Neural Network Systems Techniques and Applications (eBook)

Advances in Theory and Applications

eBook Download: PDF

1998 | 1. Auflage
438 Seiten
Elsevier Science (Verlag)
978-0-08-055390-0 (ISBN)

Infos

The book emphasizes neural network structures for achieving practical and effective systems, and provides many examples. Practitioners, researchers, and students in industrial, manufacturing, electrical, mechanical,and production engineering will find this volume a unique and comprehensive reference source for diverse application methodologies.
Control and Dynamic Systems covers the important topics of highly effective Orthogonal Activation Function Based Neural Network System Architecture, multi-layer recurrent neural networks for synthesizing and implementing real-time linear control,adaptive control of unknown nonlinear dynamical systems, Optimal Tracking Neural Controller techniques, a consideration of unified approximation theory and applications, techniques for the determination of multi-variable nonlinear model structures for dynamic systems with a detailed treatment of relevant system model input determination, High Order Neural Networks and Recurrent High Order Neural Networks, High Order Moment Neural Array Systems, Online Learning Neural Network controllers, and Radial Bias Function techniques.

Key Features
Coverage includes:
* Orthogonal Activation Function Based Neural Network System Architecture (OAFNN)
* Multilayer recurrent neural networks for synthesizing and implementing real-time linear control
* Adaptive control of unknown nonlinear dynamical systems
* Optimal Tracking Neural Controller techniques
* Consideration of unified approximation theory and applications
* Techniques for determining multivariable nonlinear model structures for dynamic systems,
with a detailed treatment of relevant system model input determination

---

The book emphasizes neural network structures for achieving practical and effective systems, and provides many examples. Practitioners, researchers, and students in industrial, manufacturing, electrical, mechanical,and production engineering will find this volume a unique and comprehensive reference source for diverse application methodologies. Control and Dynamic Systems covers the important topics of highly effective Orthogonal Activation Function Based Neural Network System Architecture, multi-layer recurrent neural networks for synthesizing and implementing real-time linear control,adaptive control of unknown nonlinear dynamical systems, Optimal Tracking Neural Controller techniques, a consideration of unified approximation theory and applications, techniques for the determination of multi-variable nonlinear model structures for dynamic systems with a detailed treatment of relevant system model input determination, High Order Neural Networks and Recurrent High Order Neural Networks, High Order Moment Neural Array Systems, Online Learning Neural Network controllers, and Radial Bias Function techniques. Coverage includes:- Orthogonal Activation Function Based Neural Network System Architecture (OAFNN)- Multilayer recurrent neural networks for synthesizing and implementing real-time linear control- Adaptive control of unknown nonlinear dynamical systems- Optimal Tracking Neural Controller techniques- Consideration of unified approximation theory and applications- Techniques for determining multivariable nonlinear model structures for dynamic systems, with a detailed treatment of relevant system model input determination

Inhalt

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

Produkt-Details

• Erscheint lt. Verlag: 9.2.1998
• Mitarbeit: Herausgeber (Serie): Cornelius T. Leondes
• Sprache: englisch
• Themenwelt: Informatik ► Grafik / Design ► Digitale Bildverarbeitung
• Themenwelt: Mathematik / Informatik ► Informatik ► Netzwerke
• Themenwelt: Mathematik / Informatik ► Informatik ► Programmiersprachen / -werkzeuge
• Themenwelt: Mathematik / Informatik ► Informatik ► Software Entwicklung
• Themenwelt: Informatik ► Theorie / Studium ► Künstliche Intelligenz / Robotik
• Themenwelt: Naturwissenschaften ► Chemie
• Themenwelt: Technik ► Bauwesen
• Themenwelt: Technik ► Elektrotechnik / Energietechnik
• ISBN-10: 0-08-055390-7 / 0080553907
• ISBN-13: 978-0-08-055390-0 / 9780080553900