Development of operation-aided system for chemical processes

Abstract This paper presents the development of a knowledge-based operation-aided system for polypropylene process. The important part of this system is the search for the root cause of faults by detecting and analyzing the symptoms which occurred in the process in the case of abnormal situations. In this system, an artificial neural network which is able to handle pattern recognition is used for qualitative interpretation of sensor data and generating symptoms. For effective fault diagnosis, two causal effect models which are based on SDG (Signed Directed Graph) are developed. One model, RCED (Reduced Cause Effect Digraph) uses only the measurable sensor data of the process and is constructed off-line and stored in the knowledge base of the system. The other model, PGTT (Pattern Graph Through Time) is generated in the real-time mode during the diagnosis period. It is generated from symptoms—status and/or tendency change—and can handle dynamic state effectively. By implementing the developed qualitative interpretation method and two causal effect graph models, the operation-aided system for the polypropylene process, FINDS/PP (Fault Isolation aNd Detection System/PolyPropylene) was developed. This system was developed with the expert system tool G2 and showed good results.

[1]  DvorakDaniel,et al.  Process Monitoring and Diagnosis , 1991 .

[2]  Chung C. Chang,et al.  On-line fault diagnosis using the signed directed graph , 1990 .

[3]  Venkat Venkatasubramanian,et al.  Representing bounded fault classes using neural networks with ellipsoidal activation functions , 1993 .

[4]  Satoshi Miyazaki,et al.  Fault location using digraph and inverse direction search with application , 1983, Autom..

[5]  Bhavik R. Bakshi,et al.  Representation of process trends—III. Multiscale extraction of trends from process data , 1994 .

[6]  James R. Whiteley,et al.  A similarity-based approach to interpretation of sensor data using adaptive resonance theory , 1994 .

[7]  Mark A. Kramer,et al.  A rule‐based approach to fault diagnosis using the signed directed graph , 1987 .

[8]  William L. Luyben,et al.  Process Modeling, Simulation and Control for Chemical Engineers , 1973 .

[9]  Eugene L. Grant,et al.  Statistical Quality Control , 1946 .

[10]  J. R. Whiteley,et al.  Knowledge-based interpretation of sensor patterns , 1992 .

[11]  Cheng-Ching Yu,et al.  Fault diagnosis based on qualitative/quantitative process knowledge , 1991 .

[12]  Bhavik R. Bakshi,et al.  Representation of process trends—IV. Induction of real-time patterns from operating data for diagnosis and supervisory control , 1994 .

[13]  G. Stephanopoulos,et al.  Representation of process trends—Part I. A formal representation framework , 1990 .

[14]  Eiji O'Shima,et al.  A graphical approach to cause and effect analysis of chemical processing systems , 1980 .

[15]  M. Iri,et al.  An algorithm for diagnosis of system failures in the chemical process , 1979 .

[16]  Robert E. Tarjan,et al.  Depth-First Search and Linear Graph Algorithms , 1972, SIAM J. Comput..

[17]  Eiji O'Shima,et al.  An improved algorithm for diagnosis of system failures in the chemical process , 1985 .

[18]  G. Stephanopoulos,et al.  Representation of process trends—Part II. The problem of scale and qualitative scaling , 1990 .