Towards Robustness in Neural Network Based Fault Diagnosis

Patan, Krzysztof; Witczak, Marcin; Korbicz, Józef

doi:10.2478/v10006-008-0039-2

Abstract

Challenging design problems arise regularly in modern fault diagnosis systems. Unfortunately, classical analytical techniques often cannot provide acceptable solutions to such difficult tasks. This explains why soft computing techniques such as neural networks become more and more popular in industrial applications of fault diagnosis. Taking into account the two crucial aspects, i.e., the nonlinear behaviour of the system being diagnosed as well as the robustness of a fault diagnosis scheme with respect to modelling uncertainty, two different neural network based schemes are described and carefully discussed. The final part of the paper presents an illustrative example regarding the modelling and fault diagnosis of a DC motor, which shows the performance of the proposed strategy.

References

Blanke M., Kinnaert M., Lunze J. and Staroswiecki M. (2003). Diagnosis and Fault-Tolerant Control, Springer, New York, NY.10.1007/978-3-662-05344-7
Search in Google Scholar
Chen J. and Patton R. J. (1999). Robust Model-Based Fault Diagnosis for Dynamic Systems, Kluwer, Berlin.10.1007/978-1-4615-5149-2
Search in Google Scholar
Duzinkiewicz K. (2006). Set membership estimation of parameters and variables in dynamic networks by recursive algorithms with a moving measurement window, International Journal of Applied Mathematics and Computer Science 16(2): 209-217.
Search in Google Scholar
Frank P. M. and Köppen-Seliger B. (1997). New developments using AI in fault diagnosis, Engineering Applications of Artificial Intelligence 10(1): 3-14.10.1016/S0952-1976(96)00072-3
Search in Google Scholar
Fuessel D. and Isermann R. (2000). Hierarchical motor diagnosis utilising structural knowledge and a self-learning neuro-fuzzy scheme, IEEE Transactions on Industrial Electronics 47(5): 1070-1077.10.1109/41.873215
Search in Google Scholar
Gertler J. (1998). Fault Detection and Diagnosis in Engineering Systems, Marcel Dekker, New York, NY.
Search in Google Scholar
Haykin S. (1999). Neural Networks. A Comprehensive Foundation, 2nd Ed., Prentice-Hall, Englewood Cliffs, NJ.
Search in Google Scholar
Iserman R. (2006). Fault Diagnosis Systems. An Introduction from Fault Detection to Fault Tolerance, Springer, New York, NY.10.1007/3-540-30368-5
Search in Google Scholar
Ivakhnenko A. G. and Mueller J. A. (1995). Self-organizing of nets of active neurons, System Analysis Modelling Simulation 20(2): 93-106.
Search in Google Scholar
Köppen-Seliger B. and Frank P. M. (1999). Fuzzy logic and neural networks in fault detection, in L. Jain and N. Martin (Eds.), Fusion of Neural Networks, Fuzzy Sets, and Genetic Algorithms, CRC Press, New York, NY, pp. 169-209.
Search in Google Scholar
Korbicz J. (2006). Fault detection using analytical and soft computing methods, Bulletin of the Polish Academy of Sciences: Technical Sciences 54(1): 75-88.
Search in Google Scholar
Korbicz J., Kościelny J., Kowalczuk Z. and Cholewa W. (2004). Fault Diagnosis. Models, Artificial Intelligence, Applications, Springer, Berlin.10.1007/978-3-642-18615-8
Search in Google Scholar
Korbicz J., Patan K. and Kowal M. (Eds.) (2007). Fault Diagnosis and Fault Tolerant Control, Academic Publishing House EXIT, Warsaw.
Search in Google Scholar
Li L., Mechefske C. K. and Li W. (2004). Electric motor faults diagnosis using artificial neural networks, Insight: Non-Destructive Testing and Condition Monitoring 46(10): 616-621.10.1784/insi.46.10.616.45210
Search in Google Scholar
Ljung L. (1999). System Identification—Theory for the User, Prentice Hall, Englewood Cliffs, NJ.
Search in Google Scholar
Marcu T., Mirea L. and Frank P. M. (1999). Development of dynamical neural networks with application to observer based fault detection and isolation, International Journal of Applied Mathematics and Computer Science 9(3): 547-570.
Search in Google Scholar
Milanese M. (2004). Set membership identification of nonlinear systems, Automatica 40(6): 957-975.10.1016/j.automatica.2004.02.002
Search in Google Scholar
Milanese M., Norton J., Piet-Lahanier H. and Walter E. (1996). Bounding Approaches to System Identification, Plenum Press, New York, NY.10.1007/978-1-4757-9545-5
Search in Google Scholar
Moseler O. and Isermann R. (2000). Application of model-based fault detection to a brushless DC motor, IEEE Transactions on Industrial Electronics 47(5): 1015-1020.10.1109/41.873209
Search in Google Scholar
Mrugalski M. (2004). Neural Network Based Modelling of Nonlinear Systems in Fault Detection Schemes., Ph.D. thesis, University of Zielona Góra, (in Polish).
Search in Google Scholar
Mueller J. E. and Lemke F. (2000). Self-Organising Data Mining, Libri, Hamburg.
Search in Google Scholar
Nandi S., Toliyat H. A. and Li X. (2005). Condition monitoring and fault diagnosis of electrical motors—A review, IEEE Transactions on Energy Conversion 20(4): 719-729.10.1109/TEC.2005.847955
Search in Google Scholar
Narendra K. S. and Parthasarathy K. (1990). Identification and control of dynamical systems using neural networks, IEEE Transactions on Neural Networks 1(1): 12-18.10.1109/72.80202
Search in Google Scholar
Nelles O. (2001). Nonlinear System Identification. From Classical Approaches to Neural Networks and Fuzzy Models, Springer-Verlag, Berlin.10.1007/978-3-662-04323-3
Search in Google Scholar
Norgard M., Ravn O., Poulsen N. and Hansen L. (2000). Networks for Modelling and Control of Dynamic Systems, Springer, London.10.1007/978-1-4471-0453-7
Search in Google Scholar
Patan K. (2007a). Approximation ability of a class of locally recurrent globally feed-forward neural networks, Proceedings of the European Control Conference, ECC 2007, Kos, Greece, published on CD-ROM.10.23919/ECC.2007.7068622
Search in Google Scholar
Patan K. (2007b). Robust faul diagnosis in a DC motor by means of artificial neural networks and model error modelling, in J. Korbicz, K. Patan and M. Kowal (Eds.), Fault Diagnosis and Fault Tolerant Control, Academic Publishing House EXIT, Warsaw, pp. 337-346.
Search in Google Scholar
Patan K. (2007c). Stability analysis and the stabilization of a class of discrete-time dynamic neural networks, IEEE Transactions on Neural Networks 18(3): 660-673.10.1109/TNN.2007.891199
Search in Google Scholar
Patan K. (2008). Aproximation of state-space trajectories by locally recurrent globally feed-forward neural networks, Neural Networks 21(1): 59-64.10.1016/j.neunet.2007.10.004
Search in Google Scholar
Patan K., Korbicz J. and Głowacki G. (2007). DC motor fault diagnosis by means of artificial neural networks, Proceedings of the 4th International Conference on Informatics in Control, Automation and Robotics, ICINCO 2007, Angers, France, published on CD-ROM.
Search in Google Scholar
Patan K. and Parisini T. (2002). Stochastic learning methods for dynamic neural networks: Simulated and real-data comparisons, Proceedings of the 2002 American Control Conference, ACC'02, Anchorage, AK, USA, pp. 2577-2582.
Search in Google Scholar
Patan K. and Parisini T. (2005). Identification of neural dynamic models for fault detection and isolation: The case of a real sugar evaporation process, Journal of Process Control 15(1): 67-79.10.1016/j.jprocont.2004.04.001
Search in Google Scholar
Puig V., Stancu A., Escobet T., Nejjari F., Quevedo J. and Patton R. J. (2006). Passive robust fault detection using interval observers: Application to the DAMADICS benchmark problem, Control Engineering Practice 14(6): 621-633.10.1016/j.conengprac.2005.03.016
Search in Google Scholar
Reinelt W., Garulli A. and Ljung L. (2002). Comparing different approaches to model error modeling in robust identification, Automatica 38(5): 787-803.10.1016/S0005-1098(01)00269-2
Search in Google Scholar
Rodrigues M., Theilliol D., Aberkane S. and Sauter D. (2007). Fault tolerant control design for polytopic LPV systems, International Journal of Applied Mathematics and Computer Science 17(1): 27-37.10.2478/v10006-007-0004-5
Search in Google Scholar
Rutkowski L. (2004). New Soft Computing Techniques for System Modelling, Pattern Classification and Image Processing, Springer, Berlin.10.1007/978-3-540-40046-2
Search in Google Scholar
Walter E. and Pronzato L. (1997). Identification of Parametric Models from Experimental Data, Springer, London.
Search in Google Scholar
Witczak M. (2006). Advances in model-based fault diagnosis with evolutionary algorithms and neural networks, International Journal of Applied Mathematics and Computer Science 16(1): 85-99.
Search in Google Scholar
Witczak M. (2007). Modelling and Estimation Strategies for Fault Diagnosis of Non-linear Systems, Springer, Berlin.
Search in Google Scholar
Witczak M., Korbicz J., Mrugalski M. and Patton R. J. (2006). A GMDH neural network-based approach to robust fault diagnosis: Application to the DAMADICS benchmark problem, Control Engineering Practice 14(6): 671-683.10.1016/j.conengprac.2005.04.007
Search in Google Scholar
Xiang-Qun L. and Zhang H. Y. (2000). Fault detection and diagnosis of permanent-magnet DC motor based on parameter estimation and neural network, IEEE Transactions on Industrial Electronics 47(5): 1021-1030.10.1109/41.873210
Search in Google Scholar

Towards Robustness in Neural Network Based Fault Diagnosis

Abstract

Paradigm

My account