Rolling bearings fault diagnosis based on two-stage signal fusion and deep multi-scale multi-sensor network
In order to realize high-precision diagnosis of bearings faults in a multi-sensor detection environment, a fault diagnosis method based on two-stage signal fusion and deep multi-scale multi-sensor networks is proposed. Firstly, the signals are decomposed and fused using weighted empirical wavelet tr...
| Main Authors: | , , , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/181054 |
| _version_ | 1826118369205551104 |
|---|---|
| author | Pan, Zuozhou Guan, Yang Fan, Fengjie Zheng, Yuanjin Lin, Zhiping Meng, Zong |
| author2 | School of Electrical and Electronic Engineering |
| author_facet | School of Electrical and Electronic Engineering Pan, Zuozhou Guan, Yang Fan, Fengjie Zheng, Yuanjin Lin, Zhiping Meng, Zong |
| author_sort | Pan, Zuozhou |
| collection | NTU |
| description | In order to realize high-precision diagnosis of bearings faults in a multi-sensor detection environment, a fault diagnosis method based on two-stage signal fusion and deep multi-scale multi-sensor networks is proposed. Firstly, the signals are decomposed and fused using weighted empirical wavelet transform to enhance weak features and reduce noise. Secondly, an improved random weighting algorithm is proposed to perform a second weighted fusion of the signals to reduce the total mean square error. The fused signals are input into the deep multi-scale residual network, the feature information of different convolutional layers is extracted through dilated convolution, and the features are fused using pyramid theory. Finally, the bearings states are classified according to the fusion features. Experiment results show the effectiveness and superiority of this method. |
| first_indexed | 2025-03-09T12:09:47Z |
| format | Journal Article |
| id | ntu-10356/181054 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2025-03-09T12:09:47Z |
| publishDate | 2024 |
| record_format | dspace |
| spelling | ntu-10356/1810542024-11-13T01:29:39Z Rolling bearings fault diagnosis based on two-stage signal fusion and deep multi-scale multi-sensor network Pan, Zuozhou Guan, Yang Fan, Fengjie Zheng, Yuanjin Lin, Zhiping Meng, Zong School of Electrical and Electronic Engineering Engineering Rolling bearings Fault diagnosis In order to realize high-precision diagnosis of bearings faults in a multi-sensor detection environment, a fault diagnosis method based on two-stage signal fusion and deep multi-scale multi-sensor networks is proposed. Firstly, the signals are decomposed and fused using weighted empirical wavelet transform to enhance weak features and reduce noise. Secondly, an improved random weighting algorithm is proposed to perform a second weighted fusion of the signals to reduce the total mean square error. The fused signals are input into the deep multi-scale residual network, the feature information of different convolutional layers is extracted through dilated convolution, and the features are fused using pyramid theory. Finally, the bearings states are classified according to the fusion features. Experiment results show the effectiveness and superiority of this method. This work was supported in part by the National Natural Science Foundation of China under Grant 52075470, in part by the Natural Science Foundation of Hebei Province of China under Grant E2023203228, in part by the introduction of foreign intellectual project of Hebei Province, in part by the Natural Science Foundation of Hunan Province under Grant 2023JJ50237. 2024-11-13T01:29:38Z 2024-11-13T01:29:38Z 2024 Journal Article Pan, Z., Guan, Y., Fan, F., Zheng, Y., Lin, Z. & Meng, Z. (2024). Rolling bearings fault diagnosis based on two-stage signal fusion and deep multi-scale multi-sensor network. ISA Transactions, 154, 311-334. https://dx.doi.org/10.1016/j.isatra.2024.08.033 0019-0578 https://hdl.handle.net/10356/181054 10.1016/j.isatra.2024.08.033 39289131 2-s2.0-85204037735 154 311 334 en ISA Transactions © 2024 International Society of Automation. Published by Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies. |
| spellingShingle | Engineering Rolling bearings Fault diagnosis Pan, Zuozhou Guan, Yang Fan, Fengjie Zheng, Yuanjin Lin, Zhiping Meng, Zong Rolling bearings fault diagnosis based on two-stage signal fusion and deep multi-scale multi-sensor network |
| title | Rolling bearings fault diagnosis based on two-stage signal fusion and deep multi-scale multi-sensor network |
| title_full | Rolling bearings fault diagnosis based on two-stage signal fusion and deep multi-scale multi-sensor network |
| title_fullStr | Rolling bearings fault diagnosis based on two-stage signal fusion and deep multi-scale multi-sensor network |
| title_full_unstemmed | Rolling bearings fault diagnosis based on two-stage signal fusion and deep multi-scale multi-sensor network |
| title_short | Rolling bearings fault diagnosis based on two-stage signal fusion and deep multi-scale multi-sensor network |
| title_sort | rolling bearings fault diagnosis based on two stage signal fusion and deep multi scale multi sensor network |
| topic | Engineering Rolling bearings Fault diagnosis |
| url | https://hdl.handle.net/10356/181054 |
| work_keys_str_mv | AT panzuozhou rollingbearingsfaultdiagnosisbasedontwostagesignalfusionanddeepmultiscalemultisensornetwork AT guanyang rollingbearingsfaultdiagnosisbasedontwostagesignalfusionanddeepmultiscalemultisensornetwork AT fanfengjie rollingbearingsfaultdiagnosisbasedontwostagesignalfusionanddeepmultiscalemultisensornetwork AT zhengyuanjin rollingbearingsfaultdiagnosisbasedontwostagesignalfusionanddeepmultiscalemultisensornetwork AT linzhiping rollingbearingsfaultdiagnosisbasedontwostagesignalfusionanddeepmultiscalemultisensornetwork AT mengzong rollingbearingsfaultdiagnosisbasedontwostagesignalfusionanddeepmultiscalemultisensornetwork |