An object-oriented expert system for fault diagnosis in the ethylene distillation process

This paper presents a unified object-oriented methodology (methods, techniques, and tools) for building relatively complex knowledge-based software systems for diagnosis of industrial equipment. A Fault Diagnosis Expert System ( fdes) is developed as a prototype for locating the root causes of a set of abnormalities in the ethylene distillation process. The underlaying domain-related features of the methodology are the problem-solving method, diagnostic knowledge representation, and control strategy. The problem-solving method is based on diagnostic knowledge and an appropriate problem-solving structure. Diagnostic knowledge is derived from shallow knowledge and deep knowledge about the problem domain. The hierarchical problem-solving structure is created on the base of functional and structural considerations. This structure leads to the structured knowledge base. A two-level knowledge base is constructed for fdes. The system structure is built entirely using an object-oriented representation scheme. All the necessary declarative and procedural knowledge is embedded in objects. In addition, the production rules, which are bearers of heuristic knowledge, are combined with that scheme thanks to the unified programming environment used. The reasoning is based on a hypothesis-test strategy. A control strategy, in which the diagnostic direction is decided at top level, is adopted. The basic part of fdes is implemented using the object-oriented version of clips (C Language Integrated Production System). fdes has a friendly user interface written in C. Two case studies are briefly discussed as examples validating the system.