Model Parameter Transfer for Gear Fault Diagnosis under Varying Working Conditions
Abstract Gear fault diagnosis technologies have received rapid development and been effectively implemented in many engineering applications. However, the various working conditions would degrade the diagnostic performance and make gear fault diagnosis (GFD) more and more challenging. In this paper,...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2021-01-01
|
| Series: | Chinese Journal of Mechanical Engineering |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s10033-020-00520-9 |
| _version_ | 1818720200904671232 |
|---|---|
| author | Chao Chen Fei Shen Jiawen Xu Ruqiang Yan |
| author_facet | Chao Chen Fei Shen Jiawen Xu Ruqiang Yan |
| author_sort | Chao Chen |
| collection | DOAJ |
| description | Abstract Gear fault diagnosis technologies have received rapid development and been effectively implemented in many engineering applications. However, the various working conditions would degrade the diagnostic performance and make gear fault diagnosis (GFD) more and more challenging. In this paper, a novel model parameter transfer (NMPT) is proposed to boost the performance of GFD under varying working conditions. Based on the previous transfer strategy that controls empirical risk of source domain, this method further integrates the superiorities of multi-task learning with the idea of transfer learning (TL) to acquire transferable knowledge by minimizing the discrepancies of separating hyperplanes between one specific working condition (target domain) and another (source domain), and then transferring both commonality and specialty parameters over tasks to make use of source domain samples to assist target GFD task when sufficient labeled samples from target domain are unavailable. For NMPT implementation, insufficient target domain features and abundant source domain features with supervised information are fed into NMPT model to train a robust classifier for target GFD task. Related experiments prove that NMPT is expected to be a valuable technology to boost practical GFD performance under various working conditions. The proposed methods provides a transfer learning-based framework to handle the problem of insufficient training samples in target task caused by variable operation conditions. |
| first_indexed | 2024-12-17T20:19:04Z |
| format | Article |
| id | doaj.art-a384a159a0694d538753dd18888997c8 |
| institution | Directory Open Access Journal |
| issn | 1000-9345 2192-8258 |
| language | English |
| last_indexed | 2024-12-17T20:19:04Z |
| publishDate | 2021-01-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Chinese Journal of Mechanical Engineering |
| spelling | doaj.art-a384a159a0694d538753dd18888997c82022-12-21T21:34:00ZengSpringerOpenChinese Journal of Mechanical Engineering1000-93452192-82582021-01-0134111310.1186/s10033-020-00520-9Model Parameter Transfer for Gear Fault Diagnosis under Varying Working ConditionsChao Chen0Fei Shen1Jiawen Xu2Ruqiang Yan3School of Instrument Science and Engineering, Southeast UniversitySchool of Instrument Science and Engineering, Southeast UniversitySchool of Instrument Science and Engineering, Southeast UniversitySchool of Instrument Science and Engineering, Southeast UniversityAbstract Gear fault diagnosis technologies have received rapid development and been effectively implemented in many engineering applications. However, the various working conditions would degrade the diagnostic performance and make gear fault diagnosis (GFD) more and more challenging. In this paper, a novel model parameter transfer (NMPT) is proposed to boost the performance of GFD under varying working conditions. Based on the previous transfer strategy that controls empirical risk of source domain, this method further integrates the superiorities of multi-task learning with the idea of transfer learning (TL) to acquire transferable knowledge by minimizing the discrepancies of separating hyperplanes between one specific working condition (target domain) and another (source domain), and then transferring both commonality and specialty parameters over tasks to make use of source domain samples to assist target GFD task when sufficient labeled samples from target domain are unavailable. For NMPT implementation, insufficient target domain features and abundant source domain features with supervised information are fed into NMPT model to train a robust classifier for target GFD task. Related experiments prove that NMPT is expected to be a valuable technology to boost practical GFD performance under various working conditions. The proposed methods provides a transfer learning-based framework to handle the problem of insufficient training samples in target task caused by variable operation conditions.https://doi.org/10.1186/s10033-020-00520-9Gear fault diagnosisModel parameter transferVarying working conditionsLeast square support vector machine |
| spellingShingle | Chao Chen Fei Shen Jiawen Xu Ruqiang Yan Model Parameter Transfer for Gear Fault Diagnosis under Varying Working Conditions Chinese Journal of Mechanical Engineering Gear fault diagnosis Model parameter transfer Varying working conditions Least square support vector machine |
| title | Model Parameter Transfer for Gear Fault Diagnosis under Varying Working Conditions |
| title_full | Model Parameter Transfer for Gear Fault Diagnosis under Varying Working Conditions |
| title_fullStr | Model Parameter Transfer for Gear Fault Diagnosis under Varying Working Conditions |
| title_full_unstemmed | Model Parameter Transfer for Gear Fault Diagnosis under Varying Working Conditions |
| title_short | Model Parameter Transfer for Gear Fault Diagnosis under Varying Working Conditions |
| title_sort | model parameter transfer for gear fault diagnosis under varying working conditions |
| topic | Gear fault diagnosis Model parameter transfer Varying working conditions Least square support vector machine |
| url | https://doi.org/10.1186/s10033-020-00520-9 |
| work_keys_str_mv | AT chaochen modelparametertransferforgearfaultdiagnosisundervaryingworkingconditions AT feishen modelparametertransferforgearfaultdiagnosisundervaryingworkingconditions AT jiawenxu modelparametertransferforgearfaultdiagnosisundervaryingworkingconditions AT ruqiangyan modelparametertransferforgearfaultdiagnosisundervaryingworkingconditions |