement the proposed WNN uncertainty observer. The inputs of the

492

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICSPART B: CYBERNETICS, VOL. 33, NO. 3, JUNE 2003

WNN are
and its derivative; the output of the WNN is the
estimated lumped uncertainty . The signal propagation and
the basic function in each layer are introduced in the following
paragraph.
For every node in the input layer, the net input and the net
output are represented as

C. Compensated Controller
To develop the compensated controller, first, the minimum
approximation error is defined as follows:
(16)
where

(11)
and
. Moreover, a family of wavelets
where
is constructed by translations and dilations performed on a
single fixed function called the mother wavelet. In the mother
that is derived
wavelet layer each node performs a wavelet
from its mother wavelet. The first derivative of a Gaussian
is adopted as a mother
function
wavelet in this study. It may be regarded as a differentiable
version of the Haar mother wavelet, just as the sigmoid is a
differentiable version of a step function, and it has the universal
approximation property [19]. For the th node

is an optimal weight vector achieves the minimum approximais the absolute value. In this study, it
tion error, in which
is assumed that the amplitude of is less than a positive conif the system existent uncertainties are
stant (i.e.,
bounded. Although the existent uncertainty in practical application is difficult to measure, a more conservative value of bound
is selected according to the powerful approximated ability of
the WNN uncertainty observer. From (3), (6), and (10), an error
equation is obtained as follows:

(12)
and
are, respectively, the translation and dilation
where
vectors in the th term of the th input to the node of layer 2,
and is the total number of the wavelets with respect to the input
nodes. In addition, each node in the wavelet layer is denoted
by , which multiplies the input signals and outputs the result
of the product, i.e., the product of monodimensional wavelets
with respect to the input node [19]. For the th-rule node

(17)
is a stable matrix, and
where
Then, a Lyapunov function is defined as

(18)
(13)
represents the th input to the node of layer 3;
,
where
which are the weights between the mother wavelet layer and the
is the number
wavelet layer, are assumed to be unity;
of wavelets with complete connection if each input node has
the same wavelet nodes. Furthermore, the single node in the
output layer is labeled as , which computes the overall output
as the summation of all input signals

where is a positive constant, and is a symmetric positive

definite matrix which satisfies the following Lyapunov equation
(19)
is selected by the designer. Taking the derivative of
and
the Lyapunov function, and use (17) and (19), then

(14)
is the output action strength
where the connecting weight
represents
of the th output associated with the th wavelet;
. On the other
the th input to the node of layer 4, and
can be rewritten as follows [23]:
representation,
(15)
, in which
is initialwhere
ized to be zero and adjusted during on-line operation;
, in which
is determined by the selected
.
wavelets and

(20)
To satisfy
controller

, the adaptation law

are designed as follows:

and the compensated

(21)
sgn

(22)

WAI: ROBUST CONTROL FOR NONLINEAR MOTOR-MECHANISM COUPLING SYSTEM

where sgn is a sign function. Substituting (21) into (20) and

using (22), then

493

Theorem 1: Let the constraint set

is defined in (28). If the
, the adaptation law (28)
initial values of the weights
for all
.
guarantees that
Proof: Define a Lyapunov function
(29)

(23)
,
is negative semidefinite [i.e.,
Since
], which implies that and
are bounded. Let
, and integrate function
function
with respect to time
(24)
is bounded, and
Because
bounded, then

is nonincreasing and

(25)
Differentiate

with respect to time

(26)

Since all the variables on the right side of (17) are bounded, it
is uniformly continuous
implies is also bounded. Then
[3]. By using Barbalats lemma [2], [3], it can be shown that
. Therefore,
as
. As a result,
the robust control system is asymptotically stable. Moreover, the
tracking error of the system will converge to zero according
. On the other hand, the guaranteed convergence
to
of tracking error to be zero does not imply convergence of the
estimated value of the lumped uncertainty to its real value. The
persistent excitation condition [3] should be satisfied for the estimated value to converge to its theoretic value.
D. Convergence Analyzes of WNN
According to the assumption of the bound of the minimum
approximation error, the stability proof of the robust control
system can be guaranteed; however, the convergence condition
of the WNN must be satisfied. If the parameters of the WNN
are bounded, the convergence property of the WNN can be
guaranteed. From (15), the output of the WNN is bounded if
the weights between the output layer and the wavelet layer are
for as
bounded. Define the constrain set

Take the derivative of the Lyapunov function with respect to

time
(30)
and
. Thus,
. On the other hand,
and
hold,
.
. Since the
Thus, it also can be guaranteed that
,
initial value of is initialized to be zero (i.e.,
is bounded by the constraint set
for all
.
Remark: Since the convergence property of the WNN can
be guaranteed, it is reasonable that the minimum approximation
error assumed to be bounded. The bound of the approximation
error is chosen to achieve the best transient control performance in both the simulation and experimentation considering
the possible variation of operating conditions.
When the conditions (
) hold,
it can be guaranteed that
when the conditions

) or (

E. Stability Analyzes Using Projection Algorithm

The modification of the adaptation law shown in (28) can
guarantee that the weights between the output layer and the
wavelet layer are bounded. Thus, the convergence property of
the WNN can be guaranteed. Moreover, the asymptotical stability of the proposed robust control system using the projection
algorithm can be summarized in the following theorem.
Theorem 2: Consider the motor-mechanism coupling system
represented by (1). If the robust control law is designed as (6),
in which the computed torque controller is designed as (10),
the WNN uncertainty observer is designed as (15), the adaptation law of the WNN is designed as (28), and the compensated
controller is designed as (22), then asymptotically stability is
guaranteed.
or (
Proof: When the conditions
and
hold, the stability analysis is the same
and
as Section III-C. On the other hand, when
, the derivative of the Lyapunov function
shown in (20) can be rewritten as follows:

(27)
is a two-norm of vector. According to the projecwhere
tion algorithm [23], the adaptation law (21) can be modified
as follows:
if
or
and

if
and
(28)

(31)

494

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICSPART B: CYBERNETICS, VOL. 33, NO. 3, JUNE 2003

Fig. 3. Simulated responses of robust control system. (a)(c) Case 1. (d)(f) Beginning at Case 1 and changing to Case 2 at 5 s. (g)(i) Beginning at Case 1 and
changing to Case 3 at 5 s.

Using the property

, which is according to
and the compensated controller shown in (22), then

,
(32)
By use of Barbalats lemma [2], [3], as shown in Section III-C,
as
. Thus, the stability property also can
be guaranteed. The effectiveness of the proposed robust control system for the control of motor-toggle servomechanism will

WAI: ROBUST CONTROL FOR NONLINEAR MOTOR-MECHANISM COUPLING SYSTEM

495

Fig. 3. (Continued). Simulated responses of robust control system. (a)(c) Case 1, (d)(f) Beginning at Case 1 and changing to Case 2 at 5 s; (g)(i) Beginning
at Case 1 and changing to Case 3 at 5 s.

be demonstrated by the following numerical and experimental

results.
IV. NUMERICAL AND EXPERIMENTAL RESULTS
By use of RungeKutta fourth-order numerical integration
method, (1) is solved for the motor-mechanism coupling
system. For numerical simulations, the parameters of the toggle
mechanism are designed as follows:
kg

kg

kg

kg

m
m

kg

m
m

m
(33)

in which
is the lead of the screw,
is the mass of slider ,
and and are the friction coefficient and gravity acceleration,
respectively. In addition, the gains of the robust control system
are given as
(34)
in this study is selected as an
For simplicity, the matrix
identity matrix. All the gains in the robust control system are
chosen to achieve the best transient control performance in
both simulation and experimentation considering the limitation
of the control effort and the requirement of stability. Moreover,
the initialization of the network parameters described in [19]
is adopted to initialize the parameters of the wavelets in this
study. The WNN has two, 14, seven, and one neurons at the
input, mother wavelet, wavelet, and output layer, respectively.
Three simulation cases due to a periodic sinusoidal command
are addressed as follows:

496

Fig. 4.

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICSPART B: CYBERNETICS, VOL. 33, NO. 3, JUNE 2003

Experimental results of robust control system: (a)(c) Nominal case; (d)(f) Parameter variation case.

Case 1) nominal case (

kg and
);
Case 2) parameter variation case (7.4 kg weight is added to
the mass of slider and
);
kg and
Case 3) external disturbance case (
).
The control objective is to control the slider to move 0.02 m
periodically. In addition, the initial position of
is 0.1216 m,
is equal to 0.02 m.
and the controlled stroke of the slider ,
Substituting the slider position
into (5), the angle of link 2
can be obtained.
In the simulation, the robust control system shown in Fig. 2 is
considered under different simulated conditions. The simulated
results at Case 1, beginning at Case 1 and changing to Case 2
at 5 s, and beginning at Case 1 and changing to Case 3 at 5 s,
are all depicted in Fig. 3. The responses of the position of slider
are depicted in Fig. 3(a), (d), and (g); the associated control
effort are depicted in Fig. 3(b), (e), and (h); the theoretic and

estimated lumped uncertainty are depicted in Fig. 3(c), (f), and

(i). From the simulated results, the proposed control scheme is
robust under the occurrence of parameter variation and external
disturbance. In addition, some experimental results are provided
here to further demonstrate the effectiveness of the robust control system. The control algorithms are implemented using a
Pentium computer with a 2-ms sampling interval. Two test conditions are provided, which are the nominal case and the parameter variation case. In the experimentation, two iron disks with
7.4 kg weight to the mass of the slider are added to the parameter variation case. The responses of the robust control system
at two test conditions due to a periodic sinusoidal command are
depicted in Fig. 4, in which the responses of the position of slider
are depicted in Fig. 4(a) and (d); the associated control effort
are depicted in Fig. 4(b) and (e); the estimated lumped uncertainty are depicted in Fig. 4(c) and (f). From the experimental
results, the tracking errors converge quickly, and the robust con-

WAI: ROBUST CONTROL FOR NONLINEAR MOTOR-MECHANISM COUPLING SYSTEM

trol characteristics of the robust control system under the occurrence of parameter variation can be clearly observed.
V. CONCLUSIONS
This study successfully demonstrates the application of a robust control system to control the position of a slider of the
motor-toggle servomechanism. First, the mathematical model
of the motor-toggle servomechanism was introduced. Then, the
theoretical bases of the proposed computed torque controller,
WNN uncertainty observer, and compensated controller were
described in detail. Moreover, simulation and experimentation
were carried out using a periodic sinusoidal reference trajectory
to test the effectiveness of the proposed robust control system.
The major contributions of this study are i) the successful development of a robust control methodology, in which an WNN
is utilized to adapt the lumped uncertainty on line and a compensated controller is designed to compensate the minimum approximation error of the WNN uncertainty observer, and ii) the
successful application of the robust control system to control the
slider position of the motor-mechanism coupling system considering the existence of uncertainties.
ACKNOWLEDGMENT
The author would like to express his gratitude to the referees
and Associate Editor for their kind comments and suggestions.
REFERENCES
[1] R. Ortega and M. W. Spong, Adaptive motion control of rigid robots:
A tutorial, in Proc. IEEE Conf. Decision Contr., 1988, pp. 15751584.
[2] K. J. Astrom and B. Wittenmark, Adaptive Control. New York: Addison-Wesley, 1995.
[3] J.-J. E. Slotine and W. Li, Applied Nonlinear Control. Englewood
Cliffs, NJ: Prentice-Hall, 1991.
[4] R. Johansson, Adaptive control of robot manipulator motion, IEEE
Trans. Robot. Automat., vol. 6, pp. 483490, Aug. 1990.
[5] C. Y. Su and T. P. Leung, A sliding mode controller with bound estimation for robot manipulators, IEEE Trans. Robot. Automat., vol. 9, pp.
208214, Apr. 1993.
[6] J. Imura, T. Sugie, and T. Yoshikawa, Adaptive robust control of robot
manipulators-theory and experiment, IEEE Trans. Robot. Automat.,
vol. 10, pp. 705710, Oct. 1994.
[7] M. Teshnehlab and K. Watanabe, Self tuning of computed torque gains
by using neural networks with flexible structures, Proc. Inst. Elect.
Eng.Control Theory Appl., vol. 141, no. 4, pp. 235242, 1994.
[8] M. H. R. Fazlur Rahman, R. Devanathan, and Z. Kuanyi, Neural network approach for linearizing control of nonlinear process plants, IEEE
Trans. Ind. Electron., vol. 47, pp. 470477, Apr. 2000.
[9] J. R. Noriega and H. Wang, A direct adaptive neural-network control
for unknown nonlinear systems and its application, IEEE Trans. Neural
Networks, vol. 9, pp. 2734, Jan. 1998.

497

[10] M. Zhihong, H. R. Wu, and M. Palaniswami, An adaptive tracking controller using neural networks for a class of nonlinear systems, IEEE
Trans. Neural Networks, vol. 9, pp. 947955, Sept. 1998.
[11] O. Omidvar and D. L. Elliott, Neural Systems for Control. New York:
Academic, 1997.
[12] Y. C. Pati and P. S. Krishnaprasad, Analysis and synthesis of feedforward neural networks using discrete affine wavelet transformations,
IEEE Trans. Neural Networks, vol. 4, pp. 7385, Jan. 1993.
[13] B. Delyon, A. Juditsky, and A. Benveniste, Accuracy analysis for
wavelet approximations, IEEE Trans. Neural Networks, vol. 6, pp.
332348, Apr. 1995.
[14] C. F. Chen and C. H. Hsiao, Wavelet approach to optimising dynamic
systems, Proc. Inst. Elect. Eng.Contr. Theory Appl., vol. 146, no. 2,
pp. 213219, 1999.
[15] T. Lindblad and J. M. Kinser, Inherent features of wavelets and pulse
coupled networks, IEEE Trans. Neural Networks, vol. 10, pp. 607614,
May 1999.
[16] Q. Zhang and A. Benveniste, Wavelet networks, IEEE Trans. Neural
Networks, vol. 3, pp. 889898, Nov. 1992.
[17] J. Zhang, G. G. Walter, Y. Miao, and W. N. W. Lee, Wavelet neural
networks for function learning, IEEE Trans. Signal Processing, vol. 43,
pp. 14851496, June 1995.
[18] Q. Zhang, Using wavelet network in nonparametric estimation, IEEE
Trans. Neural Networks, vol. 8, pp. 227236, Mar. 1997.
[19] Y. Qussar, I. Rivals, L. Personnaz, and G. Dreyfus, Training wavelet
networks for nonlinear dynamic input-output modeling, Neurocomputing, vol. 20, pp. 173188, 1998.
[20] L. M. Reyneri, Unification of neural and wavelet networks and fuzzy
systems, IEEE Trans. Neural Networks, vol. 10, pp. 801814, July
1999.
[21] F. J. Lin, R. F. Fung, and R. J. Wai, Comparison of sliding mode and
fuzzy neural network control for motor-toggle servomechanism, IEEE
Trans. Mechatron., vol. 3, pp. 302318, Dec. 1998.
[22] R. J. Wai, F. J. Lin, and K. K. Shyu, A toggle mechanism servo system
with variable structure model-following control, Int. J. Syst. Sci., vol.
30, no. 11, pp. 12131226, 1999.
[23] L. X. Wang, A Course in Fuzzy Systems and Control. Englewood
Cliffs, NJ: Prentice-Hall, 1997.

Rong-Jong Wai (M00) was born in Tainan, Taiwan,

R.O.C., in 1974. He received the B.S. degree in
electrical engineering and the Ph.D. degree in electronic engineering from the Chung Yuan Christian
University, Chung-Li, Taiwan, in 1996 and 1999,
respectively.
Since 1999, he has been with the Department
of Electrical Engineering, Yuan Ze University,
Chung-Li, where he is currently an Associate
Professor. He is the chapter author of Intelligent
Adaptive Control: Industrial Applications in the
Applied Computational Intelligence Set (Boca Raton, FL: CRC, 1998) and the
co-author of Drive and Intelligent Control of Ultrasonic Motor (Chung-Li,
Taiwan: Tsang-Hai, 1999) and Electric Control (Chung-Li, Taiwan: Tsang-Hai,
2002). He has authored numerous published journal papers in the area of
intelligent control applications. His research interests include motor servo
drives, mechatronics, nonlinear control, and intelligent control systems,
including neural networks and fuzzy logic.