Qualitative And Neural Decision For Fault Detection And Isolation

Abstract This work focuses on a residual evaluation method that explores the symbolic-numeric integration capability provided by fuzzy sets. Qualitative information obtained from symbolic interpretation of residual responses, such as signs, is used to obtain robust isolation properties. A general framework based on fuzzy systems is proposed so that the reasoning procedure can be designed either from a qualitative analysis of the residual responses or directly by the identification of a recurrent neural network. An application to an electrical motor illustrates the proposed method.

[1]  Janos Gertler,et al.  An evidential reasoning extension to quantitative model-based failure diagnosis , 1992, IEEE Trans. Syst. Man Cybern..

[2]  Paul M. Frank,et al.  Analytical and Qualitative Model-based Fault Diagnosis - A Survey and Some New Results , 1996, Eur. J. Control.

[3]  Kumpati S. Narendra,et al.  Identification and control of dynamical systems using neural networks , 1990, IEEE Trans. Neural Networks.

[4]  Ah Chung Tsoi,et al.  Locally recurrent globally feedforward networks: a critical review of architectures , 1994, IEEE Trans. Neural Networks.

[5]  Rolf Isermann,et al.  Trends in the Application of Model Based Fault Detection and Diagnosis of Technical Processes , 1996 .

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

[7]  Christophe Combastel,et al.  A symbolic reasoning approach to fault detection and isolation applied to electrical machines , 1998, Proceedings of the 1998 IEEE International Conference on Control Applications (Cat. No.98CH36104).

[8]  S Z Qin,et al.  Comparison of four neural net learning methods for dynamic system identification , 1992, IEEE Trans. Neural Networks.

[9]  Rolf Isermann,et al.  On fuzzy logic applications for automatic control, supervision, and fault diagnosis , 1998, IEEE Trans. Syst. Man Cybern. Part A.

[10]  Jacky Montmain,et al.  Dynamic Model and Causal Knowledge-Based Fault Detection and Isolation , 1997 .

[11]  Peter Tiño,et al.  Learning long-term dependencies in NARX recurrent neural networks , 1996, IEEE Trans. Neural Networks.