Suchen und Finden
Neural Network Systems Techniques and Applications - Advances in Theory and Applications
von: Cornelius T. Leondes (Ed.)
Elsevier Trade Monographs, 1997
ISBN: 9780080553900 , 438 Seiten
Format: PDF, ePUB, OL
Kopierschutz: DRM
Preis: 118,00 EUR
Mehr zum Inhalt
Neural Network Systems Techniques and Applications - Advances in Theory and Applications
Front Cover
1
Control and Dynamic Systems
4
Copyright Page
5
Contents
6
Contributors
14
Preface
16
Chapter 1. Orthogonal Functions for Systems Identification and Control
22
I. Introduction
22
II. Neural Networks with Orthogonal Activation Functions
23
III. Frequency Domain Applications Using Fourier Series Neural Networks
46
IV. Time Domain Applications for System Identification and Control
68
V. Summary
92
References
93
Chapter 2. Multilayer Recurrent Neural Networks for Synthesizing and Tuning Linear Control Systems via Pole Assignment
96
I. Introduction
97
II. Background Information
98
III. Problem Formulation
100
IV. Neural Networks for Controller Synthesis
106
V. Neural Networks for Observer Synthesis
114
VI. Illustrative Examples
119
VII. Concluding Remarks
144
References
146
Chapter 3. Direct and Indirect Techniques to Control Unknown Nonlinear Dynamical Systems Using Dynamical Neural Networks
148
I. Introduction
148
II. Problem Statement and the Dynamic Neural Network Model
151
III. Indirect Control
153
IV. Direct Control
160
V. Conclusions
175
References
175
Chapter 4. A Receding Horizon Optimal Tracking Neurocontroller for Nonlinear Dynamic Systems
178
I. Introduction
179
II. Receding Horizon Optimal Tracking Control Problem Formulation
180
III. Design of Neurocontrollers
184
IV. Case Studies
197
V. Conclusions
208
References
209
Chapter 5. On-Line Approximators for Nonlinear System Identification: A Unified Approach
212
I. Introduction
212
II. Network Approximators
214
III. Learning Algorithm
221
IV Continuous-Time Identification
231
V Conclusions
249
References
250
Chapter 6. The Determination of Multivariable Nonlinear Models for Dynamic Systems
252
I. Introduction
252
II. The Nonlinear System Representation
254
III. The Conventional NARMAX Methodology
256
IV Neural Network Models
267
V Nonlinear-in-the-Parameters Approach
275
VI Linear-in-the-Parameters Approach
280
VII. Identifiability and Local Model Fitting
292
VIII. Conclusions
294
References
296
Chapter 7. High-Order Neural Network Systems in the Identification of Dynamical Systems
300
I. Introduction
300
II. RHONNs and g-RHONNs
302
III. Approximation and Stability Properties of RHONNs and g-RHONNs
305
IV. Convergent Learning Laws
310
V. The Boltzmann g-RHONN
315
VI. Other Applications
319
VII. Conclusions
325
References
325
Chapter 8. Neurocontrols for Systems with Unknown Dynamics
328
I. Introduction
328
II. The Test Cases
330
III. The Design Procedure
334
IV. More Details on the Controller Design
339
V. More on Performance
341
VI. Closure
352
References
352
Chapter 9. On-Line Learning Neural Networks for Aircraft Autopilot and Command Augmentation Systems
354
I. Introduction
354
II. The Neural Network Algorithms
357
III. Aircraft Model
362
IV. Neural Network Autopilots
363
V. Neural Network Command Augmentation Systems
374
VI. Conclusions and Recommendations for Additional Research
400
References
401
Chapter 10. Nonlinear System Modeling
404
I. Introduction
404
II. RBF Neural Network-Based Nonlinear Modeling
406
III. On-Line RBF Structural Adaptive Modeling
415
IV. Multiscale RBF Modeling Technique
420
V. Neural State–Space–Based Modeling Techniques
427
VI. Dynamic Back-Propagation
430
VII. Properties and Relevant Issues in State–Space Neural Modeling
433
VIII. Illustrative Examples
440
References
452
Index
456
Alle Preise verstehen sich inklusive der gesetzlichen MwSt.