A case study for Fleet-wide semantic based predictive diagnostic
Résumé
Diagnosis is a critical activity in the PHM domain (Prognostics and Health Management) due to its impact on the downtime and on the global performances of a system. This activity becomes complex when dealing with large systems which are composed of multiple systems, subsystems and components of different technologies, different usages, etc. In order to ease diagnosis activities, this paper proposes to use a fleet-wide approach based on ontologies in order to capitalize knowledge and data to help decision makers to identify the causes of abnormal operations. In that sense, taking advantage of a fleet dimension implies to provide en-gineers more knowledge as well as relevant synthesis of information about the system behaviour. This paper presents a case-study concerning the occurrence of an abnormal situation for fuel engines in the marine do-main to illustrate how an ontology fleet-wide software application integrated in the KASEM e-maintenance platform facilitates diagnosis activities.