×

Neuro-fuzzy uncertainty de-coupling: a multiple-model paradigm for fault detection and isolation. (English) Zbl 1112.93013

Summary: A neuro-fuzzy and de-coupling fault diagnosis scheme (NFDFDS) is proposed for fault detection and isolation (FDI) of nonlinear dynamic systems. In this approach, powerful approximation and reasoning capabilities of neuro-fuzzy models are combined with the de-coupling capabilities of optimal observers to perform reliable fault detection and isolation. The neuro-fuzzy model presented here is a special form of Takagi-Sugeno (TS) fuzzy model used to represent the system by a fuzzy fusion of local linear sub-models. The necessary condition for the application of this FDI scheme is that this special form of the TS model can represent the nonlinear system, which is true for many practical systems. It is shown that if all the local models are stable and the corresponding local observers converge to the local models it can be expected that the global model is stable and the corresponding global observer will converge to the nonlinear input-output system. An application of FDI for an electro-pneumatic valve actuator in a sugar factory is presented. Key issues of finding a suitable structure for detecting and isolating nine realistic actuator faults are described.

MSC:

93B07 Observability
93C70 Time-scale analysis and singular perturbations in control/observation systems
93E10 Estimation and detection in stochastic control theory
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Chen, IEE Proceedings-D Control Theory and Applications 143 pp 31– (1996)
[2] , . Robust Model Based Fault Diagnosis For Dynamic Systems. Kluwer Academic Publishers: Dordrecht, 1999, ISBN 0-7923-8411-3. · Zbl 0920.93001 · doi:10.1007/978-1-4615-5149-2
[3] , . Neuro-Fuzzy Adaptive Modelling and Control. Prentice-Hall: Englewood Cliffs, NJ, 1995, ISBN 0131344536.
[4] , , . Neuro-Fuzzy and Soft Computing. Prentice-Hall: NJ, 1997, ISBN 0-13-261066-3.
[5] DAMADICS RTN Information Web site. ’http://diag.mchtr.pw.edu.pl/damadics’, Institute of Automatic Control and Robotics, Warsaw University of Technology (last checked May 2003).
[6] , , (eds). Fault Diagnosis in Dynamic Systems, Theory and Applications. Control Engineering Series. Prentice-Hall: New York, 1989.
[7] , , . Parallel distributed compensation of a non-linear systems by Takagi and Sugeno fuzzy models. Proceedings of the Fourth IEEE International Conference on Fuzzy Systems (FUZZ IEEE/IFES’95), Yohohama, Japan, 1995; 531-538.
[8] , , . Design of fuzzy control systems based on relaxed LMI stability conditions. Proceedings of the 35th CDC, Kobe, 1996; 598-603.
[9] , , , . Robust and optimal fuzzy control: a linear matrix inequality approach. Proceedings of the 14th World Congress of IFAC International Federation of Automatic Control, vol. K, Beijing, 1999; 213-218.
[10] . Observers and controllers for Takagi-Sugeno fuzzy systems. Doctoral Dissertation, Department of Technology, Oerebro University, Sweden, Universitetsbiblioteket, 2001, ISBN 91-7668-285-4.
[11] Takagi, IEEE Transactions on Systems, Man and Cybernetics 15 pp 116– (1985) · Zbl 0576.93021 · doi:10.1109/TSMC.1985.6313399
[12] , , . Neuro-fuzzy based fault diagnosis applied to an electro-pneumatic valve. 15th Triennial World Congress of the International Federation of Automatic Control, Barcelona, Spain, 21-26 July, 2002.
[13] , . Fault diagnosis of an electro-pneumatic valve actuator using neural networks with fuzzy capabilities. 10th European Symposium on Artificial Neural Networks (ESANN), Bruges, Belgium, 24-26 April, 2002.
[14] , (eds). Evolutionary Algorithms in Engineering Applications. Springer: New York, 1997. · Zbl 0879.68043 · doi:10.1007/978-3-662-03423-1
[15] , , . Neural Network Design. PWS Publishing Company: Boston, MA, 1996, ISBN 0-534-94332-2.
[16] , , , . A GMDH neural network-based approach to robust fault diagnosis: application to the DAMADICS benchmark problem. Control Engineering Practice (CEP), special issue on: Development and Application of Methods for Actuator Diagnosis in an Industrial Control Systems: The DAMADICS Benchmark Study, 2005, to be published.
[17] , . Solving Least-Squares Problems. Prentice-Hall: Englewood Cliffs, NJ, 1974 (2nd edn, Society for Industrial and Applied Mathematics: Philadelphia, 1995, ISBN: 0898713560). · Zbl 0860.65028
[18] . Methods of Optimisation. Wiley: Chichester, U.K., 1975.
[19] , . Proceedings of the 14th World Congress of IFAC, Beijing, Han-Fu Chen, Dia-Zhan Cheng, Ji-Feng Zhang (eds), 5-9 July, 1999, Paper P-7e-09-6.
[20] Willsky, Automatica 12 pp 601– (1976)
[21] Basseville, Automatica 24 pp 309– (1988)
[22] , , , , . Introduction to the actuator benchmark actuator study. Control Engineering Practice (CEP), special issue on: Development and Application of Methods for Actuator Diagnosis in an Industrial Control Systems: The DAMADICS Benchmark Study, 2005, to be published.
[23] DAMADICS Benchmark definition, ver.1.0. (2003). ’http://diag.mchtr.pw.edu.pl/damadics/’, Institute of Automatic Control and Robotics, Warsaw University of Technology, accessed May 2003.
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.