Expert system dedicated to condition-based maintenance based on a knowledge graph approach: Application to an aeronautic system

Condition Based Maintenance (CBM) has become the focus of many research topics over past decades. This is mostly related to development new machine learning algorithms and ever increasing capacity collect data allowing failures be detected system’s remaining lifetime estimated while requiring few or no expert knowledge. However, current based CBM solutions have limitations. They require an extensive relevant set train on are performed at component level, not system-wide. Conversely, Expert Systems (ES) do these restrictions but should used systems with available knowledge currently suffering from efficiency, scalability applicability limits. In this paper, ES solution for heterogeneous information network will presented address issues modern ES. An application aircraft system as case study illustrate process performance anomaly detection diagnostics.