Bearing Fault Diagnosis Based on Small Sample Learning of Maml–Triplet
Since the emergence of artificial intelligence and deep learning methods, the fault diagnosis of bearings in rotating machinery has gradually been realized, reducing the high costs of bearing faults. However, in the actual work of the equipment, faults rarely occur, resulting in less fault data. The...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-10-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/21/10723 |
| _version_ | 1797469265091100672 |
|---|---|
| author | Qiang Cheng Zhaoheng He Tao Zhang Ying Li Zhifeng Liu Ziling Zhang |
| author_facet | Qiang Cheng Zhaoheng He Tao Zhang Ying Li Zhifeng Liu Ziling Zhang |
| author_sort | Qiang Cheng |
| collection | DOAJ |
| description | Since the emergence of artificial intelligence and deep learning methods, the fault diagnosis of bearings in rotating machinery has gradually been realized, reducing the high costs of bearing faults. However, in the actual work of the equipment, faults rarely occur, resulting in less fault data. Therefore, it is necessary to study small sample fault data. For the case of less fault data, the Maml–Triplet fault classification learning framework based on the combination of maml and the triplet neural network is proposed. In the framework of Maml-Triplet fault classification, firstly, an initial signal feature extractor is obtained using the Maml training method. Secondly, the feature vectors corresponding to signal data are obtained using depth distance measurement learning in the triplet neural network, and the fault type is judged based on the feature vectors of unknown signal. The results show that the accuracy of the Maml–Triplet model is 2% higher than that of the triplet model alone and 5% higher than that of the Maml–CNN meta learning method. When there are fewer data samples, the accuracy gap is more obvious. Therefore, in the case of less data, the Maml–Triplet model has an excellent fault identification ability. |
| first_indexed | 2024-03-09T19:18:56Z |
| format | Article |
| id | doaj.art-40df612d29714693b6e9a2fa736f791c |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T19:18:56Z |
| publishDate | 2022-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-40df612d29714693b6e9a2fa736f791c2023-11-24T03:31:47ZengMDPI AGApplied Sciences2076-34172022-10-0112211072310.3390/app122110723Bearing Fault Diagnosis Based on Small Sample Learning of Maml–TripletQiang Cheng0Zhaoheng He1Tao Zhang2Ying Li3Zhifeng Liu4Ziling Zhang5Institute of Advanced Manufacturing and Intelligent Technology, Beijing University of Technology, Beijing 100124, ChinaInstitute of Advanced Manufacturing and Intelligent Technology, Beijing University of Technology, Beijing 100124, ChinaInstitute of Advanced Manufacturing and Intelligent Technology, Beijing University of Technology, Beijing 100124, ChinaInstitute of Advanced Manufacturing and Intelligent Technology, Beijing University of Technology, Beijing 100124, ChinaSchool of Mechanical and Aerospace Engineering, Jilin University, Changchun 130025, ChinaLogistics Engineering College, Shanghai Maritime University, Shanghai 201306, ChinaSince the emergence of artificial intelligence and deep learning methods, the fault diagnosis of bearings in rotating machinery has gradually been realized, reducing the high costs of bearing faults. However, in the actual work of the equipment, faults rarely occur, resulting in less fault data. Therefore, it is necessary to study small sample fault data. For the case of less fault data, the Maml–Triplet fault classification learning framework based on the combination of maml and the triplet neural network is proposed. In the framework of Maml-Triplet fault classification, firstly, an initial signal feature extractor is obtained using the Maml training method. Secondly, the feature vectors corresponding to signal data are obtained using depth distance measurement learning in the triplet neural network, and the fault type is judged based on the feature vectors of unknown signal. The results show that the accuracy of the Maml–Triplet model is 2% higher than that of the triplet model alone and 5% higher than that of the Maml–CNN meta learning method. When there are fewer data samples, the accuracy gap is more obvious. Therefore, in the case of less data, the Maml–Triplet model has an excellent fault identification ability.https://www.mdpi.com/2076-3417/12/21/10723Maml–Triplet learningbearingsmall samplefault diagnosisfew shot |
| spellingShingle | Qiang Cheng Zhaoheng He Tao Zhang Ying Li Zhifeng Liu Ziling Zhang Bearing Fault Diagnosis Based on Small Sample Learning of Maml–Triplet Applied Sciences Maml–Triplet learning bearing small sample fault diagnosis few shot |
| title | Bearing Fault Diagnosis Based on Small Sample Learning of Maml–Triplet |
| title_full | Bearing Fault Diagnosis Based on Small Sample Learning of Maml–Triplet |
| title_fullStr | Bearing Fault Diagnosis Based on Small Sample Learning of Maml–Triplet |
| title_full_unstemmed | Bearing Fault Diagnosis Based on Small Sample Learning of Maml–Triplet |
| title_short | Bearing Fault Diagnosis Based on Small Sample Learning of Maml–Triplet |
| title_sort | bearing fault diagnosis based on small sample learning of maml triplet |
| topic | Maml–Triplet learning bearing small sample fault diagnosis few shot |
| url | https://www.mdpi.com/2076-3417/12/21/10723 |
| work_keys_str_mv | AT qiangcheng bearingfaultdiagnosisbasedonsmallsamplelearningofmamltriplet AT zhaohenghe bearingfaultdiagnosisbasedonsmallsamplelearningofmamltriplet AT taozhang bearingfaultdiagnosisbasedonsmallsamplelearningofmamltriplet AT yingli bearingfaultdiagnosisbasedonsmallsamplelearningofmamltriplet AT zhifengliu bearingfaultdiagnosisbasedonsmallsamplelearningofmamltriplet AT zilingzhang bearingfaultdiagnosisbasedonsmallsamplelearningofmamltriplet |