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

• Published in: IEEE sensors journal Vol. 23; no. 3; pp. 2443 - 2455
• Main Authors: Mi, Junpeng, Hou, Yaochun, He, Weiting, He, Chengchi, Zhao, Huanpeng, Huang, Wenjun
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.02.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Anomalies; Anomaly detection; Bearing strength; Center of gravity; Datasets; Degradation; extended isolated forest (EIF); False alarms; Fault detection; Kurtosis; Machinery; Monitoring; nonparametric cumulative sum (NCUSUM); Nonparametric statistics; Probability distribution; Roller bearings; rolling bearing; Rolling bearings; Sequences; weighted dynamic time warping barycenter averaging (WDBA)

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 du...