Mathematical Approach towards Fault Detection and Isolation of Linear Dynamical Systems

Authors: V.Manikandan, N.Devarajan

Abstract:

The main objective of this work is to provide a fault detection and isolation based on Markov parameters for residual generation and a neural network for fault classification. The diagnostic approach is accomplished in two steps: In step 1, the system is identified using a series of input / output variables through an identification algorithm. In step 2, the fault is diagnosed comparing the Markov parameters of faulty and non faulty systems. The Artificial Neural Network is trained using predetermined faulty conditions serves to classify the unknown fault. In step 1, the identification is done by first formulating a Hankel matrix out of Input/ output variables and then decomposing the matrix via singular value decomposition technique. For identifying the system online sliding window approach is adopted wherein an open slit slides over a subset of 'n' input/output variables. The faults are introduced at arbitrary instances and the identification is carried out in online. Fault residues are extracted making a comparison of the first five Markov parameters of faulty and non faulty systems. The proposed diagnostic approach is illustrated on benchmark problems with encouraging results.

Keywords: Artificial neural network, Fault Diagnosis, Identification, Markov parameters.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1073052

References:

[1] N. L. C. Chui and J .M .Maciejowski, '' Sub space Identification - a Markov parameter approach'', International journal of control, vol78, no.17, 20, Nov. 2005, 1412-1436.
[2] Datta B, ''Numerical Methods for Linear Control Systems'', Academic Press ,London 2005.
[3] Gertler,J.,J.,.fault Detection and Diagnosis in Engineering Systems'',. Marcel Dekker.New York, 1998.
[4] Chen,J.,Patton,R.J. ''Robust Model-Based Fault Diagnosis for Dynamic systems'',.Kluwer Academic Publishers. Masssachusetts, 1999.
[5] Chiang.L.H.Russell,E.L.BraatzR.D ''.Fault Detection and Diagnosis in Industrial Systems'',.Springer,London, 2001.
[6] Venkatasubramanian. V., Rengaswamy,R., Kavuri.,S.N.m Yin, K., ''A review of process fault detection and diagnosis'' Part-III: Process history based methods. computers& Chemcial Engineering ,No.27, pp 327-346, 2003c.
[7] Venkatasubramanian,V.,Rengaswamy,R., Yin, K., Kavuri,S.N., ''.A review of process detection and diagnosis.'' Part-I: Quantitative model-based methods. Computers& Chemical Engineering, No.27, 293-311.,2003a.
[8] Korbiez ,J.,Koscienly.,J.,M.,Kowalezuk .Z.,Cholewa.W., ''.Fault Diagnosis.Models,ArtificialIntelligence.Aplications''.Springer.Berlin,2004.
[9] Gertler.J.,J.,Luo.Q. ''.Robust isolable models for fault diagnosis''. AIChE Journal ,No.35, pp 1856-1868, 1989.
[10] Frank,P.M., ''Fault diagnosis in dynamic systems using analytical and knowledge -based redundancy-a survey and some new results'',.Automatica , No 26(3),pp 459-474,1990.
[11] Mangoubi, R.S., ''Robust Estimation and Failure Detection. A Concise Treatment'',Springer. London.,1998.
[12] Isermann.R., ''.Fault Diagnosis of machines via parameter estimation and knowledge processing-tutorial paper'', Automatica, No 29(4) , pp 815-835, 1993.
[13] Maki,Y..Loparo.K.A., ''A neural-network approach to fault detection and diagnosis in industrial processes'', IEEE Transactions on Control Systems Technology ,No 5(6) ,529-541,1997.
[14] DE LA Fuente.M.J., Vega,P.,1999.Neural networks applied to fault detection of a biotechnical process. Engineering Applications of Artificial Intelligence, 12(5),569-584.
[15] De Miguel. L.j., Mediavilla,M..Peran,J.R. ''.Decision-making approaches for a model-based FDI method'', .In: Preprints of the Third IFAC Symposium on Fault Detection. Supervision and Safety for Technical Processes,Hull.U.K, pp719-725, 1997.
[16] Frank and KoppenSeliger,B. ''Deterministic nonlinear observer based approaches to fault diagnosis'',. International Journal of Approximate Reasoning, 161, 67-88,1997.
[17] Garcia,F.,J.,Izquierdo,V.,De Miguel,L.,J.,Peran,J.R., ''Fault diagnostic system using analytical fuzzy redundancy'',.Engineering Applications of Artificial Intelligence , No 1394, pp 441-450.,2000.
[18] Ayoubi.m.isermann.R.. ''.neuro-fuzzy systems for diagnosis'', fuzzy sets and systems, No89 (3), pp 289-307,1997.
[19] Calado, J.M.F.Korbick, J.Patan k, patton, R.J..sa da costa J.M.G., ''Soft computing approaches to fault diagnosis for dynamic systems'', European Journal of Control , No 7,248-286., 2001.
[20] Mendes,M.J.G.C.,Kowal, M.,Korbiez,J., sad a costa, J.M.G., '' Neuro-fuzzy structures in FDI systems.'', Preprints of the 15 th IFAC World Congress. Barcelona, Spain.P.2024, 2002.
[21] Witezak,M.,Korbicz,J., ''Genetic programming based observers for non-linear systems'',. In: Preprints of the Fourth IFAC Symposium on Fault Detection, Supervision and safety for Technical Processes ,Vol.2:Budapest,Hungary, pp 967-972, 2000.
[22] Obuchowicz,A.,Patan,K., '' An algorithm of evolutionary search with soft selection for training multi-layer feedforward NNs.'', In: Proceedings of the Third Conference NN&Their Applications, Poleland , pp 123-128.,1997.
[23] Chen, Y.M. and Lee, M.L.,''Neural Networks-Based Scheme for System Failure Detection and Diagnosis,'' Mathematics Computers Simulations, Vol. 58, No. 2, pp. 101-109. 2002.
[24] M.Borairi and H.Wang , ''Actuator and sensor fault diagnosis of non linear dynamic systems via genetic neural networks and parameter estimation techniques,'' in Proc.IEEE Int .Conf.Contr.Applicat. vol1,pp . 278-282. 2002.
[25] F.Filippeti,G.Franceschini,C.Tassoni and Vas,'' Recent developments of induction motor drives fault diagnosis using AI techniques,'' IEEE Trans. Industrial Elect, vol47, no.5, pp994-1004,October 2000.
[26] Vendatasubramanian,V., Rengaswamy.R., Kavuri.,S.N., ''.A review of process fault detection and diagnosis.'', Part-II: Qualitative models and search strategies.Computers & Chemical Engineering,,No 27, pp 313-326, 2003b.
[27] Luis .J.De Miguel , L.Felipe Blanquez, ''Fuzzy logic based decision making for fault diagnosis in a dc motor '', International journal on Engineering Applications of Artificial Intelligence , Vol 18, pp 423 -450, 2005.
[28] Gertler.J.J., ''All linear methods are Equal-and extendible to nonlinearities'', In:Preprints of the Fourth IFAC Symposium on Fault detection,Supervision and safety for technical process ,VolI.Budapest.Hungary, pp.52-63., 2000.
[29] Kinnaert,M., ''Fault diagnosis based on analytical models for linear and nonlinear systems. A tutorial'', In: Preprints of the Fifth Technical Processes.Washington.DC, USA pp 37-50, 2003.
[30] Lin,W,Wang H., ''Linearization techniques in fault diagnosis of non-linear systems.'', Journal of Systems and Control Engineering Part1 214(4),241-245., 2000.
[31] Blazquez .L.F., de Miguel, L.J.. ''Saturation effects detecting additive faults'',.In:Proceedings of the European Control Conference. Porto, Portugal, pp.2340-2345.,2001
[32] Kishnaswami.V.Rizzoni,G.,''Nonlinear parity equation residual generation for fault detection and isolation.'',In:Preprints of the second IFAC Syposium on Fault Detection.Supervision and Safety for Technical Processes. Vol.1.Espoo.,Finland ,pp .317-322, 1994.
[33] Garcia,E.A.,Frank.P.M., ''.Deterministic nonlinear observer based approaches to fault diagnosis'',A survey. Control Engineering Practice , No5(5), pp 663-670,1997.
[34] Shumsky.A.,Y.,''Robust residual generation for diagnosis of nonlinear systems: Parity relation approach'',In:preprints of the Third IFAC Symposium on Fault Detection ,Supervision and Safety for Technical Processes, Hull,UK, pp 867-872,1997.
[35] Hammouri,H.,Kinnaert.M.,E1Yaagobi,E.H, '' .Observer-based approach to fault detection and isolation for nonlinear systems'', .IEEE Transactions on Automatic Control , No 44(10), pp 1879-1884,1997.
[36] Blazquez.L.F., Foces.J.M, deMiguel. ''Additive fault detection in a real nonlinear system with saturation'', In: Preprints of the Fifth IFAC Symposium on Fault Detection. Supervision and Safety for ''Technical Proccesses.Washington.DC,USA,pp.1119-1124,2003.
[37] Bassevile.M..mikiforov,I., ''Detection of Abrupt changes:Theory and Application.'', Prentice-Hall ,New York,1993.
[38] Frank,P.M., ''Applications of fuzzy logic to process supervision and fault diagnosis.'',.In:Preprints of the Second IFAC Symposium on Fault Detection. Supervision and Safety for Technical Processes.Vol.2.Esopp,Finland,pp.531-538,1994.
[39] Gertler.J.J., Singer.D., ''A new structural framework for parity equation-based failure detection and isolation '', Automatica 26(2),381-388,1990.
[40] Moonen M and Ramos J, ''A subspace algorithm for balanced state space system identification'', IEEE Trans. on Automatic Control, Vol. 38, pp.1727-1729, 1993.
[41] Moonen M. and Vandewalle J, ''QSVD Approach to online and offline state-space identification'', Int. J. Control, Vol.51, pp.1133-1146, 1990.
[42] Ljumg, L. ''Systems Identification : Theory for the user'' , second edition ,Prentice hall, Engle wood Cliffs, NJ,1999
[43] Ogata. k, ''Modern Control Engineering'', Third Edition, PHI 2004.