Mechanical equipment fault diagnosis method based on improved deep residual shrinkage network.
Fault diagnosis of mechanical equipment can effectively reduce property losses and casualties. Bearing vibration signals, as one of the effective sources of diagnostic information, are often overwhelmed by substantial environmental noise. To address this issue, we present a fault diagnosis method, C...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2024-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0307672 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850180139391909888 |
|---|---|
| author | Shaoming Qiu Liangyu Liu Yan Wang Xinchen Huang Bicong E Jingfeng Ye |
| author_facet | Shaoming Qiu Liangyu Liu Yan Wang Xinchen Huang Bicong E Jingfeng Ye |
| author_sort | Shaoming Qiu |
| collection | DOAJ |
| description | Fault diagnosis of mechanical equipment can effectively reduce property losses and casualties. Bearing vibration signals, as one of the effective sources of diagnostic information, are often overwhelmed by substantial environmental noise. To address this issue, we present a fault diagnosis method, CCSDRSN, which exhibits strong noise resistance. This method enhances the soft threshold function in the traditional deep residual shrinkage network, allowing it to extract useful information from the fault signal to the maximum extent, thus significantly improving diagnostic accuracy. Additionally, we have developed a novel activation function that can nonlinearly transform the time frequency map across multiple dimensions and the entire region. In pursuit of network optimization and parameter reduction, we have strategically incorporated depthwise separable convolutions, effectively replacing conventional convolutional layers. This architectural innovation streamlines the network. By verifying the effectiveness of the proposed method using Case Western Reserve University datasets, the results demonstrate that the proposed method not only possesses strong noise resistance in high noise environments but also achieves high diagnostic accuracy and good generalization performance under different load conditions. |
| format | Article |
| id | doaj-art-b8a11847ea8b4ca0a7a77ec3184897ba |
| institution | OA Journals |
| issn | 1932-6203 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj-art-b8a11847ea8b4ca0a7a77ec3184897ba2025-08-20T02:18:16ZengPublic Library of Science (PLoS)PLoS ONE1932-62032024-01-011910e030767210.1371/journal.pone.0307672Mechanical equipment fault diagnosis method based on improved deep residual shrinkage network.Shaoming QiuLiangyu LiuYan WangXinchen HuangBicong EJingfeng YeFault diagnosis of mechanical equipment can effectively reduce property losses and casualties. Bearing vibration signals, as one of the effective sources of diagnostic information, are often overwhelmed by substantial environmental noise. To address this issue, we present a fault diagnosis method, CCSDRSN, which exhibits strong noise resistance. This method enhances the soft threshold function in the traditional deep residual shrinkage network, allowing it to extract useful information from the fault signal to the maximum extent, thus significantly improving diagnostic accuracy. Additionally, we have developed a novel activation function that can nonlinearly transform the time frequency map across multiple dimensions and the entire region. In pursuit of network optimization and parameter reduction, we have strategically incorporated depthwise separable convolutions, effectively replacing conventional convolutional layers. This architectural innovation streamlines the network. By verifying the effectiveness of the proposed method using Case Western Reserve University datasets, the results demonstrate that the proposed method not only possesses strong noise resistance in high noise environments but also achieves high diagnostic accuracy and good generalization performance under different load conditions.https://doi.org/10.1371/journal.pone.0307672 |
| spellingShingle | Shaoming Qiu Liangyu Liu Yan Wang Xinchen Huang Bicong E Jingfeng Ye Mechanical equipment fault diagnosis method based on improved deep residual shrinkage network. PLoS ONE |
| title | Mechanical equipment fault diagnosis method based on improved deep residual shrinkage network. |
| title_full | Mechanical equipment fault diagnosis method based on improved deep residual shrinkage network. |
| title_fullStr | Mechanical equipment fault diagnosis method based on improved deep residual shrinkage network. |
| title_full_unstemmed | Mechanical equipment fault diagnosis method based on improved deep residual shrinkage network. |
| title_short | Mechanical equipment fault diagnosis method based on improved deep residual shrinkage network. |
| title_sort | mechanical equipment fault diagnosis method based on improved deep residual shrinkage network |
| url | https://doi.org/10.1371/journal.pone.0307672 |
| work_keys_str_mv | AT shaomingqiu mechanicalequipmentfaultdiagnosismethodbasedonimproveddeepresidualshrinkagenetwork AT liangyuliu mechanicalequipmentfaultdiagnosismethodbasedonimproveddeepresidualshrinkagenetwork AT yanwang mechanicalequipmentfaultdiagnosismethodbasedonimproveddeepresidualshrinkagenetwork AT xinchenhuang mechanicalequipmentfaultdiagnosismethodbasedonimproveddeepresidualshrinkagenetwork AT biconge mechanicalequipmentfaultdiagnosismethodbasedonimproveddeepresidualshrinkagenetwork AT jingfengye mechanicalequipmentfaultdiagnosismethodbasedonimproveddeepresidualshrinkagenetwork |