Bearing remaining useful life prediction under starved lubricating condition using time domain acoustic emission signal processing
作者:
Highlights:
• The remaining useful life (RUL) of bearing using signal processing method is studied.
• Improved Distance Evaluation (IDE) method is used for feature dimensionality reduction.
• K-Nearest Neighbors (KNN) algorithm is used for healthy and faulty bearing classification.
• The results show that the IDE method enables natural fault detection in bearings accurately.
• The results show that kurtosis, FM4, k factor, energy, and peak are the best features.
摘要
•The remaining useful life (RUL) of bearing using signal processing method is studied.•Improved Distance Evaluation (IDE) method is used for feature dimensionality reduction.•K-Nearest Neighbors (KNN) algorithm is used for healthy and faulty bearing classification.•The results show that the IDE method enables natural fault detection in bearings accurately.•The results show that kurtosis, FM4, k factor, energy, and peak are the best features.
论文关键词:Acoustic emission,Angular contact bearing,Condition monitoring,K-nearest neighbor,IDE method
论文评审过程:Received 6 March 2020, Revised 24 May 2020, Accepted 27 November 2020, Available online 5 December 2020, Version of Record 11 December 2020.
论文官网地址:https://doi.org/10.1016/j.eswa.2020.114391