Research and implementation of an on-line fault diagnosis expert system for the chemical process

An expert system for on-line fault diagnosis of the lubricating oil refining process is presented. Design of the expert system structure, the knowledge base, and the inference machine are discussed in detail. A new strategy for conflict resolution of knowledge - the sorting strategy of antecedents and a selection strategy of knowledge rules in the memory knowledge base are proposed. Knowledge acquisition mechanism is discussed in the work, while knowledge verification is carried out based on the directed graph approach. The diagnose system has been developed for an industrial lubricating oil refining process. The system responds with the process faults promptly and satisfies requirement of the production.