Advances in model-based fault diagnosis with evolutionary algorithms and neural networks
Witczak, Marcin
International Journal of Applied Mathematics and Computer Science, Tome 16 (2006), p. 85-99 / Harvested from The Polish Digital Mathematics Library

Challenging design problems arise regularly in modern fault diagnosis systems. Unfortunately, the classical analytical techniques often cannot provide acceptable solutions to such difficult tasks. This explains why soft computing techniques such as evolutionary algorithms and neural networks become more and more popular in industrial applications of fault diagnosis. The main objective of this paper is to present recent developments regarding the application of evolutionary algorithms and neural networks to fault diagnosis. In particular, a brief introduction to these computational intelligence paradigms is presented, and then a review of their fault detection and isolation applications is performed. Close attention is paid to techniques that integrate the classical and soft computing methods. A selected group of them is carefully described in the paper. The performance of the presented approaches is illustrated with the use of the DAMADICS fault detection benchmark that deals with a valve actuator.

Publié le : 2006-01-01
EUDML-ID : urn:eudml:doc:207780
@article{bwmeta1.element.bwnjournal-article-amcv16i1p85bwm,
     author = {Witczak, Marcin},
     title = {Advances in model-based fault diagnosis with evolutionary algorithms and neural networks},
     journal = {International Journal of Applied Mathematics and Computer Science},
     volume = {16},
     year = {2006},
     pages = {85-99},
     zbl = {1334.90045},
     language = {en},
     url = {http://dml.mathdoc.fr/item/bwmeta1.element.bwnjournal-article-amcv16i1p85bwm}
}
Witczak, Marcin. Advances in model-based fault diagnosis with evolutionary algorithms and neural networks. International Journal of Applied Mathematics and Computer Science, Tome 16 (2006) pp. 85-99. http://gdmltest.u-ga.fr/item/bwmeta1.element.bwnjournal-article-amcv16i1p85bwm/

[000] Alessandri A., Parisini T. and Zoppoli R (1997): Neural approximators for non-linear finite-memory state estimation. - Int. J. Contr., Vol. 67, No. 2, pp. 275-302. | Zbl 0875.93490

[001] Atkinson A.C. and Donev A.N. (1992): Optimum Experimental Designs. - New York: Oxford University Press. | Zbl 0829.62070

[002] Back T., Hammel U. and Schwefel H.P.(1997): Evolutionary computation: Comments on the history and current state. - IEEE Trans. Evolut. Computat., Vol. 1, No. 1, pp. 3-17

[003] Blanke M., Kinnaert M., Lunze J. and Staroswiecki M. (2003): Diagnosis and Fault-Tollerant Control. - Berlin: Springer | Zbl 1023.93001

[004] Chandra P. and Sing Y. (2004): Feedforward sigmoidal networks - Equicontinuity and fault tolerance. - IEEE Trans. Neural Netw., Vol. 15, No. 6, pp. 1350-1366.

[005] Chen J. and Patton R. J. (1999): Robust Model-based Fault Diagnosis for Dynamic Systems. - London: Kluwer. | Zbl 0920.93001

[006] Chen J., Patton R. J. and Liu G.P. (1996): Optimal residual design for fault diagnosis using multi-objective optimization and genetic algorithms. - Int. J. Syst. Sci., Vol. 27, No. 6,pp. 567-576. | Zbl 0854.93134

[007] Chen Z., He Y., Chu F. and Huang J. (2003): Evolutionary strategy for classification problems and its application in fault diagnosis. - Eng. Appl. Artif. Intell., Vol. 16, No. 1, pp. 31-38.

[008] Cohn D.A. (1994): Neural network exploration using optimal experimental design, In: Advances in Neural Information Processing Systems 6 (J. Cowan et al., Eds.). - San Mateo: Morgan Kaufman.

[009] Chryssolouris G., Lee M. and Ramsey A. (1996): Confidence interval predictionfor neural network models. - IEEE Trans. Neural Netw., Vol. 7,No. 1, pp. 229-232.

[010] DAMADICS (2004): Website of DAMADICS: Development and Application of Methods for Actuator Diagnosis in Industrial Control Systems. http://diag.mchtr.pw.edu.pl/damadics/ .

[011] Delebecque F., Nikoukah R. and Rubio Scola H. (2003): Test signal design for failure detection: A linear programming approach. - Int. J. Appl. Math. Comput. Sci., Vol. 13, No. 4, pp. 515-526. | Zbl 1049.93032

[012] Fedorov V.V., and Hackl P. (1997): Model-Oriented Design of Experiments.- New York: Springer. | Zbl 0878.62052

[013] Fleming P.J. and Purshouse (2002): Evolutionary algorithms in control systems engineering: A survey. - Contr. Eng. Pract., Vol. 10, No. 11,pp. 1223-1241.

[014] Fogel D.B. (1995): Evolutionary Computation:Toward a New Philosophy of Machine Intelligence. - New York: Willey-IEEE Press.

[015] Fogel L.J., Owens A.J. and Walsh M.J.(1999): An overview of evolutionary programming, In: Evolutionary Algorithms (De Jong K., Vose M.D. and Whitley L.D.,Eds.). - Heidelberg: Springer.

[016] Frank P.M. and Koppen-Seliger (1997): New developments using AI in fault diagnosis. -Eng. Appl. Artif. Intell., Vol. 10, No. 1, pp. 3-14.

[017] Frank P.M., Schreier G. and Garcia E.A. (1999): Non-linear observers for fault detection and isolation, In: New Directions in Non-linear Observer Design (Nijmeijer H., Fossen T.I., Eds.).- Berlin: Springer.

[018] Fuente M.J. and Saludes S. (2000): Fault detection and isolation in a non-linear plantvia neural networks. - Proc. Symp. Fault Detection, Supervisionand Safety for Technical Processes, SAFEPROCESS, Budapest, Hungary, pp. 472-477.

[019] Fukumizu K. (1996): Active learning in multilayer perceptrons, In: Advances in Neural Information Processing Systems (D.S. Touretzky et al., Eds.). - Cambridge: MIT Press, pp. 295-301.

[020] Fukumizu K. (2000): Statistical active learning in multilayer perceptrons. - IEEE Trans. Neural Netw., Vol. 11, No. 1, pp. 17-26.

[021] Galar R. (1989): Evolutionary search with soft selection. - Biol. Cybern., Vol. 60, No. 1, pp. 124-141. | Zbl 0659.92012

[022] Goodwin G.C. and Payne R.L. (1977): Dynamic Systems Identification. Experiment Design and Data Analysis. - New York: Acadamic Presss. | Zbl 0578.93060

[023] Gray G. J, Murray-Smith D. J., Li Y., SharmanK. C. and Weinbrenner T. (1998): Non-linear model structure identification using genetic programming. - Contr. Eng. Pract., Vol. 6, No. 11, pp. 1341-1352.

[024] Guo L.Z. and Zhu Q.M. (2002): A fast convergent extended Kalman observer for non-linear discrete-time systems. - Int. J. Syst. Sci., Vol. 33, No. 13, pp. 1051-1058. | Zbl 1029.93008

[025] Gupta M.M., Jin L. and Homma N. (2003): Static and Dynamic Neural Networks. From Fundamentals to Advanced Theory. -Hoboken, NJ: Wiley.

[026] Holland J.H. (1975): Adaptation in Naturaland Artificial Systems. - Ann Arbor, MI: The University of Michigan Press.

[027] Hunt K.J., Sbarbaro D., Zbikowski R. and Gawthrop P.J. (1992): Neural networks for control systems - A survey. -Automatica, Vol. 28, No. 6, pp. 1083-1112. | Zbl 0763.93004

[028] Ivakhnenko A.G. and Mueller J.A. (1995): Self-organizing of nets of active neurons. - Syst. Anal. Modell. Simul., Vol. 20, pp. 93-106.

[029] Janczak A. (2005): Identification of Non-Linear Systems Using Neural Networks and Polynomial Models: A Block-Oriented Approach. - Berlin: Springer. | Zbl 1103.93023

[030] Karpenko M., Sepehri N. and Scuse D. (2003): Diagnosis of process valve actuator faults using a multilayer neural network. - Contr. Eng. Practice, Vol. 11, No. 11, pp. 1289-1299.

[031] Korbicz J., Kościelny J.M., Kowalczuk Z. and Cholewa W. (Eds.) (2004): Fault Diagnosis. Models, Artificial Intelligence, Applications. - Berlin: Springer. | Zbl 1074.93004

[032] Kowalczuk Z., Suchomski P. and Białaszewski T. (1999): Evolutionary muti-objective Pareto optimization of diagnostic state observers. - Int. J. Appl. Math. Comput.Sci., Vol. 9, No. 3, pp. 689-709. | Zbl 0945.93515

[033] Koza J. R. (1992): Genetic Programming: On the Programming of Computers by Means of Natural Selection.- Cambridge: The MIT Press. | Zbl 0850.68161

[034] Le T.T., Watton J. and Pham D.T. (1997): An artificial neural network based approach to fault diagnosis and classification of fluid power systems. - J. Syst. Contr. Eng., Vol. 211, No. 4, pp. 307-317.

[035] Le T.T., Watton J. and Pham D.T. (1998): Fault classification of fluid power systems using a dynamics feature extraction technique and neural networks. - J. Syst. Contr. Eng., Vol. 212, No. 2, pp. 87-97.

[036] MacKay D. (1992): Information-based objective functions for active data selection. - Neural Comput., Vol. 4, No. 4, pp. 305-318.

[037] Marcu T. (1997): A multiobjective evolutionary approach to pattern recognition for robust diagnosis of process faults. - Proc. Symp. Fault Detection, Supervision and Safety for Technical Processes, SAFEPROCESS, Hull, UK, pp. 1183-1188.

[038] Metenidis M.F., Witczak M. and Korbicz J. (2004): A novel genetic programming approach to non-linear system modelling: Application to the DAMADICS benchmark problem. - Eng. Appl. Artif. Intell., Vol. 17, No. 4, pp. 363-370.

[039] Michalewicz Z. (1996): Genetic Algorithms+ Data Structures = Evolution Programs. - Berlin: Springer. | Zbl 0841.68047

[040] Milanese M., Norton J., Piet-Lahanier H. and Walter E. (Eds.) (1996): Bounding Approaches to System Identification. - New York: Plenum Press. | Zbl 0845.00024

[041] Miller J.A., Potter W.D., Gandham R.V. and Lapena C.N. (1993): An evaluation of local improvement operators for genetic algorithms. - IEEE Trans. Syst. Man and Cybern., Vol. 23, No. 5, pp. 1340-1351.

[042] Mrugalski M. and Witczak M. (2002): Parameter estimation of dynamic GMDH neural networks with the bounded-error technique. - J. Appl. Comput. Sci., Vol. 10, No. 1, pp. 77-90.

[043] Narendra K.S. and Parthasarathy K. (1990): Identification and control of dynamical systems using neural networks. - IEEE Trans. Neural Netw., Vol. 1, No. 1, pp. 1-27.

[044] Patan K. and Parisini T. (2005): Identification of neural dynamic models for fault detection and isolation: the case of a real sugar evaporation process. - J. Proc. Contr., Vol. 15, No. 1, pp. 67-79.

[045] Porter L.L. and Passino K.M. (1995): Genetic adaptive observers. - Eng. Appl. Artif. Intell., Vol. 8, No. 3, pp. 261-269.

[046] Ruano A.E. (Ed.) (2005): Intelligent Control Systems Using Computational Intelligence Techniques. - London: The IEE Press. | Zbl 1109.93003

[047] Sjoberg J., Zhang Q., Ljung L., Benveniste A., Delyon B., Glorennec P. Y., Hjalmarsson H. and Juditsky A. (1995): Non-linear black-box modeling in system identification: A unified overview. - Automatica, Vol. 31, No. 12, pp. 1691-1724. | Zbl 0846.93018

[048] Sun R., Tsung F. and Qu L. (2004): Combining bootstrap and genetic programming for feature discovery in diesel engine diagnosis. - Int. J. Ind. Eng.,Vol. 11, No. 3, pp. 273-281.

[049] Uciński D. (2005): Optimal Measurements Methods for Distributed Parameter System Identification. - Boca Raton, FL: CRC Press. | Zbl 1155.93003

[050] Walter E. and Pronzato L. (1997): Identification of Parametric Models from Experimental Data. - Berlin: Springer | Zbl 0864.93014

[051] Watton J. and Pham D.T. (1997): An artificial NN based approach to fault diagnosis and classification of fluid power systems. - J. Syst. Contr.Eng., Vol. 211, No. 4, pp. 307-317.

[052] Weerasinghe M., Gomm J.B and Williams D. (1998): Neural networks for fault diagnosis of a nuclear fuel processing plant at different operating points. - Contr. Eng. Pract., Vol. 6, No. 2, pp. 281-289.

[053] Witczak M., Obuchowicz A. and Korbicz J. (2002): Genetic programming based approaches to identification and fault diagnosis of non-linear dynamic systems. - Int. J. Contr., Vol. 75, No. 13, pp. 1012-1031. | Zbl 1028.93009

[054] Witczak M. (2003): Identification and Fault Detection of Non-linear Dynamic Systems. - Zielona Góra: University of Zielona Góra Press. | Zbl 1101.93005

[055] Witczak M. and Korbicz J. (2004): Observers and genetic programming in the identification and fault diagnosis of non-linear dynamic systems, In: Fault Diagnosis. Models, Artificial Intelligence, Applications (Korbicz J., Kościelny J.M., Kowalczuk Z. and Cholewa W., Eds.). - Berlin: Springer.

[056] Witczak M., Korbicz J., Mrugalski M. and Patton R.J. (2006): GMDH neural network-based approach to robust fault detection and its application to solve the DAMADICS benchmark problem. -Contr. Eng. Pract., Vol. 14, No. 6, pp. 671-683.

[057] Witczak M. and Pretki P. (2005): Designing neural-network-based fault detection systems with D-optimum experimental conditions. - Comput. Assist. Mech. Engi. Sci., Vol. 12, No. 2, pp. 279-291. | Zbl 1180.62110

[058] Witczak M. (2006): Towards the training of feed-forward neural networks with the D-optimum input sequence. - IEEE Trans. Neural Netw., Vol. 17, No. 2, pp. 357-373.

[059] White H. (1989): Learning in artificial neural networks: A statistical perspective. - Neural Comput., Vol. 4, No. 4, pp. 305-318.

[060] Yen G.G. and Lin K. (2000): Wavelet packet feature extraction for vibration monitoring. - IEEE Trans. Ind. Electron., Vol. 47, No. 3, pp. 650-667.

[061] Zhang J., Ma J. and Yan Y. (2000): Assessing blockage of the sensing line in a differential-pressure flow sensor by using the wavelet transform of its output. - Meas. Sci. Technol., Vol. 11, No. 3, pp. 178-184.

[062] Zhao J., Chen B. and Shen J. (1998): Multidimensional nonorthogonal wavelet-sigmoid basis function neural network for dynamic process fault diagnosis. - Comput. Chem. Eng., Vol. 23, pp. 83-92.

[063] Zolghardi A., Henry D. and Monision M. (1996): Design of non-linear observers for fault diagnosis. A case study. - Contr. Eng. Pract., Vol. 4, No. 11, pp. 1535-1544.