Fault Feature Extraction of Parallel-Axis Gearbox Based on IDBO-VMD and t-SNE
For the problem that the fault states of parallel shaft gearboxes are difficult to identify, a diagnostic method is proposed to optimize variational modal decomposition (VMD) and t-distributed stochastic neighbor embedding (t-SNE) using an improved dung beetle optimization algorithm I have checked a...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/14/1/289 |
| _version_ | 1797359101168058368 |
|---|---|
| author | Zhen Wang Shuaiyu Wang Yiyang Cheng |
| author_facet | Zhen Wang Shuaiyu Wang Yiyang Cheng |
| author_sort | Zhen Wang |
| collection | DOAJ |
| description | For the problem that the fault states of parallel shaft gearboxes are difficult to identify, a diagnostic method is proposed to optimize variational modal decomposition (VMD) and t-distributed stochastic neighbor embedding (t-SNE) using an improved dung beetle optimization algorithm I have checked and revised all. (IDBO). IDBO is obtained by amplifying dung beetle optimization (DBO) using strategies such as chaos mapping, Levy flight policy, and dynamic adaptive weighting. IDBO is employed to optimize VMD, extracting decomposed eigenvalues restructured into high-dimensional feature vectors. Subsequently, we employ the t-SNE algorithm for dimensionality reduction to eliminate redundancy, obtaining two-dimensional vectors. Finally, these vectors are input into a support vector machine (SVM) for fault diagnosis. We apply IDBO, grey wolf optimization (GWO), DBO, and the sparrow search algorithm (SSA) to both benchmark functions and VMD, conducting a performance comparison. The results demonstrate that IDBO exhibits superior convergence speed and global search capability, effectively suppressing modal aliasing issues in VMD, thereby enhancing the algorithm’s robustness. Through experimental fault diagnosis on a gear transmission system, we compare our proposed method with EMD + t-SNE and traditional VMD + t-SNE feature extraction approaches. The experimental results indicate that the fault diagnosis accuracy reaches 100% after processing the fault signals with IDBO-VMD + t-SNE. This method proves to be an effective fault diagnosis approach specifically tailored for parallel-axis gearboxes, providing a reliable means to enhance diagnostic accuracy. |
| first_indexed | 2024-03-08T15:11:52Z |
| format | Article |
| id | doaj.art-cdb4c8725aa24302a74789f7d8e6c3b8 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-08T15:11:52Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-cdb4c8725aa24302a74789f7d8e6c3b82024-01-10T14:51:37ZengMDPI AGApplied Sciences2076-34172023-12-0114128910.3390/app14010289Fault Feature Extraction of Parallel-Axis Gearbox Based on IDBO-VMD and t-SNEZhen Wang0Shuaiyu Wang1Yiyang Cheng2School of Mechanical Engineering, Dalian University, Dalian 116022, ChinaSchool of Mechanical Engineering, Dalian University, Dalian 116022, ChinaSchool of Mechanical Engineering, Dalian University, Dalian 116022, ChinaFor the problem that the fault states of parallel shaft gearboxes are difficult to identify, a diagnostic method is proposed to optimize variational modal decomposition (VMD) and t-distributed stochastic neighbor embedding (t-SNE) using an improved dung beetle optimization algorithm I have checked and revised all. (IDBO). IDBO is obtained by amplifying dung beetle optimization (DBO) using strategies such as chaos mapping, Levy flight policy, and dynamic adaptive weighting. IDBO is employed to optimize VMD, extracting decomposed eigenvalues restructured into high-dimensional feature vectors. Subsequently, we employ the t-SNE algorithm for dimensionality reduction to eliminate redundancy, obtaining two-dimensional vectors. Finally, these vectors are input into a support vector machine (SVM) for fault diagnosis. We apply IDBO, grey wolf optimization (GWO), DBO, and the sparrow search algorithm (SSA) to both benchmark functions and VMD, conducting a performance comparison. The results demonstrate that IDBO exhibits superior convergence speed and global search capability, effectively suppressing modal aliasing issues in VMD, thereby enhancing the algorithm’s robustness. Through experimental fault diagnosis on a gear transmission system, we compare our proposed method with EMD + t-SNE and traditional VMD + t-SNE feature extraction approaches. The experimental results indicate that the fault diagnosis accuracy reaches 100% after processing the fault signals with IDBO-VMD + t-SNE. This method proves to be an effective fault diagnosis approach specifically tailored for parallel-axis gearboxes, providing a reliable means to enhance diagnostic accuracy.https://www.mdpi.com/2076-3417/14/1/289fault diagnosisfeature extractionIDBOt-SNEVMD |
| spellingShingle | Zhen Wang Shuaiyu Wang Yiyang Cheng Fault Feature Extraction of Parallel-Axis Gearbox Based on IDBO-VMD and t-SNE Applied Sciences fault diagnosis feature extraction IDBO t-SNE VMD |
| title | Fault Feature Extraction of Parallel-Axis Gearbox Based on IDBO-VMD and t-SNE |
| title_full | Fault Feature Extraction of Parallel-Axis Gearbox Based on IDBO-VMD and t-SNE |
| title_fullStr | Fault Feature Extraction of Parallel-Axis Gearbox Based on IDBO-VMD and t-SNE |
| title_full_unstemmed | Fault Feature Extraction of Parallel-Axis Gearbox Based on IDBO-VMD and t-SNE |
| title_short | Fault Feature Extraction of Parallel-Axis Gearbox Based on IDBO-VMD and t-SNE |
| title_sort | fault feature extraction of parallel axis gearbox based on idbo vmd and t sne |
| topic | fault diagnosis feature extraction IDBO t-SNE VMD |
| url | https://www.mdpi.com/2076-3417/14/1/289 |
| work_keys_str_mv | AT zhenwang faultfeatureextractionofparallelaxisgearboxbasedonidbovmdandtsne AT shuaiyuwang faultfeatureextractionofparallelaxisgearboxbasedonidbovmdandtsne AT yiyangcheng faultfeatureextractionofparallelaxisgearboxbasedonidbovmdandtsne |