An Outlier Cleaning Based Adaptive Recognition Method for Degradation Stage of Bearings

Accurate identification of the degradation stage is key to the prediction of the remaining useful life (RUL) of bearings. The 3σ method is commonly used to identify the degradation point. However, the recognition accuracy is seriously disturbed by the random outliers in the normal stage. Therefore, this paper proposes an adaptive recognition method for the degradation stage based on outlier cleaning. Firstly, an improved multi-scale kernel regression outlier detection method is adopted to roughly search the abnormal signal segments. Then, a method for the accurate locating of the start and end points of abnormal impulses is established. After that, indexes are constructed for screening abnormal segments and an iterative strategy is proposed to achieve an accurate and efficient removal of abnormal impulses. After outlier cleaning, the 3σ approach is used to set the degradation warning threshold adaptively to realize the degradation stage recognition of the bearings. The PHM 2012 rotating machinery dataset is used to verify the effectiveness of the proposed method. Experimental results show that the proposed method can accurately locate and remove the outliers adaptively. After the cleaning of the outliers, the identification of the degradation stage is no longer disturbed by the selection of the reference signal of the normal stage and the robustness and the accuracy of the degradation stage identification have been improved significantly.