Muutke küpsiste eelistusi

High-level Feedback Control With Neural Networks [Kõva köide]

(Univ Of Texas At Arlington, Usa), (.)
Teised raamatud teemal:
High-level Feedback Control With Neural NetworksSuurem pilt
Teised raamatud teemal:
Püsilink: https://www.kriso.ee/db/9789810233761.html
Complex industrial or robotic systems with uncertainty and disturbances are difficult to control. As system uncertainty or performance requirements increase, it becomes necessary to augment traditional feedback controllers with additional feedback loops that effectively add intelligence to the system. Some theories of artificial intelligence (AI) are now showing how complex machine systems should mimic human cognitive and biological processes to improve their capabilities for dealing with uncertainty.This book bridges the gap between feedback control and AI. It provides design techniques for high-level neural-network feedback-control topologies that contain servo-level feedback-control loops as well as AI decision and training at the higher levels. Several advanced feedback topologies containing neural networks are presented, including dynamic output feedback, reinforcement learning and optimal design, as well as a fuzzy-logic reinforcement controller. The control topologies are intuitive, yet are derived using sound mathematical principles where proofs of stability are given so that closed-loop performance can be relied upon in using these control systems. Computer-simulation examples are given to illustrate the performance.
Preface ix
CHAPTER 1 INTRODUCTION
1(5)
1.1. Motivation
1(2)
1.2. Research Objectives and Organization of Book
3(3)
CHAPTER 2 BACKGROUND
6(28)
2.1. Vector and Matrix Operations
6(1)
2.2. Practical Stability of Non-linear Systems
7(1)
2.3. Neural Network Model
8(12)
2.3.1. Processing Element
9(2)
2.3.2. Multi-layer Neural Network
11(6)
2.3.3. Dynamic Recurrent Neural Network
17(3)
2.4. Fuzzy System and Fuzzy Basis Function
20(7)
2.4.1. Formulas of Fuzzy System
21(2)
2.4.2. Fuzzy Basis Function
23(2)
2.4.3. Approximation Properties of Fuzzy System
25(2)
2.5. Learning Paradigms
27(7)
2.5.1. General Learning
27(1)
2.5.2. Specialized Learning
28(1)
2.5.3. Feedback Error Learning
29(1)
2.5.4. Reinforcement Learning
30(4)
CHAPTER 3 MULTIPLE MANIPULATORS CONTROL USING NEURAL NETWORKS
34(21)
3.1. Introduction
34(2)
3.2. Multiple Manipulators Models and Properties
36(4)
3.3. Neural Network Coordinated Controller Design
40(10)
3.3.1. Bounding Assumptions and Facts
40(3)
3.3.2. Controller Structure and Error Dynamics
43(1)
3.3.3. Stability Analysis
44(6)
3.4. Simulation Results
50(4)
3.5. Discussion
54(1)
CHAPTER 4 NEURAL NETWORK OUTPUT FEEDBACK CONTROL OF ROBOT MANIPULATORS
55(21)
4.1. Introduction
55(2)
4.2. Robot Dynamics and Properties
57(1)
4.3. Dynamic Neural Network Observer Design
58(5)
4.3.1. Observer Structure and Error Dynamics
58(2)
4.3.2. Stability Analysis
60(3)
4.4. Neural Network Output Feedback Controller Design
63(6)
4.4.1. Controller Structure and Error Dynamics
64(2)
4.4.2. Stability Analysis
66(3)
4.5. Simulation Results
69(6)
4.6. Discussion
75(1)
CHAPTER 5 NONLINEAR OBSERVER USING DYNAMIC RECURRENT NEURAL NETWORKS
76(20)
5.1. Introduction
76(3)
5.2. Non-linear Plant and Observer
79(3)
5.3. Dynamic Neural Network Observer Design
82(9)
5.3.1. Observer Structure and Error Dynamics
82(3)
5.3.2. Stability Analysis: SPR Lyapunov Approach
85(6)
5.4. Simulation Results
91(4)
5.5. Discussion
95(1)
CHAPTER 6 DIRECT REINFORCEMENT LEARNING CONTROL OF NONLINEAR SYSTEMS
96(19)
6.1. Introduction
96(3)
6.2. Reinforcement Neural Controller Design
99(10)
6.2.1. Controller Architecture
99(3)
6.2.2. Stability Analysis: Reinforcement Algorithm
102(7)
6.3. Simulation Results
109(5)
6.4. Discussion
114(1)
CHAPTER 7 DIRECT REINFORCEMENT FUZZY CONTROL OF NONLINEAR SYSTEMS
115(20)
7.1. Introduction
115(3)
7.2. Reinforcement Adaptive Fuzzy Controller Design
118(11)
7.2.1. Controller Architecture
119(1)
7.2.2. Stability Analysis: Reinforcement algorithm
120(9)
7.3. Simulation Results
129(4)
7.4. Discussion
133(2)
CHAPTER 8 NEURAL FRICTION COMPENSATION FOR HIGH PERFORMANCE
135(15)
8.1. Introduction
135(2)
8.2. 1-DOF System and Friction Models
137(2)
8.3. Reinforcement Adaptive Learning Controller Design
139(6)
8.4. Simulation Results
145(4)
8.5. Discussion
149(1)
CHAPTER 9 INTELLIGENT OPTIMAL CONTROL OF ROBOT MANIPULATORS
150(21)
9.1. Introduction
150(2)
9.2. Robot Arm Dynamics and Properties
152(1)
9.3. Optimal Computed Torque Controller Design
153(5)
9.3.1. Hamilton-Jacobi-Bellman Optimization
153(4)
9.3.2. Stability Analysis
157(1)
9.4. Neural Optimal Controller Design
158(6)
9.5. Simulation Results
164(6)
9.6. Discussion
170(1)
CHAPTER 10 CONCLUSION AND FUTURE RESEARCH
171(3)
10.1. General Conclusion
171(1)
10.2. Future Research
172(2)
APPENDICES 174(26)
APPENDIX A. OPTIMAL CONTROL LAW AND CRITIC GAIN DERIVATION 174(4)
APPENDIX B. MULTI-LAYER NEURAL NETWORK WEIGHT INITIALIZATION 178(12)
APPENDIX C. CODE FOR SIMULATION OF INTELLIGENT CONTROLLERS 190(10)
BIBLIOGRAPHY 200(13)
INDEX 213