Multiple faults diagnosis of a linear system using ART2 neural networks

ART2 신경회로망을 이용한 선형 시스템의 다중고장진단

  • 이인수 (상주산업대학교 전자 전기공학과) ;
  • 신필재 (LG전자) ;
  • 전기준 (경북대학교 전자.전기공학부, 제어계측신기술연구센터)
  • Published : 1997.06.01

Abstract

In this paper, we propose a fault diagnosis algorithm to detect and isolate multiple faults in a system. The proposed fault diagnosis algorithm is based on a multiple fault classifier which consists of two ART2 NN(adaptive resonance theory2 neural network) modules and the algorithm is composed of three main parts - parameter estimation, fault detection and isolation. When a change in the system occurs, estimated parameters go through a transition zone in which residuals between the system output and the estimated output cross the threshold, and in this zone, estimated parameters are transferred to the multiple faults classifier for fault isolation. From the computer simulation results, it is verified that when the proposed diagnosis algorithm is performed successfully, it detects and isolates faults in the position control system of a DC motor.

References

  1. Int. J. Computer Integrated Manufacturing v.5 no.4&5 A review and implementation of contingency managementin flexible manufacturing systems Y.S. Wong(et al.)
  2. Automatica v.25 no.6 Performance monitoring in expert control systems R. Doraiswami;J. Jiang
  3. Automatica v.29 no.4 Application of artificial neural networks in process fault diagnosis T. Sorsa;H.N. Koivo
  4. IEEE Trans. Automat. Contr. v.AC-29 no.7 Analytical redundary and the design of robust failure detection systems E.Y. Chow;A.S. Willsky
  5. Fault Diagnosis in Dynamic Systems Theory and Application R. Patton;P. Frank;R. Clark
  6. IEEE Trans. Automat. Contr. v.AC-31 no.9 A geometric approach to the synthesis of failure detection filters M.A. Massoumnia
  7. Pattern Recognition v.27 no.1 Hidden markov models for fault detection in dynamic systems P. Smyth
  8. Automatica v.29 no.4 Fault diagnosis of machines via parameter estimation and knowledge processing R. Isermann
  9. Proc. of American Control Conference(ACC) Model based fault detection and diagnosis methods R. Isermann
  10. Automatica v.20 no.4 Process fault detection based on modeling and estimation methods- asurvey R. Isermann
  11. Journal of Dynamic systems, Measurement, and Control. v.113 Process fault diagnosis for fault diagnosis with parameter estimation R. Isermann ;B. Freyermuth
  12. IEEE Trans. Neural Networks v.5 no.6 Hopfield/ART-1 neural network-based fault detection and isolation A. Srinivasan;C. Batur
  13. IEEE Control System Magazine Learning methodology for failure detection and accommodation M.M. Polycarpou;A.T. Vemuri
  14. Digital Neural Networks S.Y. Kung
  15. Adaptive Pattern Recognition and Neural Networks Y.H. Pao
  16. Theory and Practice of Recursive Identification L. Ljung;T. Soderstrom