Page 800 - Mechanical Engineers' Handbook (Volume 2)

Mechanical Engineers’ Handbook: Instrumentation, Systems, Controls, and MEMS, Volume 2, Third Edition.

Edited by Myer Kutz

Copyright  2006 by John Wiley & Sons, Inc.
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 7 NN OBSERVERS FOR OUTPUT
FEEDBACK CONTROL 806
2 BACKGROUND 793
2.1 Neural Networks 793 8 REINFORCEMENT LEARNING
2.2 NN Control Topologies 794 CONTROL USING NNs 807
8.1 NN Reinforcement Learning
3 FEEDBACK LINEARIZATION Controller 808
DESIGN OF NN TRACKING 8.2 Adaptive Reinforcement
CONTROLLERS 795 Learning Using Fuzzy Logic
3.1 Multilayer NN Controller 796 Critic 809
3.2 Single-Layer NN Controller 798
3.3 Feedback Linearization of 9 OPTIMAL CONTROL USING
Nonlinear Systems Using NNs 798 NNs 810
3.4 Partitioned NNs and Input 9.1 NN H 2 Control Using the
Preprocessing 799 Hamilton–Jacobi–Bellman
Equation 811
4 NN CONTROL FOR 9.2 NN H Control Using the
DISCRETE-TIME SYSTEMS 800 Hamilton–Jacobi–Isaacs
Equation 813
5 MULTILOOP NN FEEDBACK
CONTROL STRUCTURES 800 10 APPROXIMATE DYNAMIC
5.1 Backstepping Neurocontroller PROGRAMMING AND
for Electrically Driven Robot 801 ADAPTIVE CRITICS 815
5.2 Compensation of Flexible
Modes and High-Frequency 11 HISTORICAL DEVELOPMENT,
Dynamics Using NNs 802 REFERENCED WORK, AND
5.3 Force Control with Neural Nets 803 FURTHER STUDY 817
11.1 NN for Feedback Control 817
6 FEEDFORWARD CONTROL 11.2 Approximate Dynamic
STRUCTURES FOR ACTUATOR Programming 819
COMPENSATION 804
6.1 Feedforward Neurocontroller REFERENCES 821
for Systems with Unknown
Deadzone 804 BIBLIOGRAPHY 825
6.2 Dynamic Inversion
Neurocontroller for Systems
with Backlash 805

791