Design of a novel knowledge-based fault detection and isolation scheme

In this paper, a real-time fault detection and isolation (FDI) scheme for dynamical systems is developed, by integrating the signal processing technique with neural network design. Wavelet analysis is applied to capture the fault-induced transients of the measured signals in real-time, and the decomposed signals are pre-processed to extract details about a fault. A Regional Self-Organizing feature Map (R-SOM) neural network is synthesized to classify the fault types. The R-SOM neural network adopts two regions adjustment in the learning algorithm, thus it has high precision in clustering and matching, especially when the noise, disturbance and other uncertainties exist in the systems. As a result, the proposed FDI scheme is robust and accurate. The design is implemented on a stirred tank system and satisfactory online testing results are obtained.

[1]  Hong Guo,et al.  Automotive signal diagnostics using wavelets and machine learning , 2000, IEEE Trans. Veh. Technol..

[2]  Antonio Pietrosanto,et al.  An advanced neural-network-based instrument fault detection and isolation scheme , 1998, IEEE Trans. Instrum. Meas..

[3]  R. Burnett,et al.  The application of modern signal processing techniques to rotor fault detection and location within three phase induction motors , 1995, Proceedings of 1995 IEEE Instrumentation and Measurement Technology Conference - IMTC '95.

[4]  Kenneth A. Loparo,et al.  A neural-network approach to fault detection and diagnosis in industrial processes , 1997, IEEE Trans. Control. Syst. Technol..

[5]  Mu-Chun Su,et al.  Fast self-organizing feature map algorithm , 2000, IEEE Trans. Neural Networks Learn. Syst..

[6]  S. Altug,et al.  Comparative analysis of fuzzy inference systems implemented on neural structures , 1997, Proceedings of International Conference on Neural Networks (ICNN'97).

[7]  S. Mallat.  A wavelet tour of signal processing , 1998 .

[8]  Alan S. Morris,et al.  A fuzzy expert system for fault detection in statistical process control of industrial processes , 2000, IEEE Trans. Syst. Man Cybern. Part C.

[9]  Ingrid Daubechies,et al.  The wavelet transform, time-frequency localization and signal analysis , 1990, IEEE Trans. Inf. Theory.

[10]  P. Vega,et al.  A neural networks based approach for fault detection and diagnosis: application to a real process , 1995, Proceedings of International Conference on Control Applications.

[11]  A. Willsky,et al.  Analytical redundancy and the design of robust failure detection systems , 1984 .

[12]  P. Balle,et al.  Fault detection and isolation for nonlinear processes based on local linear fuzzy models and parameter estimation , 1998, Proceedings of the 1998 American Control Conference. ACC (IEEE Cat. No.98CH36207).

[13]  M. Borairi,et al.  Actuator and sensor fault diagnosis of nonlinear dynamic systems via genetic neural networks and adaptive parameter estimation technique , 1998, Proceedings of the 1998 IEEE International Conference on Control Applications (Cat. No.98CH36104).

[14]  Fiorenzo Filippetti,et al.  Recent developments of induction motor drives fault diagnosis using AI techniques , 2000, IEEE Trans. Ind. Electron..

[15]  P.M. Frank,et al.  Fault detection and isolation in technical processes with neural networks , 1995, Proceedings of 1995 34th IEEE Conference on Decision and Control.

[16]  Jorge L. Aravena,et al.  A modular methodology for fast fault detection and classification in power systems , 1998, IEEE Trans. Control. Syst. Technol..

[17]  Teuvo Kohonen,et al.  Self-Organizing Maps , 2010 .

[18]  Janos Gertler,et al.  Fault detection and diagnosis in engineering systems , 1998 .

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

[20]  Esa Alhoniemi,et al.  Clustering of the self-organizing map , 2000, IEEE Trans. Neural Networks Learn. Syst..