Condition monitoring data based remaining useful life prediction of stochastic degradation systems
Date:
Modern industrial equipments are in the rapid development towards enlargement, complication, and high precision, which poses challenges for ensuring the operating safety. As a key technology to assess system health, RUL prediction is capable of providing effective information for the formulation of maintenance strategy, with the reduction of economic loss caused by faults or anomalies accordingly. Subject to the stochastic uncertainty of failure mechanism and environmental interaction, the temporal correlation of degradation among whole life cycle of the system cannot be ignored. Based on the non-Markovian theoretical framework, we conduct some researches with regard to data-driven fractional degradation process modeling and RUL prediction.