An Intelligent Multi-Local Model Bearing Fault Diagnosis Method Using Small Sample Fusion
It is essential to accurately diagnose bearing faults to avoid property losses or casualties in the industry caused by motor failures. Recently, the methods of fault diagnosis for bearings using deep learning methods have improved the safety of motor operations in a reliable and intelligent way. How...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-08-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/17/7567 |
| _version_ | 1827727777758969856 |
|---|---|
| author | Xianzhang Zhou Aohan Li Guangjie Han |
| author_facet | Xianzhang Zhou Aohan Li Guangjie Han |
| author_sort | Xianzhang Zhou |
| collection | DOAJ |
| description | It is essential to accurately diagnose bearing faults to avoid property losses or casualties in the industry caused by motor failures. Recently, the methods of fault diagnosis for bearings using deep learning methods have improved the safety of motor operations in a reliable and intelligent way. However, most of the work is mainly suitable for situations where there is sufficient monitoring data of the bearings. In industrial systems, only a small amount of monitoring data can be collected by the bearing sensors due to the harsh monitoring conditions and the short time of the signals of some special motor bearings. To solve the issue above, this paper introduces a transfer learning strategy by focusing on the multi-local model bearing fault based on small sample fusion. The algorithm mainly includes the following steps: (1) constructing a parallel Bi-LSTM sub-network to extract features from bearing vibration and current signals of industrial motor bearings, serially fusing the extracted vibration and current signal features for fault classification, and using them as a source domain fault diagnosis model; (2) measuring the distribution difference between the source domain bearing data and the target bearing data using the maximum mean difference algorithm; (3) based on the distribution differences between the source domain and the target domain, transferring the network parameters of the source domain fault diagnosis model, fine-tuning the network structure of the source domain fault diagnosis model, and obtaining the target domain fault diagnosis model. A performance evaluation reveals that a higher fault diagnosis accuracy under small sample fusion can be maintained by the proposed method compared to other methods. In addition, the early training time of the fault diagnosis model can be reduced, and its generalization ability can be improved to a great extent. Specifically, the fault diagnosis accuracy can be improved to higher than 80% while the training time can be reduced to 15.3% by using the proposed method. |
| first_indexed | 2024-03-10T23:12:49Z |
| format | Article |
| id | doaj.art-dcf7e7b93f824a92890c4cf66733ecc5 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T23:12:49Z |
| publishDate | 2023-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-dcf7e7b93f824a92890c4cf66733ecc52023-11-19T08:51:34ZengMDPI AGSensors1424-82202023-08-012317756710.3390/s23177567An Intelligent Multi-Local Model Bearing Fault Diagnosis Method Using Small Sample FusionXianzhang Zhou0Aohan Li1Guangjie Han2Chongqing Academy of Education Science, Chongqing 400015, ChinaGraduate School of Informatics and Engineering, The University of Electro-Communications, Tokyo 1828585, JapanDepartment of Internet of Things Engineering, Hohai University, Changzhou 213022, ChinaIt is essential to accurately diagnose bearing faults to avoid property losses or casualties in the industry caused by motor failures. Recently, the methods of fault diagnosis for bearings using deep learning methods have improved the safety of motor operations in a reliable and intelligent way. However, most of the work is mainly suitable for situations where there is sufficient monitoring data of the bearings. In industrial systems, only a small amount of monitoring data can be collected by the bearing sensors due to the harsh monitoring conditions and the short time of the signals of some special motor bearings. To solve the issue above, this paper introduces a transfer learning strategy by focusing on the multi-local model bearing fault based on small sample fusion. The algorithm mainly includes the following steps: (1) constructing a parallel Bi-LSTM sub-network to extract features from bearing vibration and current signals of industrial motor bearings, serially fusing the extracted vibration and current signal features for fault classification, and using them as a source domain fault diagnosis model; (2) measuring the distribution difference between the source domain bearing data and the target bearing data using the maximum mean difference algorithm; (3) based on the distribution differences between the source domain and the target domain, transferring the network parameters of the source domain fault diagnosis model, fine-tuning the network structure of the source domain fault diagnosis model, and obtaining the target domain fault diagnosis model. A performance evaluation reveals that a higher fault diagnosis accuracy under small sample fusion can be maintained by the proposed method compared to other methods. In addition, the early training time of the fault diagnosis model can be reduced, and its generalization ability can be improved to a great extent. Specifically, the fault diagnosis accuracy can be improved to higher than 80% while the training time can be reduced to 15.3% by using the proposed method.https://www.mdpi.com/1424-8220/23/17/7567industrial IoTbearing fault diagnosissmall sample fusiontransfer learning |
| spellingShingle | Xianzhang Zhou Aohan Li Guangjie Han An Intelligent Multi-Local Model Bearing Fault Diagnosis Method Using Small Sample Fusion Sensors industrial IoT bearing fault diagnosis small sample fusion transfer learning |
| title | An Intelligent Multi-Local Model Bearing Fault Diagnosis Method Using Small Sample Fusion |
| title_full | An Intelligent Multi-Local Model Bearing Fault Diagnosis Method Using Small Sample Fusion |
| title_fullStr | An Intelligent Multi-Local Model Bearing Fault Diagnosis Method Using Small Sample Fusion |
| title_full_unstemmed | An Intelligent Multi-Local Model Bearing Fault Diagnosis Method Using Small Sample Fusion |
| title_short | An Intelligent Multi-Local Model Bearing Fault Diagnosis Method Using Small Sample Fusion |
| title_sort | intelligent multi local model bearing fault diagnosis method using small sample fusion |
| topic | industrial IoT bearing fault diagnosis small sample fusion transfer learning |
| url | https://www.mdpi.com/1424-8220/23/17/7567 |
| work_keys_str_mv | AT xianzhangzhou anintelligentmultilocalmodelbearingfaultdiagnosismethodusingsmallsamplefusion AT aohanli anintelligentmultilocalmodelbearingfaultdiagnosismethodusingsmallsamplefusion AT guangjiehan anintelligentmultilocalmodelbearingfaultdiagnosismethodusingsmallsamplefusion AT xianzhangzhou intelligentmultilocalmodelbearingfaultdiagnosismethodusingsmallsamplefusion AT aohanli intelligentmultilocalmodelbearingfaultdiagnosismethodusingsmallsamplefusion AT guangjiehan intelligentmultilocalmodelbearingfaultdiagnosismethodusingsmallsamplefusion |