Korean Chemical Engineering Research

The Korean Institute of Chemical Engineers (한국화학공학회)
권호 표지

A Fault Diagnostic Expert System Using the Symptom Tree Model

증상 트리 모델을 이용한 이상 진단 전문가 시스템

Kim, Chul-Jin;Oh, Jeon-Keun;Yoon, En-Sup
김철진;오전근;윤인섭

  • Published : 1990.08.31

⟨ Previous Next ⟩

Abstract

The Symptom Tree Model(STM) based on the Fault Tree Model(FTM)is modified to be appropriate in fault diagnosis and to be applied to large scale processes. Knowledge representation hybridizing frames and production rules is presented. It is used to implement knowledge base for fault diagnostic expert system with the STM of qualitative model for chemical processes. In order to perform fault diagnosis by using symptom trees on the real-time basis, a diagnostic strategy with hypothesis and test is presented. In order to apply the presented knowledge representation method and diagnostic strategy to naphtha furnace process, EXFAST(EXpert system for FAult diagnosis using Symptom Tree model)is developed. This developed EXFAST is tested and showed successful results. It is found that the STM is quite adequate as a qualitative knowledge model in fault diagnostic expert systems for chemical processes.

이상 트리 모델(fault tree model)을 기반으로 하는 증상 트리 모델(symptom tree model)을 이상진단에 적합하도록 개조하였으며, 큰 공정에 적용 가능하도록 하였다. 또 공정의 정상적인 모델인 증상 트리를 전문가 시스템에 지식 기반(knowledge base)으로 사용하기 위하여, frames과 production rules을 적절히 혼합한 형태의 지식 표현 방법을 제시하였다. 이와 같은 지식을 적절히 이용하여 가설과 검증(hypothesis and test)에 의한 진단 전략을 제시하였다. 이와 같이 제시된 증상 트리의 지식 표현 방법과 전단 전략을 실제 공정인 나프타 분해로에 적용하여 이상 진단 전문가 시스템인 EXFAST를 개발하였다. 개발된 EXFAST를 실제 사고 사례와 가상 사고 사례에 대하여 수행시켜 본 결과, 이상 원인을 초기에 진단할 수 있는 것을 확인하였다. 이로써 공정의 정성적인 모델인 증상 트리가 이상 진단 전문가의 지식으로 사용하기에 적합함을 알 수 있었다.

Keywords

References

  1. AIChE J. v.33 no.7 A Rule-Based Approach to Fault Diagnosis using the Signed Directed Graph Kramer, M.A.;Palowitch, B.L.
  2. AIChE J. v.33 no.1 Malfunction Diagnosis using Quantitative Models with Non-Boolean Reasoning in Expert Systems Kramer, M.A.
  3. Comput. Chem. Engng. v.11 no.2 Model-Based Reasoning in Diagnostic Expert Systems for Chemical Process Plants Rich, S.H.;Venkatasubramanian, V.
  4. Comput. Chem. Engng. v.12 no.1 An Expert System Approach to Malfunction Diagnosis in Chemical Plants Shum, S.K.;Davis, J.F.;Punch, W.F.;Chandrasekaran, B.
  5. Comput. Chem. Engng. v.4 Real-Time Analysis of Process Plant Alarms using a Mini-Computer Andow, P.K.
  6. Comput. Chem. Engng. v.7 no.6 Process Computer Alarm and Disturbance Analysis: Review of the State of the Art Lees, F.P.
  7. The Chemical Engineering Journal v.29 Application of Expert System Techniques to Fault Diagnosis Kumamoto, H.;Ikenchi, K.;Inoue, K.
  8. Rule-Based Expert Systems Buchanan, B.G.;Shortliffe, E.H.
  9. Expert Systems for the Technical Professional Wolfgram, D.D.;Dear, T.J.;Galbraith, C.S.
  10. Comput. Chem. Engng. v.12 no.9;10 A Structured Framework for Efficient Problem Solving in Diagnostic Expert Systems Ramesh, T.S.;Shum, S.K.;Davis, J.F.
  11. Comput. Chem. Engng. v.12 no.9 Artificial Neural Network Models for Knowledge Representation in Chemical Engineering Hoskins, J.C.;Himmelbrau, D.M.
  12. Process Diagnostics using the Symptom Sub-Tree Model Yoon, E.S.;Evans, L.B.;Tooney, T.B.
  13. Comput. Chem. Engng. v.12 no.9;10 An Object-Oriented Two-Tier Architecture for Integrating Compiled and Deep-Level Knowledge for Process Diagnosis Venkatasubramanian, V.;Rich, S.H.
  14. Introduction to Artificial Intelligence Charniak, E.;McDermott, D.
  15. Principles of Artificial Intelligence Nilson, N.J.
  16. Artifcial Intelligence Winston, P.H.
  17. A Study on the Knowledge-Based Expert System for Cement Process Control and Diagnosis Han, J.H.;Yoon, E.S.
  18. Fault Tree Analysis-Concepts and Technique, NATO Adv. Study Inst. on Generic Techniques in Systems Reliability Assessment Fussell, J.B.
  19. AIChE Annual Meeting no.26C A Real-Time Operation Aiding System of Naphtha Furnaces Oh, Jeon-Keun;Yoon, En-Sup
  20. 공정 사고 분석 주식회사 유공
  21. Unit 사고 분석 주식회사 유공
  22. 사고 사례 분석 주식회사 유공