Journal of the Korean Institute of Intelligent Systems (한국지능시스템학회논문지)

Korean Institute of Intelligent Systems (한국지능시스템학회)
권호 표지
DOI QR코드

DOI QR Code

Neural Networks-based Statistical Approach for Fault Diagnosis in Nonlinear Systems

비선형시스템의 고장진단을 위한 신경회로망 기반 통계적접근법

  • 이인수 (상주대학교 전자전기공학부) ;
  • 조원철 (경상북도 도립 경도대학 컴퓨터전자과)
  • Published : 2002.12.01
Download PDF
⟨ Previous Next ⟩

Abstract

This paper presents a fault diagnosis method using neural network-based multi-fault models and statistical method to detect and isolate faults in nonlinear systems. In the proposed method, faults are detected when the errors between the system output and the neural network nominal system output cross a predetermined threshold. Once a fault in the system is detected, the fault classifier statistically isolates the fault by using the error between each neural network-based fault model output and the system output. From the computer simulation results, it is verified that the proposed fault diagonal method can be performed successfully to detect and isolate faults in a nonlinear system.

본 논문에서는 비선형시스템에서 발생한 고장을 감지하고 분류하기 위해 신경회로망기반 다중고장모델과 통계적기법에 의한 고장진단 방법을 제안한다. 제안한 알고리듬에서는 시스템의 출력과 신경회로망 공칭모델 출력 사이의 오차가 미리 설정한 문턱 값을 넘으면 고장을 감지한다. 고장이 감지되면 고장분류기에서는 각 신경회로망 고장모델 출력과 시스템 출력 사이의 오차를 이용하여 통계적 기법으로 고장을 분류한다. 컴퓨터 시뮬레이션 결과로부터 제안한 고장진단방법이 비선형 시스템에서의 고장감지 및 분류문제에 잘 적용됨을 알 수 있다.

Keywords

References

  1. ASME J. Eng. for Industry v.115 A failure isolation strategy for thermofluid system diagnostics J. Wagner;R. Shoureshi https://doi.org/10.1115/1.2901790
  2. Automatica v.20 no.4 Process fault detection based on modeling and estimation methods-a survey R. Isermann https://doi.org/10.1016/0005-1098(84)90098-0
  3. IEEE Contr. Syst. Mag. Learning methodology for failure detection and accommodation M. M. Polycarpou;A. T. Vemuri
  4. Computers Chem. Engng. v.12 no.9 Artificial neural network models of knowledge representation in chemical engineering J. C. Hoskins;D. M. Himmelblau https://doi.org/10.1016/0098-1354(88)87015-7
  5. Computers Chem. Engng. v.14 no.7 Process fault detection and diagnosis using neural networks-steady state processes V. Venkatasubramanian;R. Vaidyanathan;Y. Yamamoto https://doi.org/10.1016/0098-1354(90)87081-Y
  6. IEEE Trans. Nuclear Science v.37 no.2 Sensor validation for power plants using adaptive back propagation neural network E. Eryurek;B. R. Upadhyaya https://doi.org/10.1109/23.106752
  7. IEEE Trans. Syst., Man and Cybern. v.21 no.4 Neural networks in process fault diagnosis T. Sorsa;H. N. Koivo;H. Koivisto https://doi.org/10.1109/21.108299
  8. Computers Chem. Engng. v.14 no.12 Diagnosis using backpropagation neural networks-analysis and criticism M. A. Kramer;J. A. Leonard https://doi.org/10.1016/0098-1354(90)80015-4
  9. IEEE Trans. Neural Networks v.5 no.6 Hopfield/ART-1 neural network-based fault detection and isolation A. Srinivasan;C. Batur https://doi.org/10.1109/72.329685
  10. 대한전자공학회 논문집 v.39-S no.1 신경회로망기반 다중고장모델에 의한 비선형시스템의 고장감지와 분류 이인수
  11. IEEE Trans. Aerosp. Electron. Syst. v.28 M-ary sequential hypothesis tests for automatic target recognition I. Jouny;F. D. Garber https://doi.org/10.1109/7.144573
  12. Parallel distributed processing: explorations in the microstructure of cognition v.1 D. E. Rumelhart;J. L. McClelland
  13. Time Series Analysis J. D. Cryer
  14. Estimation Theory with Applications to Communications and Control A. P. Sage;J. L. Melsa