Fault prognostic of bearings by using support vector data description

This paper presents a method for fault prognostic of bearings based on Principal Component Analysis (PCA) and Support Vector Data Description (SVDD). The purpose of the paper is to transform the monitoring vibration signals into features that can be used to track the health condition of bearings and to estimate their remaining useful life. PCA is used to reduce the dimensionality of original vibration features by removing the redundant ones. SVDD is a pattern recognition method based on structural risk minimization principles. In this contribution, the SVDD is used to fit the trained data to a hypersphere such that its radius can be used as a health indicator. The proposed method is then applied on real bearing degradation performed on an accelerated life test. The experimental results show that the health indicator reflects the bearing's degradation.