Reliable Fault Diagnosis of Rolling Bearing Based on Ensemble Modified Deep Metric Learning

Abstract

A novel ensemble Yu’s norm-based deep metric learning (DMLYu) is proposed to diagnose the fault of rolling bearing in this paper, which can diagnose the fault classes through the information fusion method that combines the different diagnosis results produced by several Yu’s norm-based deep metric learning models with different scale signals. The suggested method is composed of three steps: firstly the vibration signal is decomposed into multiple IMF components by the EEMD method, then these IMF components are input into the DMLYu models which is called the modified deep metric learning model based on Yu’s norm-based similarity measure, respectively, to extract the feature parameters to diagnose the fault of rolling bearings from the different scales, and finally the final diagnosis decision is made by fusion strategy based on Bayesian belief method (BBM). At last, through a multifaceted diagnosis test of rolling bearing on different datasets, the effectiveness of the proposed ensemble DMLYu based on BBM is verified, and the superiority of the proposed diagnosis method is validated by comparing its diagnosis accuracy and generalization with DMLYu based on voting method and the individual DMLYu model.