A Case based Reasoning System based on Domain Ontology for Fault Diagnosis of Steam Turbines

Industrial diagnosis is a domain where problems are recurrent and therefore previous documented solution can be successfully reused. Different methodologies may be implemented for a given diagnosis domain, one of the appropriate, appears to be Case-Based Reasoning (CBR). A CBR system is a combination of processes and knowledge called “knowledge containers“, that allows to preserve and to exploit previous experiences. Its reasoning power can be improved through the use of general knowledge about the domain in question. CBR systems combining case specific knowledge with general domain knowledge models are called knowledge intensive CBR (KI-CBR). The present work aims to develop a CBR application for fault diagnosis of steam turbines that integrates a domain knowledge modeling in an ontological form. This system is view as a KI-CBR system based on domain ontology, built around jCOLIBRI a well-known framework to design KI-CBR systems.