A Novel Method of Production Line Bearing Fault Diagnosis Based on 2D Image and Cross-Domain Few-Shot Learning
Data-driven intelligent fault diagnosis has made considerable strides. However, collecting sufficient fault information in real production data is extremely challenging. Therefore, a novel method of bearing fault diagnosis based on two-dimensional (2D) images and cross-domain few-shot learning is pr...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-01-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/3/1809 |
| _version_ | 1827760363203985408 |
|---|---|
| author | Tong Wang Changzheng Chen Xingjun Dong Hanrui Liu |
| author_facet | Tong Wang Changzheng Chen Xingjun Dong Hanrui Liu |
| author_sort | Tong Wang |
| collection | DOAJ |
| description | Data-driven intelligent fault diagnosis has made considerable strides. However, collecting sufficient fault information in real production data is extremely challenging. Therefore, a novel method of bearing fault diagnosis based on two-dimensional (2D) images and cross-domain few-shot learning is proposed. Initially, the approach uses multiscale morphology to convert the bearing’s one-dimensional (1D) vibration signal into a 2D image, which preserves the whole information. Second, to address the issue of limited bearing fault data, we extend a substantial amount of natural image knowledge to the converted 2D image based on the improved cross-domain few-shot learning method. A distance-based classifier is employed to prevent the problem of overfitting owing to insufficient data to improve the approach’s classification capacity with few samples. The experimental results demonstrate that, with the limited dataset provided, our method outperforms other prevalent methods and has high feasibility and certain engineering applications. |
| first_indexed | 2024-03-11T09:52:30Z |
| format | Article |
| id | doaj.art-dc8b37dc9068467b80742889d89b40a2 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-11T09:52:30Z |
| publishDate | 2023-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-dc8b37dc9068467b80742889d89b40a22023-11-16T16:10:43ZengMDPI AGApplied Sciences2076-34172023-01-01133180910.3390/app13031809A Novel Method of Production Line Bearing Fault Diagnosis Based on 2D Image and Cross-Domain Few-Shot LearningTong Wang0Changzheng Chen1Xingjun Dong2Hanrui Liu3School of Mechanical Engineering, Shenyang University of Technology, Shenyang 110870, ChinaSchool of Mechanical Engineering, Shenyang University of Technology, Shenyang 110870, ChinaBMW Brilliance Automotive Ltd., Shenyang 110143, ChinaCollege of Software, Northeastern University, Shenyang 110819, ChinaData-driven intelligent fault diagnosis has made considerable strides. However, collecting sufficient fault information in real production data is extremely challenging. Therefore, a novel method of bearing fault diagnosis based on two-dimensional (2D) images and cross-domain few-shot learning is proposed. Initially, the approach uses multiscale morphology to convert the bearing’s one-dimensional (1D) vibration signal into a 2D image, which preserves the whole information. Second, to address the issue of limited bearing fault data, we extend a substantial amount of natural image knowledge to the converted 2D image based on the improved cross-domain few-shot learning method. A distance-based classifier is employed to prevent the problem of overfitting owing to insufficient data to improve the approach’s classification capacity with few samples. The experimental results demonstrate that, with the limited dataset provided, our method outperforms other prevalent methods and has high feasibility and certain engineering applications.https://www.mdpi.com/2076-3417/13/3/1809cross-domain few-shot learningmultiscale morphology2D imagebearingfault diagnosis |
| spellingShingle | Tong Wang Changzheng Chen Xingjun Dong Hanrui Liu A Novel Method of Production Line Bearing Fault Diagnosis Based on 2D Image and Cross-Domain Few-Shot Learning Applied Sciences cross-domain few-shot learning multiscale morphology 2D image bearing fault diagnosis |
| title | A Novel Method of Production Line Bearing Fault Diagnosis Based on 2D Image and Cross-Domain Few-Shot Learning |
| title_full | A Novel Method of Production Line Bearing Fault Diagnosis Based on 2D Image and Cross-Domain Few-Shot Learning |
| title_fullStr | A Novel Method of Production Line Bearing Fault Diagnosis Based on 2D Image and Cross-Domain Few-Shot Learning |
| title_full_unstemmed | A Novel Method of Production Line Bearing Fault Diagnosis Based on 2D Image and Cross-Domain Few-Shot Learning |
| title_short | A Novel Method of Production Line Bearing Fault Diagnosis Based on 2D Image and Cross-Domain Few-Shot Learning |
| title_sort | novel method of production line bearing fault diagnosis based on 2d image and cross domain few shot learning |
| topic | cross-domain few-shot learning multiscale morphology 2D image bearing fault diagnosis |
| url | https://www.mdpi.com/2076-3417/13/3/1809 |
| work_keys_str_mv | AT tongwang anovelmethodofproductionlinebearingfaultdiagnosisbasedon2dimageandcrossdomainfewshotlearning AT changzhengchen anovelmethodofproductionlinebearingfaultdiagnosisbasedon2dimageandcrossdomainfewshotlearning AT xingjundong anovelmethodofproductionlinebearingfaultdiagnosisbasedon2dimageandcrossdomainfewshotlearning AT hanruiliu anovelmethodofproductionlinebearingfaultdiagnosisbasedon2dimageandcrossdomainfewshotlearning AT tongwang novelmethodofproductionlinebearingfaultdiagnosisbasedon2dimageandcrossdomainfewshotlearning AT changzhengchen novelmethodofproductionlinebearingfaultdiagnosisbasedon2dimageandcrossdomainfewshotlearning AT xingjundong novelmethodofproductionlinebearingfaultdiagnosisbasedon2dimageandcrossdomainfewshotlearning AT hanruiliu novelmethodofproductionlinebearingfaultdiagnosisbasedon2dimageandcrossdomainfewshotlearning |