Rolling Bearing Fault Diagnosis Based on Sensitive Feature Transfer Learning and Local Maximum Margin Criterion under Variable Working Condition
In real industrial scenarios, the working conditions of bearings are variable, and it is therefore difficult for data-driven diagnosis methods based on conventional machine-learning techniques to guarantee the desirable performance of diagnosis models, as the models assume that the distributions of...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2020-01-01
|
| Series: | Shock and Vibration |
| Online Access: | http://dx.doi.org/10.1155/2020/8582732 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832553936646569984 |
|---|---|
| author | Shiyuan Liu Xiao Yu Xu Qian Fei Dong |
| author_facet | Shiyuan Liu Xiao Yu Xu Qian Fei Dong |
| author_sort | Shiyuan Liu |
| collection | DOAJ |
| description | In real industrial scenarios, the working conditions of bearings are variable, and it is therefore difficult for data-driven diagnosis methods based on conventional machine-learning techniques to guarantee the desirable performance of diagnosis models, as the models assume that the distributions of both the training and testing data are the same. To enhance the performance of the fault diagnosis of bearings under different working conditions, a novel diagnosis framework inspired by feature extraction, transfer learning (TL), and feature dimensionality reduction is proposed in this work, and dual-tree complex wavelet packet transform (DTCWPT) is used for signal processing. Additionally, transferable sensitive feature selection by ReliefF and the sum of mean deviation (TSFSR) is proposed to reduce the redundant information of the original feature set, to select sensitive features for fault diagnosis, and to reduce the difference between the marginal distributions of the training and testing feature sets. Furthermore, a modified feature reduction method, the local maximum margin criterion (LMMC), is proposed to acquire low-dimensional mapping for high-dimensional feature spaces. Finally, bearing vibration signals collected from two test rigs are analyzed to demonstrate the adaptability, effectiveness, and practicability of the proposed diagnosis framework. The experimental results show that the proposed method can achieve high diagnosis accuracy and has significant potential benefits in industrial applications. |
| format | Article |
| id | doaj-art-3983615d13ea42db9bc1765dab093b8f |
| institution | Kabale University |
| issn | 1070-9622 1875-9203 |
| language | English |
| publishDate | 2020-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Shock and Vibration |
| spelling | doaj-art-3983615d13ea42db9bc1765dab093b8f2025-02-03T05:52:42ZengWileyShock and Vibration1070-96221875-92032020-01-01202010.1155/2020/85827328582732Rolling Bearing Fault Diagnosis Based on Sensitive Feature Transfer Learning and Local Maximum Margin Criterion under Variable Working ConditionShiyuan Liu0Xiao Yu1Xu Qian2Fei Dong3College of Applied Science and Technology, Beijing Union University, Beijing 100083, ChinaIOT Perception Mine Research Center, China University of Mining and Technology, Xuzhou 221000, ChinaSchool of Mechanical Electronic & Information Engineering, China University of Mining and Technology (Beijing), Beijing 100083, ChinaIOT Perception Mine Research Center, China University of Mining and Technology, Xuzhou 221000, ChinaIn real industrial scenarios, the working conditions of bearings are variable, and it is therefore difficult for data-driven diagnosis methods based on conventional machine-learning techniques to guarantee the desirable performance of diagnosis models, as the models assume that the distributions of both the training and testing data are the same. To enhance the performance of the fault diagnosis of bearings under different working conditions, a novel diagnosis framework inspired by feature extraction, transfer learning (TL), and feature dimensionality reduction is proposed in this work, and dual-tree complex wavelet packet transform (DTCWPT) is used for signal processing. Additionally, transferable sensitive feature selection by ReliefF and the sum of mean deviation (TSFSR) is proposed to reduce the redundant information of the original feature set, to select sensitive features for fault diagnosis, and to reduce the difference between the marginal distributions of the training and testing feature sets. Furthermore, a modified feature reduction method, the local maximum margin criterion (LMMC), is proposed to acquire low-dimensional mapping for high-dimensional feature spaces. Finally, bearing vibration signals collected from two test rigs are analyzed to demonstrate the adaptability, effectiveness, and practicability of the proposed diagnosis framework. The experimental results show that the proposed method can achieve high diagnosis accuracy and has significant potential benefits in industrial applications.http://dx.doi.org/10.1155/2020/8582732 |
| spellingShingle | Shiyuan Liu Xiao Yu Xu Qian Fei Dong Rolling Bearing Fault Diagnosis Based on Sensitive Feature Transfer Learning and Local Maximum Margin Criterion under Variable Working Condition Shock and Vibration |
| title | Rolling Bearing Fault Diagnosis Based on Sensitive Feature Transfer Learning and Local Maximum Margin Criterion under Variable Working Condition |
| title_full | Rolling Bearing Fault Diagnosis Based on Sensitive Feature Transfer Learning and Local Maximum Margin Criterion under Variable Working Condition |
| title_fullStr | Rolling Bearing Fault Diagnosis Based on Sensitive Feature Transfer Learning and Local Maximum Margin Criterion under Variable Working Condition |
| title_full_unstemmed | Rolling Bearing Fault Diagnosis Based on Sensitive Feature Transfer Learning and Local Maximum Margin Criterion under Variable Working Condition |
| title_short | Rolling Bearing Fault Diagnosis Based on Sensitive Feature Transfer Learning and Local Maximum Margin Criterion under Variable Working Condition |
| title_sort | rolling bearing fault diagnosis based on sensitive feature transfer learning and local maximum margin criterion under variable working condition |
| url | http://dx.doi.org/10.1155/2020/8582732 |
| work_keys_str_mv | AT shiyuanliu rollingbearingfaultdiagnosisbasedonsensitivefeaturetransferlearningandlocalmaximummargincriterionundervariableworkingcondition AT xiaoyu rollingbearingfaultdiagnosisbasedonsensitivefeaturetransferlearningandlocalmaximummargincriterionundervariableworkingcondition AT xuqian rollingbearingfaultdiagnosisbasedonsensitivefeaturetransferlearningandlocalmaximummargincriterionundervariableworkingcondition AT feidong rollingbearingfaultdiagnosisbasedonsensitivefeaturetransferlearningandlocalmaximummargincriterionundervariableworkingcondition |