Fault diagnosis of axlebox roller bearings of high speed rail vehicles based on empirical mode decomposition and machine learning

Abstract: Axlebox bearings are one of the most critical components of a rail vehicle with regard to safety. An axlebox bearing that breaks during operation can be dangerous for the passengers and expensive for the operator. In-service failure of axlebox bearings has been the cause of many catastrophic accidents. Thus, it is of utmost importance to predict bearing failures as early as possible. This will increase reliability and safety of the vehicle as well as reduce the vehicle maintenance cost. Monitoring of roller bearings is an active research eld, and many methods have been proposed by other researchers. Many of these methods employ complex algorithms to make the most use of the given measurements. The algorithms often lack interpretability and have high computational costs, making them dicult to employ in an on-board system. This thesis proposes an interpretable and transparent algorithm that predicts bearing damages with high accuracy. Meanwhile, it tries to retain interpretability as much as possible. The algorithm is based on Empirical Mode Decomposition (EMD) and Singular Value Decomposition (SVD). These two techniques extract essential and meaningful information from the axlebox accelerations. The algorithm is benchmarked on two benchmark datasets, and the results are compared to the respective literature. Then the algorithm is employed on the railway axlebox acceleration measurements that were taken on an axlebox test bench available at SWJTU. The proposed algorithm can be extended to incorporate additional measurements of dierent types, e.g. sound or temperature measurements. The incorporation of other types of measurements will improve the performance of the algorithm even further.