-
[show abstract]
[hide abstract]
ABSTRACT: In this paper an efficient Q-learning paradigm implemented on a fuzzy CMAC network is proposed. The fuzzy CMAC network topological architecture is described. The continuous states of the system are partitioned into a number of fuzzy boxes. With the proposed fuzzy CMAC the Q-values of agents in the fired fuzzy boxes are evaluated and the control actions with maximum Q-values can be derived. The proposed hybrid adaptive and learning type of Fuzzy Neural control system based on the Q-learning is applied to the control of a pH-neutralization process.
Fuzzy Systems, 2003. FUZZ '03. The 12th IEEE International Conference on; 06/2003
-
[show abstract]
[hide abstract]
ABSTRACT: A class of fuzzy neural network with dynamic weights is proposed and its corresponding network topological architecture with suitable supervised learning algorithm is presented. Using the proposed network in control system design, a priori knowledge of the control system is not essential and this includes the order of the control system. The proposed network is applied to the control of a highly nonlinear pH-neutralization process. Simulation shows that the proposed dynamic learning control strategy has better dynamic quality, stronger robustness, adaptability and intelligence while comparing to the conventional control techniques, which demand the explicit and quantitative mathematical model of the system under control.
Fuzzy Systems, 2001. The 10th IEEE International Conference on; 01/2002
-
[show abstract]
[hide abstract]
ABSTRACT: Case-based reasoning (CBR) can support hydraulic circuit design. Existing expert systems for hydraulic system design use production rules as its source of knowledge. However, this leads to problems of knowledge acquisition and knowledge base maintenance. This paper describes the application of CBR to hydraulic circuit design for production machines, which helps solving problems using past experience. A technique Case-based adaptation (CBA) is implemented in the adaptation stage of CBR so that adaptation becomes much easier. A prototype system has been developed to verify the usefulness of CBR and CBA in hydraulic production machines.
Engineering Applications of Artificial Intelligence 01/2002; 15:567-585. · 1.66 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: Deals with adaptive control of a class of nonlinear dynamic
systems preceded by unknown backlash-like hysteresis nonlinearities,
where the hysteresis is modeled by a differential equation. By
exploiting solution properties of the differential equation and
combining those properties with adaptive control techniques, a robust
adaptive control algorithm is developed without constructing a
hysteresis inverse. The new control law ensures global stability of the
adaptive system and achieves both stabilization and tracking to within a
desired precision. Simulations performed on a nonlinear system
illustrate and clarify the approach
IEEE Transactions on Automatic Control 01/2001; · 2.11 Impact Factor
-
01/2001
-
[show abstract]
[hide abstract]
ABSTRACT: In this study, forecasting and compensatory control (FCC)
techniques are employed to improve the workpiece roundness accuracy in
taper turning on an experimental lathe. This paper describes the
methodology to online determine, model and forecast the workpiece
roundness error using autoregressive (AR) modelling and the aspects
associated with its practical implementation on the turning process.
Experimental results have shown that an improvement of around 24% was
achieved for the roundness error of workpieces in the taper turning
operations
American Control Conference, 1997. Proceedings of the 1997; 07/1997
-
[show abstract]
[hide abstract]
ABSTRACT: Recent researches show that neural networks have the ability to
approximate a function as well as its derivatives. This result offers a
promising opportunity to introduce neural network theory into nonlinear
system control. In this paper a novel method of approximate nonlinear
system linearization with neural networks is proposed. The network
approximator is designed to integrate the involutive equation of a
nonlinear system no matter whether the integrability condition is
satisfied or not. Simulation results show that this method is feasible
Intelligent Control, 1996., Proceedings of the 1996 IEEE International Symposium on; 10/1996
-
[show abstract]
[hide abstract]
ABSTRACT: In this paper, an inverse system method (ISM), which is a simple
exact linearization method for nonlinear system design, has been
employed to design a nonlinear excitation control law of synchronous
generator, and neural network is proposed for the controller to provide
desired controller output. The main motivation is to exploit
generalization capabilities of neural networks to interpolate between
training data, and thus to deal with system parametric uncertainties
caused by a large sudden fault. Simulation results show that transient
stability of the perturbed power system can be improved
Neural Networks, 1995. Proceedings., IEEE International Conference on; 12/1995
-
[show abstract]
[hide abstract]
ABSTRACT: A novel control scheme for the flexible manipulator based on
variable structure system theory is proposed and tested. The controller
shows the robustness towards the variation of the system parameters.
Also the performance of the controller can be tuned easily without
complicated calculation for stability. Experimental results are
presented and they are compared with those obtained from the hybrid
proportional controller which is based on the optimal control scheme
American Control Conference, 1995. Proceedings of the; 07/1995
-
[show abstract]
[hide abstract]
ABSTRACT: Presents a new approach using a fuzzy logic control method based
on reference model tracking to overcome the uncertainties of vehicle
dynamic systems. Simulation of the lateral velocity and the yaw rate
control show that it is satisfactory to apply this method to vehicle
dynamic control resulting in close matching with the reference model
American Control Conference, 1995. Proceedings of the; 07/1995
-
[show abstract]
[hide abstract]
ABSTRACT: A system using a variable structure controller (VSC) in the
sliding mode is robust to disturbances. However, this advantage cannot
be obtained in the reaching phase. The remedial approach adopted here is
that a small switching surface slope is used at the beginning and then
it is increased continuously when the system output approaches the
reference setting. This method reduces the duration of the reaching
phase and hence the sensitivity to disturbances during the early control
period. Simulation of a brushless DC motor velocity regulator system to
illustrate the effectiveness of the approach is included in this paper
Power Electronics and Drive Systems, 1995., Proceedings of 1995 International Conference on; 03/1995
-
[show abstract]
[hide abstract]
ABSTRACT: This paper describes an object-oriented CAD system for
electro-pneumatic sequential circuits. The system is organised in an
object-oriented manner for supporting both pneumatic power system and
control system design. An algorithm is developed based on the Karnaugh
mapping method to generate indexing equations to link appropriate
objects to perform sequential control system design. The algorithm
developed can handle an ordinary sequence, a sequence with simultaneous
paths and a time delay function. A class which encapsulates this
algorithm is described in detail. A prototype system (OOCADEP) written
in C++ has been developed to demonstrate the concept
Emerging Technologies and Factory Automation, 1994. ETFA '94., IEEE Symposium on; 12/1994
-
[show abstract]
[hide abstract]
ABSTRACT: This paper describes the use of genetic algorithms (GAs) for
optimizing the parameters of PID controllers for a 6-DOF robot arm. An
efficient GA is designed to optimal-tune the parameters of the PID
controller of each joint for a single step response and for the tracking
of other specified trajectories. This GA is required to optimize fitness
functions related to the combinations of different performance indices
such as ISE, time-optimal and others. The simulations are carried out on
a PUMA 560 arm model being controlled by PID controllers with their
parameters optimized using the proposed GA. The simulation results
obtained are compared with that obtained by traditional optimization
techniques, wherever applicable
Industrial Electronics, Control, and Instrumentation, 1993. Proceedings of the IECON '93., International Conference on; 12/1993
-
[show abstract]
[hide abstract]
ABSTRACT: In this paper, an iterative learning control strategy is presented
for a class of constrained robots. The controller design is based on the
reduced form of the robot model. The strategy guarantees the perfect
motion tracking of the robot with its end-effector moving on a linear
and frictionless constrained surface in the presence of unknown bounded
disturbances. The bounded and adjustable force tracking error is
obtained
TENCON '93. Proceedings. Computer, Communication, Control and Power Engineering.1993 IEEE Region 10 Conference on; 11/1993
-
[show abstract]
[hide abstract]
ABSTRACT: This paper addresses an adaptive inverse dynamics robotic control algorithm. Based on Lyapunov stability theory, the theorems on the global stability of robotic system are proven. The proposed algorithm is easy to implement and the robotic system is robust to parameter uncertainty and payload variation. Simulation results show the effectiveness of the scheme
TENCON '93. Proceedings. Computer, Communication, Control and Power Engineering.1993 IEEE Region 10 Conference on; 11/1993
-
[show abstract]
[hide abstract]
ABSTRACT: This paper presents the learning algorithm of a neural network
being applied to identification of affine nonlinear systems, and
proposes a neural-network-based model reference adaptive control
approach. The theorems on exponential stability of the system are
proven. Simulation results show that this method is feasible
TENCON '93. Proceedings. Computer, Communication, Control and Power Engineering.1993 IEEE Region 10 Conference on; 11/1993
-
Aerospace Control Systems, 1993. Proceedings. The First IEEE Regional Conference on; 06/1993
-
[show abstract]
[hide abstract]
ABSTRACT: An implicit adaptive inverse dynamics control scheme for robot
manipulators is presented. Instead of estimating manipulator parameters,
the feedback gain is directly updated according to the bounds of
uncertainties of the robotic system. Two theorems are proven, and the
resulting algorithm can tolerate the variation of physical parameters to
some extent. The controller parameters have a certain relation to the
desired position and velocity accuracy, such that the choice for them is
easy. Simulation results verify the effectiveness of the approach
Robotics and Automation, 1993. Proceedings., 1993 IEEE International Conference on; 06/1993
-
[show abstract]
[hide abstract]
ABSTRACT: A sliding-mode control algorithm combined with an adaptive scheme,
which is used to estimate the unknown parameter bounds, is developed for
the trajectory control of robot manipulators. The major contribution of
this methodology lies in the use of a special matrix, called the
regressor, which makes it possible to isolate the unknown parameters
from the robotic dynamics. Based on the upper bounds of those unknown
parameters, which are estimated by a simple adaptive law, the proposed
VSS (variable-structure-system) controller guarantees the stability of
the closed-loop system. The robustness analysis shows that in the
presence of the uncertainties, which are assumed to be unbounded and
rapidly varying, the closed-loop system can still be stabilized.
Chattering is reduced by using the boundary layer technique. Simulation
results show the validity of the proposed algorithm
IEEE Transactions on Robotics and Automation 05/1993;
-
[show abstract]
[hide abstract]
ABSTRACT: A regressor-based variable-structure control scheme has been
developed for the trajectory control of robot manipulators in the
presence of disturbances, parameter variations, and unmodeled dynamics.
The method is based on the regressor structure given by J.J.E. Slotine
and W. Li, without parameter adaptation. This avoids the requirement of
persistency of excitation, and the convergence of the overall transient
exponential. The method is robust against a class of state-dependent
uncertainties, which may result, for example, from unmodeled dynamics.
The problem of chattering is solved by the smoothing control law. It is
with respect to a set around the origin, which can be made arbitrarily
small. To illustrate the feasibility of this controller, it was
implemented using a Motorola M68000 microprocessor on a two-link
revolute joint manipulator subjected to a variable payload. Experimental
results confirm the validity of accurate tracking capability and the
robust performance
IEEE Transactions on Industrial Electronics 03/1993; · 5.16 Impact Factor
