Conditioned-Based Maintenance at USC - Part I:Integration of Maintenance Management Systems and Health Monitoring Systems through Historical Data Investigation

摘要

Maintenance Management Systems (MMS) are the core of traditional maintenance record-keeping practices and often facilitate the usage of textual descriptions of faults and actions performed on a vehicle. Recently developed Health and Usage Monitoring Systems (HUMS) are capable of directly monitoring vehicle component parameters; however, attempts to link observed MMS events to HUMS sensor measurements have been fairly limited in their approach and scalability. A new theoretical process for integrating the two disparate data types is proposed. This procedure implements a relational database which tags events from both data sets with location, severity, and rarity parameters. Metadata is extracted from the MMS textual descriptions using a natural language processor (NLP), and HUMS records are processed using simpler statistical analyses. The results and benefits of a full MMS and HUMS integration are predicted and evaluated.