This monograph presents a variety of techniques that can be used for designing robust fault diagnosis schemes for non-linear systems. The introductory part of the book is of a tutorial value and can be perceived as a good starting point for the new-comers to this field. Subsequently, advanced robust observer structures are presented. Parameter estimation based techniques are discussed as well. A particular attention is drawn to experimental design for fault diagnosis. The book also presents a number of robust soft computing approaches utilizing evolutionary algorithms and neural networks. All approaches described in this book are illustrated by practical applications.
Author(s): Marcin Witczak
Series: Lecture Notes in Control and Information Sciences
Publisher: Springer
Year: 2007
Language: English
Pages: 198
City: Berlin
Tags: Автоматизация;Теория автоматического управления (ТАУ);
Cover......Page 1
Contents......Page 10
Introduction......Page 13
Introductory Background......Page 16
Content......Page 18
Approaches to Linear Systems......Page 20
Approaches to Non-linear Systems......Page 25
Robustness Issues......Page 31
Concluding Remarks......Page 38
Soft Computing-Based FDI......Page 40
Neural Networks......Page 41
Evolutionary Algorithms......Page 50
Concluding Remarks......Page 54
Extended Unknown Input Observer......Page 56
Extended Unknown Input Observer Revisited......Page 65
Design of Observers and Unknown Input Observers for Lipschitz Systems......Page 73
Concluding Remarks......Page 88
Parameter Estimation-Based FDI......Page 91
Experimental Design......Page 92
Impedance Measurement and Diagnosis......Page 94
Concluding Remarks......Page 106
Evolutionary Algorithms......Page 108
Model Design with Genetic Programming......Page 109
Robustifying the EUIO with Genetic Programming......Page 117
Robustifying the EUIO with the ESSS Algorithm......Page 118
Experimental Result......Page 122
Neural Networks......Page 136
Robust Fault Detection with the Multi-layer Perceptron......Page 137
Robust Fault Detection with GMDH Neural Networks......Page 166
Concluding Remarks......Page 185
Conclusions and Future Research Directions......Page 187
back-matter.pdf......Page 193
