Steam turbine diagnostic system based on a domain ontology implemented using J2EE technology

Abstract

This paper describes the design and the implementation of an aided diagnostic system based on a domain ontology and an expert system. A mono ontology obtained from multiple CCOs (Canonical Conceptual Ontologies) constitutes the knowledge base of the Expert System. The NCCO (Non Canonical Conceptual Ontology) are defined and used for realising inter-CCO mapping and to express the relationships between the COO. An expert system JESS (Java Expert System Shell) is integrated with the ontology. Knowledge inference is then possible to solve maintenance cases by given adequate diagnoses to given symptoms. The second aspect of the paper focuses on the possible enhancement and evolution of the developed ontology in order to take into account new maintenance cases. The complete system is developed following a J2EE (Java 2 Enterprise Edition) architecture.