Use of Artificial Intelligence Methods for Advanced Bearing Health Diagnostics and Prognostics

Prognostics is the ability to predict the condition of a piece of equipment at any stage during its useful life. It is the cornerstone of Prognostics Health Management (PHM), major goals of which are efficient maintenance and logistical practices, and optimized mission or equipment use and effectiveness. PHM will be achieved through monitoring a range of equipment sub-systems and combining the information to predict how and when the equipment will fail, with sufficient time for action or planning. This paper describes ongoing research by the University of Southampton and GE Aviation to investigate the intelligent processing of mechanical component health data to improve prognostics and diagnostics: In particular to evaluate the effectiveness of various sensing technologies (when applied to monitoring bearings), extending the window of time over which a failing component condition may be determined (prognosing) and identifying the nature of the failure (diagnosing).