A Nonparametric Cumulative Sum-Based Fault Detection Method for Rolling Bearings Using High-Level Extended Isolated Forest

As an advanced anomaly detection method, extended isolated forest (EIF) has great potential for use in bearings. A low-dimensional data transformation method based on EIF with high extension level and an early fault detection strategy for rolling bearings based on feature combination are proposed due to the limitation of EIF extension level on low-dimensional data. First, a preliminary sequence base is generated through sliding windows, and the sequences related to the number of transformed dimensions are selected based on the dynamic time warped (DTW) distance of the original sequence to perform weighted DTW barycenter averaging (WDBA), which enables preprocessing of the maximum extension level of EIF. Then, to realize early fault detection of rolling bearings, the nonparametric cumulative sum (NCUSUM) algorithm is used to design a joint threshold discrimination scheme for root mean square (rms) and kurtosis of the new and original sequences. We tested the algorithm on fault simulation using FEMTO-ST and XJTU-SY bearing datasets. The results show that WDBA-EIF algorithm can better remove uncorrelated noise from time series at high extension level. Compared with several anomaly detection methods, under 60% datasets, it has the best detection result of an early weak anomaly in the running process of rolling bearings and has a low false alarm rate.