Remaining useful life prediction of the ball screw system based on weighted Mahalanobis distance and an exponential model

The ball screw system is one of the crucial components of machine tools and predicting its remaining useful life (RUL) can enhance the reliability and safety of the entire machine tool and reduce maintenance costs. Although quite a few techniques have been developed for the fault diagnosis of the ball screw system, forecasting the RUL of the ball screw system is a remaining challenge. To make up for this deficiency, we present a model-based method to predict the RUL of the ball screw system, which consists of two parts: health indicator (HI) construction and RUL prediction. First, we develop a novel HI, weighted Mahalanobis distance (WDMD). Unlike the Mahalanobis distance (MD), which is constructed by fusing original features directly, the WDMD is formed with some selected features only, and the features are weighted before integration. Second, an exponential model is developed to describe the degradation path of the ball screw system. Then, the particle filtering algorithm is employed to combine the WDMD and the degradation model for state estimation and RUL prediction. The proposed approach is verified by a dataset obtained from an experimental system designed for accelerated life tests of the ball screw system. The results show that the WDMD has a more apparent deterioration trend than the MD and the proposed exponential model performs better than both the linear model and the nonlinear model in RUL prediction.