An improved multi-scale branching convolutional neural network for rolling bearing fault diagnosis.
The vibration signals measured in practical engineering are usually complex and noisy, which brings challenges to fault diagnosis. In addition, industrial scenarios also put forward higher requirements for the accuracy and computational efficiency of diagnostic models. Aiming at these problems, an i...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Public Library of Science (PLoS)
2023-01-01
|
Series: | PLoS ONE |
Online Access: | https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0291353&type=printable |
_version_ | 1797682742712860672 |
---|---|
author | Meng Xu Yaowei Shi Minqiang Deng Yang Liu Xue Ding Aidong Deng |
author_facet | Meng Xu Yaowei Shi Minqiang Deng Yang Liu Xue Ding Aidong Deng |
author_sort | Meng Xu |
collection | DOAJ |
description | The vibration signals measured in practical engineering are usually complex and noisy, which brings challenges to fault diagnosis. In addition, industrial scenarios also put forward higher requirements for the accuracy and computational efficiency of diagnostic models. Aiming at these problems, an improved multiscale branching convolutional neural network is proposed for rolling bearing fault diagnosis. The proposed method first applies the multiscale feature learning strategy to extract rich and compelling fault information from diverse and complex vibration signals. Further, the lightweight dynamic separable convolution is elaborated and coupled into the feature extractor to "slim down" the model, reduce the computational loss on the one hand, and further improve the model's adaptive learning ability for different inputs hand. Extensive experiments indicate that the proposed method is significantly improved compared with existing multi-scale neural networks. |
first_indexed | 2024-03-12T00:05:16Z |
format | Article |
id | doaj.art-844a2a3178f64ee9b2923be4df618dd7 |
institution | Directory Open Access Journal |
issn | 1932-6203 |
language | English |
last_indexed | 2024-03-12T00:05:16Z |
publishDate | 2023-01-01 |
publisher | Public Library of Science (PLoS) |
record_format | Article |
series | PLoS ONE |
spelling | doaj.art-844a2a3178f64ee9b2923be4df618dd72023-09-17T05:31:04ZengPublic Library of Science (PLoS)PLoS ONE1932-62032023-01-01189e029135310.1371/journal.pone.0291353An improved multi-scale branching convolutional neural network for rolling bearing fault diagnosis.Meng XuYaowei ShiMinqiang DengYang LiuXue DingAidong DengThe vibration signals measured in practical engineering are usually complex and noisy, which brings challenges to fault diagnosis. In addition, industrial scenarios also put forward higher requirements for the accuracy and computational efficiency of diagnostic models. Aiming at these problems, an improved multiscale branching convolutional neural network is proposed for rolling bearing fault diagnosis. The proposed method first applies the multiscale feature learning strategy to extract rich and compelling fault information from diverse and complex vibration signals. Further, the lightweight dynamic separable convolution is elaborated and coupled into the feature extractor to "slim down" the model, reduce the computational loss on the one hand, and further improve the model's adaptive learning ability for different inputs hand. Extensive experiments indicate that the proposed method is significantly improved compared with existing multi-scale neural networks.https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0291353&type=printable |
spellingShingle | Meng Xu Yaowei Shi Minqiang Deng Yang Liu Xue Ding Aidong Deng An improved multi-scale branching convolutional neural network for rolling bearing fault diagnosis. PLoS ONE |
title | An improved multi-scale branching convolutional neural network for rolling bearing fault diagnosis. |
title_full | An improved multi-scale branching convolutional neural network for rolling bearing fault diagnosis. |
title_fullStr | An improved multi-scale branching convolutional neural network for rolling bearing fault diagnosis. |
title_full_unstemmed | An improved multi-scale branching convolutional neural network for rolling bearing fault diagnosis. |
title_short | An improved multi-scale branching convolutional neural network for rolling bearing fault diagnosis. |
title_sort | improved multi scale branching convolutional neural network for rolling bearing fault diagnosis |
url | https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0291353&type=printable |
work_keys_str_mv | AT mengxu animprovedmultiscalebranchingconvolutionalneuralnetworkforrollingbearingfaultdiagnosis AT yaoweishi animprovedmultiscalebranchingconvolutionalneuralnetworkforrollingbearingfaultdiagnosis AT minqiangdeng animprovedmultiscalebranchingconvolutionalneuralnetworkforrollingbearingfaultdiagnosis AT yangliu animprovedmultiscalebranchingconvolutionalneuralnetworkforrollingbearingfaultdiagnosis AT xueding animprovedmultiscalebranchingconvolutionalneuralnetworkforrollingbearingfaultdiagnosis AT aidongdeng animprovedmultiscalebranchingconvolutionalneuralnetworkforrollingbearingfaultdiagnosis AT mengxu improvedmultiscalebranchingconvolutionalneuralnetworkforrollingbearingfaultdiagnosis AT yaoweishi improvedmultiscalebranchingconvolutionalneuralnetworkforrollingbearingfaultdiagnosis AT minqiangdeng improvedmultiscalebranchingconvolutionalneuralnetworkforrollingbearingfaultdiagnosis AT yangliu improvedmultiscalebranchingconvolutionalneuralnetworkforrollingbearingfaultdiagnosis AT xueding improvedmultiscalebranchingconvolutionalneuralnetworkforrollingbearingfaultdiagnosis AT aidongdeng improvedmultiscalebranchingconvolutionalneuralnetworkforrollingbearingfaultdiagnosis |