Hierarchical diagnosis of bearing faults using branch convolutional neural network considering noise interference and variable working conditions

作者：

Highlights：

• We propose a Hierarchical Branch based Convolutional Neural Network (HB-CNN) scheme for bearing faults diagnosis.

• We consider data with noise interference and under variable working conditions.

• We compare performance of our method with several salient models on two benchmark datasets.

• HB-CNN exhibits superior robustness and accuracy.

摘要

•We propose a Hierarchical Branch based Convolutional Neural Network (HB-CNN) scheme for bearing faults diagnosis.•We consider data with noise interference and under variable working conditions.•We compare performance of our method with several salient models on two benchmark datasets.•HB-CNN exhibits superior robustness and accuracy.

论文关键词：Convolutional neural network,Hierarchical branch structure,Intelligent bearing diagnosis,Noise interference,Variable working conditions

论文评审过程：Received 4 December 2020, Revised 6 June 2021, Accepted 9 August 2021, Available online 11 August 2021, Version of Record 19 August 2021.

论文官网地址：https://doi.org/10.1016/j.knosys.2021.107386