Differential neural networks for robust nonlinear control : identification, state estimation and trajectory tracking /
This book deals with continuous time dynamic neural networks theory applied to the solution of basic problems in robust control theory, including identification, state space estimation (based on neuro-observers) and trajectory tracking. The plants to be identified and controlled are assumed to be a...
Saved in:
Main Authors: | |
---|---|
Corporate Authors: | |
Group Author: | ; |
Published: |
World Scientific Pub. Co.,
|
Publisher Address: | Singapore : |
Publication Dates: | 2001. |
Literature type: | eBook |
Language: | English |
Subjects: | |
Online Access: |
http://www.worldscientific.com/worldscibooks/10.1142/4703#t=toc |
Summary: |
This book deals with continuous time dynamic neural networks theory applied to the solution of basic problems in robust control theory, including identification, state space estimation (based on neuro-observers) and trajectory tracking. The plants to be identified and controlled are assumed to be a priori unknown but belonging to a given class containing internal unmodelled dynamics and external perturbations as well. The error stability analysis and the corresponding error bounds for different problems are presented. The effectiveness of the suggested approach is illustrated by its application to various controlled physical systems (robotic, chaotic, chemical, etc.). |
Carrier Form: | 1 online resource (xxxi,422pages) : illustrations |
Bibliography: | Includes bibliographical references and index. |
ISBN: | 9789812811295 |
CLC: | TP273 |
Contents: | 1. Neural networks structures. 1.1. Introduction. 1.2. Biological .eural networks. 1.3. Neuron model. 1.4. Neural networks structures. 1.5. Neural networks in control. 1.6. Conclusions. 1.7. References -- 2. Nonlinear system identification: Differential learning. 2.1. Introduction. 2.2. Identification error stability analysis for simplest differential neural networks without hidden layers. 2.3. Multilayer differential neural networks for nonlinear system on-line identification. 2.4. Illustrating examples. 2.5. Conclusion. 2.6. References -- 3. Sliding mode identification: Algebraic learning. 3.1. Introduction. 3.2. Sliding mode technique: Basic principles. 3.3. Sliding model learning. 3.4. Simulations. 3.5. Conclusion. 3.6. References -- 4. Neural state estimation. 4.1. Nonlinear systems and nonlinear observers. 4.2. Robust nonlinear observer. 4.3. The neuro-observer for unknown nonlinear systems. 4.4. Application. 4.5. Concluding remarks. 4.6. References -- 5. Passivation via neuro control. 5.1 Introduction. 5.2. Partially known systems and applied DNN. 5.3 Passivation of partially known nonlinear system via DNN. 5.4. Numerical experiments. 5.5. Conclusions. 5.6. References -- 6. Neuro trajectory tracking. 6.1. Tracking using dynamic neural networks. 6.2. Trajectory tracking based neuro observer. 6.3. Simulation results. 6.4. Conclusions. 6.5. References -- 7. Neural control for chaos. 7.1. Introduction. 7.2. Lorenz system. 7.3. Duffing equation. 7.4. Chua's circuit. 7.5. Conclusion. 7.6. References -- 8. Neuro control for robot manipulators. 8.1. Introduction. 8.2. Manipulator dynamics. 8.3. Robot joint velocity observer and RBF compensator. 8.4. PD control with velocity estimation and neuro compensator. 8.5. Simulation results. 8.6. Conclusion. 8.7. References -- 9. Identification of chemical processes. 9.1. Nomenclature. 9.2. Introduction. 9.3. Process modeling and problem formulation. 9.4. Observability condition. 9.5. Neuro observer. 9.6. Estimation of the reaction rate constants. 9.7. Simulation results. 9.8. Conclusions. 9.9. References -- 10. Neuro-control for distillation column. 10.1. Introduction. 10.2. Modeling of a multicomponent distillation column. 10.3. A local optimal controller for distillation column. 10.4. Application to multicomponent nonideal distillation column. 10.5. Conclusion. 10.6. References -- 11. General conclusions and future work. |