Real-time remaining useful life kernel density estimation considering dynamic transition of degradation states

Abstract

The accurate prediction of remaining useful life is a significant issue for ensuring the reliable operation of the system. An adaptive kernel density estimation model for real-time remaining useful life is established considering the dynamic transition of degraded states. Firstly, a time series density peak clustering algorithm suitable for real-time manifold data clustering is proposed, which can efficiently, quickly, and accurately cluster data in different degradation states. Then, different degradation state patterns according to clustering results can be divided. Moreover, the smoothing parameters can be adaptively updated according to the sample density under different degradation modes and an adaptive kernel density remaining useful life estimation model is established. The test of the gearbox verifies the necessity and accuracy of the proposed model by comparison with the remaining useful life predictions of kernel density estimation without considering degraded state transitions.