Novel hybrid representation of knowledge in the expert system for real-time faults diagnosis

Abstract

This paper presents the development and implementation of an expert system for real-time fault diagnosis of chemical processes. The expert system is applied as a real-time computer aided decision support system, providing operation suggestions to help field operators when abnormal situations occur. Representation of knowledge, structure of the knowledge base, and access to expertise are technically considered. Industrial application indicates that the expert system works efficiently and promptly.