Soft computing in systems and control technology / editor, S.G. Tzafestas.

Format:

Book

Contributor:

Tzafestas, S. G., 1939-

Series:

World Scientific Series in Robotics and Intelligent Systems

World Scientific series in robotics and intelligent systems ; vol. 18

Language:

English

Subjects (All):

Soft computing.

Fuzzy logic.

Physical Description:

1 online resource (510 p.)

Place of Publication:

Singapore ; River Edge, N.J. : World Scientific, c1999.

Language Note:

English

Summary:

Soft computing is a branch of computing which, unlike hard computing, can deal with uncertain, imprecise and inexact data. The three constituents of soft computing are fuzzy-logic-based computing, neurocomputing, and genetic algorithms. Fuzzy logic contributes the capability of approximate reasoning, neurocomputing offers function approximation and learning capabilities, and genetic algorithms provide a methodology for systematic random search and optimization. These three capabilities are combined in a complementary and synergetic fashion.This book presents a cohesive set of contributions dea

Contents:

PREFACE; CONTRIBUTORS; CONTENTS; EDITORIAL; PART I NEURAL NETWORKS IN SYSTEM IDENTIFICATION AND CONTROL; Chapter 1Supervised Learning in Multilayer Perceptrons:The Back-Propagation Algorithm; 1 Introduction; 2 The Supervised Learning Problem; 2.1 The Main Learning Problems; 3 Multilayer Perceptrons (MLPs); 3.1 Approximating Capabilities of Multilayer Perceptrons; 4 Supervised Learning in Multilayer Perceptrons; 4.1 Generalization; 5 The Back-Propagation Algorithm; 6 References; Chapter 2 Identification of Two-Dimensional State Space Discrete Systems Using Neural Networks; 1 Introduction

2. Problem Approach2.1 Motivation; 2.2 NNModel Representation; 3 A Pattern Mode Training Algorithm; 3.1 Training Objective; 3.2 Weight Adjustment; 3.3 Gradient Calculation; 3.4 Algorithm Summary; 4 Implementation Issues; 4.1 Identifying a 2-D Separable in Denominator Digital Filter; 4.2 Order Selection and Order Reduction; 4.3 Pattern verse Batch Mode Training; 5 Simulation Results; 5.1 Example 1: 2-D Gaussian Filter Design; 5.2 Example 2:1-Q Gaussian SDDF Filter Design; 5.3 Example 3: A (2, 2) Order System; 6 Concluding Remarks; References; Chapter 3 Neural Networks for Control

1 Introduction1.1 Neural Network Principles; 1.2 History of Neural Networks; 1.3 Properties of Neural Networks; 1.4 Applications of Neural Networks; 1.5 Types of Neural Network; 2 Feedforward Networks; 2.1 Multi-Layer Perceptron Networks; 2.2 Radial Basis Function Networks; 2.3 Comparison of MLP and RBF; 3 Recurrent Networks; 3.1 Hopfield Network; 3.2 Continuous Version of the Hopfield Network; 3.3 Real-Time Recurrent Networks; 4 Weightless Networks; Conclusion; References; Chapter 4 Neuro-Based Adaptive Regulator; 1 Introduction; 2 Neuro-Based Adaptive Regulator; 2.1 System Formulation

2.2 Quadratic Optimal Regulator for Linearized System2.3 Derivation of Compensatory Input; 2.4 Neuro-Based Adaptive Regulator; 3 Multi-layer Neural Network and Learning; 4 Computer Simulation of Double Cart-Spring System; 4.1 Control Performance; 4.2 Ability of Learning and Identification; 4.3 Nonlinear Uncertainties; 5 Conclusion; Appendix; References; Chapter 5 Local Model Networks and Self-Tuning Predictive Control; 1 Introduction; 2 Continuous-time LMN; 3 Continuous-time GPC; 4 LMNGPC; 5 Self-tuning LMNGPC; 6 An example; 7 Conclusions; Acknowledgements; References

PART II FUZZY AND NEURO-FUZZY SYSTEMS IN MODELLING, CONTROL AND ROBOT PATH PLANNINGChapter 6 An On-Line Self Constructing Fuzzy Modeling Architecture Based on Neural and Fuzzy Concepts and Techniques; 1. INTRODUCTION; 2. GENERAL ISSUES ON THE PROPOSED ARCHITECTURE; 3. THE BASIC TAKAGI-SUGENO-KANG MODEL; 4. THE FUZZY ART ALGORITHM; 5. ANALYTICAL PRESENTATION OF THE PROPOSED ARCHITECTURE; 5.1 Adaptive parameters; 5.2 Input variable transformation for efficient output calculation; 5.3 Basic parameters and performance indices; 5.4 The core of the algorithm; 5.5 Discussion; 6. MEMBERSHIP FUNCTIONS

6.1 First Membership Function

Notes:

Description based upon print version of record.

Includes bibliographical references and index.

ISBN:

9789812816528

9812816526