Abstract Though many good methodologies for process diagnosis and abnormal situation management have been developed for the last two decades, there is no single panacea that always shows better performance over all kinds of diagnostic problems. In this paper, a framework of message-passing, cooperative, intelligent diagnostic agents is presented for cooperative problem solving of on-line fault diagnosis. The diagnostic agents in charge of each process functional perform local diagnoses in parallel; exchange related information with other diagnostic agents (possible to include (mobile) business agents); and cooperatively solve the global diagnostic problem of the whole process plant or business units just like human experts would do. For their better sharing and exchanging of process knowledge and information, we also suggest a way of remodeling processes and protocols, taking into account semantic abstracts of process information and data. The benefits of the suggested multi-agents-based approach are demonstrated by the implementations for solving the diagnostic problems of various chemical processes.
[1]
Timo Sorsa,et al.
Neural networks in process fault diagnosis
,
1991,
IEEE Trans. Syst. Man Cybern..
[2]
David Mautner Himmelblau,et al.
Fault detection and diagnosis in chemical and petrochemical processes
,
1978
.
[3]
Mark A. Kramer,et al.
A rule‐based approach to fault diagnosis using the signed directed graph
,
1987
.
[4]
Michael R. Genesereth,et al.
Software agents
,
1994,
CACM.
[5]
Tetsuo Fuchino,et al.
A KQML multi-agent environment for concurrent process engineering
,
1999
.
[6]
Vincenzo Loia,et al.
A Distributed Approach for Multiple Model Diagnosis of Physical Systems
,
1997,
Inf. Sci..
[7]
Munindar P. Singh,et al.
Readings in agents
,
1997
.
[8]
Dongil Shin,et al.
Cooperative problem solving in diagnostic agents for chemical processes
,
2000
.