Advanced pattern recognition techniques for system monitoring and diagnosis : A survey

In the feature-based approach to system monitoring and diagnosis, knowledge about the system is assumed to consist exclusively in a database of measurement vectors and associated operating conditions. This data is used to build a mapping from the measurement space onto a decision space, in such a way that the probability of misclassification (or assignment to a wrong state) is minimised. In this paper, the main pattern recognition techniques applicable to this problem are reviewed. Standard statistical techniques are generally not sufficient because (1) they assume a priori knowledge of all system states, and (2) they do not take into account the time evolution of the process under study. Some recent approaches are based on non-standard theories of uncertainty such as fuzzy logic and evidence theory. Specific techniques allow us to make classifiers (1) more robust by taking into account past decisdons to establish a diagnostic, (2) adaptive by including incremental procedures for parameter learning and detection of new classes, and (3) predictive by anticipating the evolution of the system.

[1]  Anil K. Jain,et al.  Small Sample Size Effects in Statistical Pattern Recognition: Recommendations for Practitioners , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Richard P. Lippmann,et al.  Neural Networks, Bayesian a posteriori Probabilities, and Pattern Classification , 1994 .

[3]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[4]  Bernard Dubuisson,et al.  A statistical decision rule with incomplete knowledge about classes , 1993, Pattern Recognit..

[5]  Heikki N. Koivo,et al.  Application of artificial neural networks in process fault diagnosis , 1991, Autom..

[6]  James M. Keller,et al.  Information fusion in computer vision using the fuzzy integral , 1990, IEEE Trans. Syst. Man Cybern..

[7]  G. Govaert,et al.  Combined supervised and unsupervised learning for system diagnosis using Dempster-Shafer theory , 1996 .

[8]  Thierry Denoeux,et al.  Generalizing the Evidence-Theoretic k-NN rule to Fuzzy Pattern Recognition , 1997 .

[9]  B. Dubuisson,et al.  Tool Wear Monitoring and Diagnosis in Milling Using Vibration Signal , 1994 .

[10]  Paul M. Frank,et al.  Fault Diagnosis in Dynamic Systems , 1993, Robotics, Mechatronics and Manufacturing Systems.

[11]  Teuvo Kohonen,et al.  The self-organizing map , 1990 .

[12]  Michel Grabisch,et al.  Fuzzy Measures and Integrals , 1995 .

[13]  B. Dubuisson,et al.  Conception d'un module de reconnaissance des formes floues pour le diagnostic , 1996 .

[14]  Thierry Dennux.  Reasoning with Imprecise Belief Structures 1 , 1997 .

[15]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[16]  Sankar K. Pal,et al.  Fuzzy sets and decisionmaking approaches in vowel and speaker recognition , 1977 .

[17]  Richard O. Duda,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[18]  Denoeux.  1 - Application du modèle des croyances transférables en reconnaissance de formes , 1997 .

[19]  R. Bellman,et al.  Abstraction and pattern classification , 1996 .

[20]  Michel Grabisch,et al.  The representation of importance and interaction of features by fuzzy measures , 1996, Pattern Recognit. Lett..

[21]  Alessandro Saffiotti,et al.  The Transferable Belief Model , 1991, ECSQARU.

[22]  Michèle Basseville,et al.  Detecting changes in signals and systems - A survey , 1988, Autom..

[23]  Bernard Dubuisson,et al.  Surveillance of a Nuclear Reactor by Use of a Pattern Recognition Methodology , 1980, IEEE Transactions on Systems, Man, and Cybernetics.

[24]  Steffen Leonhardt,et al.  Real-time supervision for diesel engine injection , 1994 .

[25]  F. Girosi,et al.  Networks for approximation and learning , 1990, Proc. IEEE.

[26]  B. Dubuisson,et al.  On-Line Diagnosis of a Technological System: a Fuzzy Pattern Recognition Approach , 1996 .

[27]  Sankar K. Pal,et al.  Fuzzy models for pattern recognition , 1992 .

[28]  Thierry Denoeux,et al.  A k-nearest neighbor classification rule based on Dempster-Shafer theory , 1995, IEEE Trans. Syst. Man Cybern..

[29]  T. Trautmann,et al.  Comparison of dynamic feature map models for environmental monitoring , 1995, Proceedings of ICNN'95 - International Conference on Neural Networks.

[30]  Federico Girosi,et al.  Regularization Theory, Radial Basis Functions and Networks , 1994 .

[31]  Glenn Shafer,et al.  A Mathematical Theory of Evidence , 2020, A Mathematical Theory of Evidence.

[32]  B. Dubuisson,et al.  K-step ahead prediction in fuzzy decision space-application to prognosis , 1992, [1992 Proceedings] IEEE International Conference on Fuzzy Systems.

[33]  Leo Breiman,et al.  Classification and Regression Trees , 1984 .

[34]  L. F. Pau.  Diagnosis of Equipment Failures by Pattern Recognition , 1974 .

[35]  Lalla Merieme Zouhal,et al.  A Comparison between Fuzzy and Evidence-theoretic K-nn Rules for Pattern Recognition , 1995 .

[36]  James C. Bezdek,et al.  Pattern Recognition with Fuzzy Objective Function Algorithms , 1981, Advanced Applications in Pattern Recognition.

[37]  Régis Lengellé,et al.  Training MLPs layer by layer using an objective function for internal representations , 1996, Neural Networks.

[38]  Gilles Mourot,et al.  Pattern recognition for diagnosis of technological systems: a review , 1993, Proceedings of IEEE Systems Man and Cybernetics Conference - SMC.

[39]  Teuvo Kohonen,et al.  Self-Organization and Associative Memory , 1988 .

[40]  Thierry Denoeux,et al.  An Adaptive k-NN Rule Based on Dempster-Shafer Theory , 1995, CAIP.

[41]  Keinosuke Fukunaga,et al.  Introduction to Statistical Pattern Recognition , 1972 .

[42]  Paul M. Frank,et al.  Fault diagnosis in dynamic systems using analytical and knowledge-based redundancy: A survey and some new results , 1990, Autom..

[43]  Yoshua Bengio,et al.  Pattern Recognition and Neural Networks , 1995 .

[44]  A fuzzy clustering algorithm based on the k-nearest neighbors rule for the detection of evolution , 1993, Proceedings of IEEE Systems Man and Cybernetics Conference - SMC.

[45]  C. Frélicot.  Un systeme adaptatif de diagnostic predictif par reconnaissance des formes floues , 1992 .

[46]  Sankar K. Pal,et al.  Fuzzy tools for the management of uncertainty in pattern recognition, image analysis, vision and expert systems , 1991 .

[47]  G. McLachlan.  Discriminant Analysis and Statistical Pattern Recognition , 1992 .

[48]  Rolf Isermann,et al.  Process fault detection based on modeling and estimation methods - A survey , 1984, Autom..

[49]  Thierry Denoeux,et al.  Analysis of evidence-theoretic decision rules for pattern classification , 1997, Pattern Recognit..

[50]  H. Carter.  Fuzzy Sets and Systems — Theory and Applications , 1982 .

[51]  Steffen Leonhardt,et al.  Real-time supervision for diesel engine injection , 1994 .

[52]  O. Bardou,et al.  Early detection of leakages in the exhaust and discharge systems of reciprocating machines by vibration analysis , 1994 .

[53]  C. K. Chow,et al.  On optimum recognition error and reject tradeoff , 1970, IEEE Trans. Inf. Theory.

[54]  Thierry Denoeux.  An evidence-theoretic neural network classifier , 1995, 1995 IEEE International Conference on Systems, Man and Cybernetics. Intelligent Systems for the 21st Century.

[55]  Michel Grabisch,et al.  Classification by fuzzy integral: performance and tests , 1994, CVPR 1994.

[56]  Padhraic Smith,et al.  Detecting novel fault conditions with hidden Markov models and neural networks , 1994 .

[57]  Padhraic J. Smyth,et al.  Hidden Markov models for fault detection in dynamic systems , 1993 .