Fault Diagnosis

Models, Artificial Intelligence, Applications

By: Jszef Korbicz (Editor), Jan M. Koscielny (Editor), Zdzislaw Kowalczuk (Editor)

Write A Review

Paperback | 1 December 2003

At a Glance

Paperback
954 Pages

Dimensions(cm)
23.5 x 16.51 x 3.81

Paperback

$489.75

or 4 interest-free payments of $122.44 with

Ships in 5 to 7 business days

All real systems in nature - physical, biological and engineering ones - can malfunction and fail due to faults in their components. Logically, the chances for malfunctions increase with the systems' complexity. The complexity of engineering systems is permanently growing due to their growing size and the degree of automation, and accordingly increasing is the danger of fail- ing and aggravating their impact for man and the environment. Therefore, in the design and operation of engineering systems, increased attention has to be paid to reliability, safety and fault tolerance. But it is obvious that, compared to the high standard of perfection that nature has achieved with its self-healing and self-repairing capabilities in complex biological organisms, fault management in engineering systems is far behind the standards of their technological achievements; it is still in its infancy, and tremendous work is left to be done. In technical control systems, defects may happen in sensors, actuators, components of the controlled object - the plant, or in the hardware or soft- ware of the control framework. Such defects in the components may develop into a failure of the whole system. This effect can easily be amplified by the closed loop, but the closed loop may also hide an incipient fault from be- ing observed until a situation has occurred in which the failing of the whole system has become unavoidable.

Industry Reviews

From the reviews of the first edition: "This is an extremely full treatment of its topic, with a total of 23 chapters by different groups of authors ! . 'The book on hand is one of the few comprehensive works on the market covering the fundamentals of model-based fault diagnosis ! '. This is an impressively comprehensive and well-prepared work. Each chapter begins with an introduction and ends with a summary, and is followed by an extensive list of references." (Alex M. Andrew, Kybernetes, Vol. 34 (5), 2005) "This book presents descriptions of modern diagnosis methods which are based on control engineering. ! the goal of the book is to present in a coherent way various research methods ! . The book contains most of the modern control methods which are used in fault diagnosis and wide bibliographical information. The book is a good introduction to fault diagnosis and may be very useful for students, post graduate students, engineers and scientists who deal with industrial control systems to guarantee their safety." (Yuri N. Sankin, Zentralblatt MATH, Vol. 1074, 2005)

Shipping

	Standard Shipping	Express Shipping
Metro postcodes:	$9.99	$14.95
Regional postcodes:	$9.99	$14.95
Rural postcodes:	$9.99	$14.95

Orders over $89.00 qualify for free shipping.

How to return your order

At Booktopia, we offer hassle-free returns in accordance with our returns policy. If you wish to return an item, please get in touch with Booktopia Customer Care.

Additional postage charges may be applicable.

Defective items

If there is a problem with any of the items received for your order then the Booktopia Customer Care team is ready to assist you.

For more info please visit our Help Centre.

Methodology	p. 1
Introduction	p. 3
Diagnostics of process and its fundamental tasks	p. 3
Main concepts	p. 6
Aims of process diagnostics	p. 11
General description of the diagnosed object	p. 13
Basic concepts of process diagnostics	p. 19
Summary	p. 25
References	p. 26
Moldels in the diagnostics of processes	p. 29
Introduction	p. 29
Relations in diagnostics	p. 30
Moldels applied to fault detection	p. 31
Physical equations	p. 32
State equations of linear systems	p. 33
State observers	p. 34
Transfer functions of linear systems	p. 35
Neural models	p. 37
Fuzzy modles	p. 40
Models applied to fault isolation and system state recognition	p. 44
Models mapping the space of binary diagnostic signals into the space of faults or system states	p. 46
Binary diagnostic matrix	p. 46
Diagnostic trees and graphs	p. 48
Rules and logic functions	p. 49
Models mapping the space of multi-value diagnostic signals into the space of faults or systtem states	p. 50
Information system	p. 50
Other models	p. 53
Modles mapping the space of continuous diagnostic signals into the space of faults or system states	p. 54
Pattern pictures	p. 54
Neural networks	p. 55
Fuzzy neural networks	p. 55
Summary	p. 55
References	p. 56
Process diagnostics methodology	p. 59
Introduction	p. 59
Fault detection	p. 59
Fault detection using system models	p. 60
Generation of residuals on the grounds of physical equations	p. 61
Generation of residuals on the grounds of system transmittance	p. 62
Generation of residuals using state equations	p. 64
Generation of residuals on the grounds of state observers	p. 66
Generation of residuals using on-line identification	p. 67
Residual generation with neural and fuzzy models	p. 68
Algorithms for making a decision on fault detection using residual value evaluation	p. 70
Fault detection using tests of simple relationships existing between signals	p. 72
Application of hardware redundancy	p. 72
Application of feedback signals	p. 72
Test of statistical relationships existing between process variables	p. 72
Testing the relations existing between process variables	p. 73
Methods of signal analysis and the testing of limits	p. 74
Analysis of statistic signal parameters	p. 74
Spectral analysis	p. 75
Methods of limit checking	p. 76
Fault isolation	p. 79
Diagnosing based on the binary diagnostic matrix	p. 80
Rules of parallel diagnostic inference on the assumption about single faults	p. 80
Rules of series diagnostic inference on the assumption about single faults	p. 81
Inference with the inconsistency of symptoms	p. 82
System states with multiple faults	p. 83
Parallel inference on the assumption about multiple faults	p. 85
Series inference on the assumption about multiple faults	p. 87
Diagnosing based on the information system	p. 87
Parallel diagnostic inference based on the information system	p. 88
Series diagnostic inference based on the information system	p. 88
Methods of pattern recognition	p. 89
Recognition of directions in the space of residuals	p. 91
Other methods	p. 95
Fault distinguishability	p. 95
Fault distinguishability based on the binary diagnostic matrix	p. 96
Distinguishability of system states based on the binary table of states	p. 97
Fault distinguishability based on the information system	p. 98
Fault distinguishability based on pattern recognition in the space of diagnostic signals	p. 100
Fault distinguishability improvement by taking the dynamics of symptoms into account	p. 101
Methods of the structural design of the set of detection algorithms	p. 101
Generation of secondary residuals based on physical equations	p. 102
Choice of a structural set of residuals generated on the basis of parity equations	p. 103
Banks of observers	p. 105
Design of a structured set of detection algorithms based on partial models	p. 106
Minimising the set of detection algorithms	p. 107
Fault identification	p. 108
Residual equations	p. 109
Residuals without the knowledge of the effect of faults	p. 1ll
Monitoring the system state	p. 112
Summary	p. 113
References	p. 114
Methods of signal analysis	p. 119
Introduction	p. 119
Signal classification	p. 121
Initial pre-processing of signals	p. 123
Analogue-to-digital conversion of signals	p. 124
Filtering	p. 124
Smoothing	p. 129
Averaging	p. 131
Principal component analysis	p. 132
Non-parametric methods of signal feature estimation	p. 134
Scalar feature estimation	p. 134
Spectral analysis	p. 135
Higher order spectral analysis	p. 139
Analysis with the use of the wavelet transform	p. 141
Analysis with the use of the Wigner-Ville transform	p. 145
Parametric methods of signal estimation	p. 145
Signal features estimated with respect to object properties	p. 147
Summary	p. 151
References	p. 151
Control theory methods in designing diagnostic systems	p. 155
Introduction	p. 155
Transfer function approach	p. 157
Residue generation	p. 157
Properties of the system matrix	p. 163
Non-homogeneous residual reaction models	p. 167
Homogeneous residual reaction models	p. 171
Parity space approach	p. 173
Deterministic assignment of state estimation	p. 177
Full-order observer	p. 177
Minimal-order observer	p. 180
Observer matrix determination by pole placement	p. 186
Detection observers of the Luenberger type	p. 191
Linear Kalman filters	p. 198
Models of estimated processes	p. 199
Linear Kalman filtering founded on innovations	p. 200
Summary	p. 207
Appendix	p. 208
References	p. 213
Optimal detection observers based on eigenstructure assignment	p. 219
Introduction	p. 219
System modelling	p. 221
Preliminary synthesis of residuals	p. 222
Conditions for disturbance decoupling	p. 223
Necessary condition for decoupling	p. 224
Sufficient conditions for decoupling	p. 226
Parameterisation of attainable eigensubspaces	p. 227
Separate spectra of the observer and the object	p. 229
Mutuality in the spectra of the observer and the object	p. 229
Partial observer gain	p. 231
Synthesis of a numerically robust state observer	p. 232
Separate spectra of the observer and the object	p. 234
Mutuality in the spectra of the observer and the object	p. 235
Synthesis of a numerically robust decoupled state observer	p. 236
Numerically robust attainable decoupling	p. 237
Complete observer gain	p. 238
Completely decoupled observers	p. 238
Dead-beat design of residue generators	p. 239
Residue generation using parity equations	p. 242
Numerical example	p. 242
Decoupled dead-beat residue generator	p. 243
Properties of dead-bead observers	p. 244
Properties of non-dead-bead observers	p. 249
Robustness of dead-beat observers	p. 251
Summary	p. 251
Appendices	p. 253
Observability of dynamic systems	p. 253
Useful geometric relationships	p. 254
References	p. 257
Robust H_∞-optimal synthesis of FDI systems	p. 261
Introduction	p. 261
FDI design task as optimal filtering in H_∞	p. 263
Optimal filtering based on the basic modelling of generalised processes	p. 264
Solution using the basic model	p. 267
Optimal filtering based on the dual modelling of generalised plants	p. 272
Solution using the dual model	p. 274
FDI filtering with the instrumental reference signal	p. 280
Synthesis of primary and secondary residual vectors	p. 283
Numerical example	p. 286
Summary	p. 290
Appendices	p. 291
Discrete-time models	p. 291
Norms and spaces	p. 292
Factorisation	p. 293
Discrete Riccati equation	p. 294
References	p. 295
Artificial Intelligence	p. 299
Evolutionary methods in designing diagnostic systems	p. 301
Introduction	p. 301
Evolutionary algorithms	p. 302
Basic concepts of evolutionary search	p. 303
Some evolutionary algorithms	p. 305
Optimization tasks in designing FDI systems	p. 308
Symptom extraction	p. 309
Choice of the gain matrix for the robust non-linear observer via genetic programming	p. 309
Designing the robust residual generator using multi-objective optimization and evolutionary algorithms	p. 312
Evolutionary algorithms in the design of neural models	p. 314
Symptom evaluation	p. 323
Genetic clustering	p. 324
Evolutionary algorithms in designing the rule base	p. 325
Genetic adaptation of fuzzy systems	p. 327
Summary	p. 329
References	p. 329
Artificial neural networks in fault diagnosis	p. 333
Introduction	p. 333
Structure of a neural fault diagnosis system	p. 334
Neural models in modelling	p. 337
Multi-layer perceptron	p. 337
Recurrent networks	p. 339
Neural networks of the GMDH type	p. 347
Fault classification using neural networks	p. 352
Multi-layer perceptron	p. 352
Kohonen network	p. 352
Radial basic networks	p. 354
Multiple network structure	p. 356
Selected applications	p. 357
Two-tank laboratory system	p. 357
Instrumentation fault detection	p. 365
Actuator fault detection and isolation	p. 369
Summary	p. 375
References	p. 376
Parametric and neural network Wiener and Hammerstein models in fault detection and isolation	p. 381
Introduction	p. 381
Wiener and Hammerstein models	p. 382
Identification of Wiener and Hammerstein systems	p. 384
Parametric and neural network Wiener and Hammerstein models	p. 386
Parametric models	p. 387
Neural network models	p. 388
Fault detection. Estimating parameter changes	p. 389
Definitions of the identification error	p. 390
Hammerstein system. Parameter estimation of the residual equation	p. 393
Wiener system. Parameter estimation of the residual equation	p. 396
Five-stage sugar evaporator. Identification of the nominal model of steam pressure dynamics	p. 402
Theoretical model	p. 402
Experimental models	p. 403
Estimation results	p. 404
Summary	p. 407
References	p. 407
Application of fuzzy logic to diagnostics	p. 411
Introduction	p. 411
Fault detection	p. 412
Wang and Mendel's fuzzy models	p. 413
Construction of fuzzy models using Wang and Mendel's method	p. 413
Modification of Wang and Mendel's method	p. 415
Calculation of a residual on the basis of the fuzzy model	p. 416
Fuzzy neural networks	p. 417
Fuzzy neural networks with outputs in the form of singletons	p. 418
TSK-type fuzzy neural networks	p. 420
Fuzzy neural networks with outputs in the form of fuzzy sets	p. 422
Example of fault detection	p. 423
Fault isolation with the use of fuzzy logic	p. 428
Fuzzy evaluation of residual values	p. 429
Rules of inference	p. 431
Fuzzy diagnostic inference	p. 433
Example of fault isolation	p. 437
Uncertainty of the diagnostic signals-faults relation	p. 441
Fault isolation with the use of the fuzzy neural network	p. 442
Realisation of fuzzy residual evaluation by the fuzzy neural network	p. 444
Fault isolation in the fuzzy neural network	p. 445
Example of fuzzy neural network application to fault isolation	p. 449
Summary	p. 450
References	p. 454
Observers and genetic programming in the identification and fault diagnosis of non-linear dynamic systems	p. 457
Introduction	p. 457
Identification of non-linear dynamic systems	p. 460
Data acquisition and preparation	p. 460
Table of Contents provided by Publisher. All Rights Reserved.

Fault Diagnosis

Models, Artificial Intelligence, Applications

At a Glance

Paperback

Industry Reviews

Shipping

How to return your order

Defective items

You Can Find This Book In

More in Automatic Control Engineering

Control, Robotics and Sensors

Design, Control and Applications

Sixth Congress on Intelligent Systems

CIS 2025, Volume 6

Trends in Advanced Unmanned Aerial Systems

Selected Contributions of ICAUAS 2025

Novel Sensing for Robotics and Drones

Smart Sensors, Measurement and Instrumentation

Modeling, Planning and Control of Robotics

Fundamentals of Robotics

Construction in the Age of Automation and Robotics

Blood in the Machine

The Origins of the Rebellion Against Big Tech

Make: Electronics

Learning by Discovery: A Hands-On Primer for the New Electronics Enthusiast

Scary Smart

The Future of Artificial Intelligence and How You Can Save Our World

The Lego Technic Idea Book

Simple Machines

Electric and Hybrid Vehicles

Managing Innovation 6ed

Integrating Technological, Market and Organizational Change

Encyclopedia of Electronic Components

Resistors, Capacitors, Inductors, Semiconductors, Electromagnetism

Chemical Industries

Chemical Industries

Learning the Art of Electronics

A Hands-On Lab Course

We Are Not Machines

The Fight for the Future of Work

Encyclopedia of Electronic Components V3

Sensors for Location, Presence, Proximity, Orientation, Oscillation, Force, Load, Human Input, Liquid and Gas Properties, Light, Heat, Sound, and Electricity

Arduino Projects For Dummies

For Dummies (Computer/Tech)

Missions to Mars

A New Era of Rover and Spacecraft Discovery on the Red Planet

Scary Smart

The Future of Artificial Intelligence and How You Can Save Our World

Agentic AI For Dummies

For Dummies (Computer/Tech)

Encyclopedia of Electronic Components Volume 2

Leds, Lcds, Audio, Thyristors, Digital Logic, and Amplification

Applied Machine Learning on Sensing Technologies

Ubiquitous Computing, Healthcare and Well-being

This product is categorised by