High-level feedback control with neural networks /
"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...
Saved in:
Main Authors: | |
---|---|
Corporate Authors: | |
Group Author: | |
Published: |
World Scientific Pub. Co.,
|
Publisher Address: | Singapore : |
Publication Dates: | 1998. |
Literature type: | eBook |
Language: | English |
Series: |
World Scientific series in robotics and intelligent systems ; vol. 21 |
Subjects: | |
Online Access: |
http://www.worldscientific.com/worldscibooks/10.1142/3701#t=toc |
Summary: |
"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." |
Carrier Form: | 1 online resource (x,216pages) : illustrations. |
Bibliography: | Includes bibliographical references and index. |
ISBN: | 9789812816542 |
Index Number: | TJ216 |
CLC: | TP271 |
Contents: | ch. 1. Introduction. 1.1. Motivation. 1.2. Research objectives and organization of book -- ch. 2. Background. 2.1. Vector and matrix operations. 2.2. Practical stability of non-linear systems. 2.3. Neural network model. 2.4. Fuzzy system and fuzzy basis function. 2.5. Learning paradigms -- ch. 3. Multiple manipulators control using neural networks. 3.1. Introduction. 3.2. Multiple manipulators models and properties. 3.3. Neural network coordinated controller design. 3.4. Simulation results. 3.5. Discussion -- ch. 4. Neural network output feedback control of robot manipulators. 4.1. Introduction. 4.2. Robot dynamics and properties. 4.3. Dynamic neural network observer design. 4.4. Neural network output feedback controller design. 4.5. Simulation results -- ch. 5. Nonlinear observer using dynamic recurrent neural networks. 5.1. Introduction. 5.2. Non-linear plant and observer. 5.3. Dynamic neural network observer design. 5.4. Simulation results -- ch. 6. Direct reinforcement learning control of nonlinear systems. 6.1. Introduction. 6.2. Reinforcement neural controller design. 6.3. Simulation results -- ch. 7. Direct reinforcement fuzzy control of nonlinear systems. 7.1. Introduction. 7.2. Reinforcement adaptive fuzzy controller design. 7.3. Simulation results -- ch. 8. Neural friction compensation for high performance. 8.1. Introduction. 8.2. 1-DOF system and friction models. 8.3. Reinforcement adaptive learning controller design. 8.4. Simulation results -- ch. 9. Intelligent optimal control of robot manipulators. 9.1. Introduction. 9.2. Robot arm dynamics and properties. 9.3. Optimal computed torque controller design. 9.4. Neural optimal controller design. 9.5. Simulation results -- ch. 10. Conclusion and future research. |