Fault detection and quantitative assessment of wheel diameter difference based on ensemble adaptive tunable Q-factor wavelet transform and mixed kernel principal component analysis

Abstract

Abstract Tread wear is inevitable for railway vehicles. Because of the complicated railway condition, the wear rates of the two wheels of a wheelset are usually unequal, which leads to the wheel diameter difference (WDD). The WDD shortens the service life of the wheelset and deteriorates the dynamic performance of railway vehicles. Therefore, it has long been desired to monitor and quantify the WDD condition. However, influenced by the random irregularity, the effective vibration features induced by the WDD may be completely submerged in noise. In this paper, an adaptive TQWT decomposition method is proposed for denoise and feature enhancement. In this method, a new evaluation index is constructed and used to determine parameters. The influence of the WDD on the vibration of the wheelset can be more obvious after denoised by the adaptive TQWT decomposition. Mixed kernel principal component analysis is introduced into the condition monitoring and quantitative assessment of the WDD. By calculating the Hoteling’s T 2 and SPE statistics, control charts are employed to identify and assess the WDD conditions quantitatively in conjunction with the corresponding control limits. The effectiveness of the proposed method is validated by the simulation and experimental study. For the experimental datasets, the proposed method gives the average fault detection rate (FDR), false alarm rate (FAR), false alarm rate (PA) of 92.74%, 2.23%, 97.47% for the T 2 statistic and the average FDR, FAR, PA of 96.57%, 2.60%, 97.29% for the SPE statistic. The results show that the proposed method can effectively monitor the WDD conditions.