791
CHAPTER 19
NEURAL NETWORKS IN
FEEDBACK CONTROL SYSTEMS
F. L. Lewis
Automation and Robotics Research Institute
University of Texas at Arlington
Fort Worth, Texas
Shuzhi Sam Ge
Department of Electrical and Computer Engineering
National University of Singapore
Singapore
1
INTRODUCTION
792
2
BACKGROUND
793
2.1 Neural Networks
793
2.2 NN Control Topologies
794
3
FEEDBACK LINEARIZATION
DESIGN OF NN TRACKING
CONTROLLERS
795
3.1 Multilayer NN Controller
796
3.2 Single-Layer NN Controller
798
3.3 Feedback Linearization of
Nonlinear Systems Using NNs
798
3.4 Partitioned NNs and Input
Preprocessing
799
4
NN CONTROL FOR
DISCRETE-TIME SYSTEMS
800
5 MULTILOOP NN FEEDBACK
CONTROL STRUCTURES
800
5.1 Backstepping Neurocontroller
for Electrically Driven Robot
801
5.2 Compensation of Flexible
Modes and High-Frequency
Dynamics Using NNs
802
5.3 Force Control with Neural Nets
803
6
FEEDFORWARD CONTROL
STRUCTURES FOR ACTUATOR
COMPENSATION
804
6.1 Feedforward Neurocontroller
for Systems with Unknown
Deadzone
804
6.2 Dynamic Inversion
Neurocontroller for Systems
with Backlash
805
7
NN OBSERVERS FOR OUTPUT
FEEDBACK CONTROL
806
8
REINFORCEMENT LEARNING
CONTROL USING NNs
807
8.1 NN Reinforcement Learning
Controller
808
8.2 Adaptive Reinforcement
Learning Using Fuzzy Logic
Critic
809
9
OPTIMAL CONTROL USING
NNs
810
9.1 NN H2 Control Using the
Hamilton–Jacobi–Bellman
Equation
811
9.2 NN H Control Using the
Hamilton–Jacobi–Isaacs
Equation
813
10 APPROXIMATE DYNAMIC
PROGRAMMING AND
ADAPTIVE CRITICS
815
11 HISTORICAL DEVELOPMENT,
REFERENCED WORK, AND
FURTHER STUDY
817
11.1 NN for Feedback Control
817
11.2 Approximate Dynamic
Programming
819
REFERENCES
821
BIBLIOGRAPHY
825
Mechanical Engineers’ Handbook: Instrumentation, Systems, Controls, and MEMS, Volume 2, Third Edition.
Edited by Myer Kutz
Copyright
2006 by John Wiley & Sons, Inc.
792 Neural Networks in Feedback Control Systems
1 INTRODUCTION
Dynamical systems are ubiquitous in nature and include naturally occurring systems such as
the cell and more complex biological organisms, the