Fault diagnosis for chemical processes using weighted symptom model and pattern matching

가중증상모델과 패턴매칭을 이용한 화학공정의 이상진단

  • Published : 1997.10.01

Abstract

This paper presents a fault detection and diagnosis methodology based on weighted symptom model and pattern matching between the coming fault propagation trend and the simulated one. In the first step, backward chaining is used to find the possible cause candidates for the faults. The weighted symptom model is used to generate those candidates. The weight is determined from dynamic simulation. Using WSM, the methodology can generate the cause candidates and rank them according to the probability. Second, the fault propagation trends identified from the partial or complete sequence of measurements are compared with the standard fault propagation trends stored a priori. A pattern matching algorithm based on a number of triangular episodes is used to effectively match those trends. The standard trends have been generated using dynamic simulation and stored a priori. The proposed methodology has been illustrated using two case studies, and the results showed satisfactory diagnostic resolution.

References

  1. Computers Chem. Engng. v.20 Automatic construction of extended symptom-fault association from the signed dirgraph D. S. Nam;C. H. Han;C. H. Jeong;E. S. Yoon
  2. Proc. of 4th Int. Symp. Process Systems Engineering (PSE91) v.II Fault diagnosis strategies for chemical plants: A reviet of competing technologies W. R. Becraft;P. L. Guo;P. L. Lee;R. B. Newell
  3. AIChE Journal v.33 no.7 A rule-based approach to fault diagnosis using the signed directed graph M. A. Kramer;B. L. Palowitch
  4. Proc. Of 5th Int. Symp. Process Systems Engineering (PSE94) v.II Practical problems in application of failure diagnostic systems E. O'Hsima;H. Matsuyama
  5. Trans IChemE v.74 Fault detection and diagnosis using multivariate statisical techniques J. Zhang;E. B. Martin;A. H. J. Morris
  6. IFAC Workshop on Fault Detection and Safety on Chemical Plants Process failure detection and diagnosis using the tree model E. S. Yoon;J. H. Han
  7. Computers Chem Engng. v.14 Representation of process trends-Part I. A formal representation framework J. T. Y. Cheung;G. Stephanopoulos
  8. Computers Chem. Engng. v.17 A plant-wide industrial process control J. J. Downs;E. F. Vogel
  9. Computers Chem. Engng. v.19 Nonlinear modeling and state estimation for the Tennessee Eastman chailenge process N. I. Ricker;J. H. Lee