Data Piecewise Linear Approximation for Bearings Degradation Monitoring
Abstract
In this paper, we propose a method based on piecewise linear approximation (PLA) with segmented projection error (SPE) to reveal the underlying correlation structures and approximate multivariate time series. Based on this method we elaborate an indicator called vector of segmented projection error (VSPE) to characterize the bearings degradation using standard time domain standard features extracted from the vibration signal. The indicator VSPE monitors the evolution of the entire degradation process efficiently and provides real-time information on bearings degradation. We show the effectiveness of this new indicator using benchmark data. The results reveal the sensitive and monotonic character of the indicator VSPE according to the bearings degradation, which is promising for monitoring bearings on their lifespan.