A New Transfer Learning Ensemble Model with New Training Methods for Gear Wear Particle Recognition
Aiming at solving the acquisition problems of wear particle data of large-modulus gear teeth and few training datasets, an integrated model of LCNNE based on transfer learning is proposed in this paper. Firstly, the wear particles are diagnosed and classified by connecting a new joint loss function...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-01-01
|
| Series: | Shock and Vibration |
| Online Access: | http://dx.doi.org/10.1155/2022/3696091 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832559162905591808 |
|---|---|
| author | Chunhua Zhao zhangwen Lin Jinling Tan Hengxing Hu Qian Li |
| author_facet | Chunhua Zhao zhangwen Lin Jinling Tan Hengxing Hu Qian Li |
| author_sort | Chunhua Zhao |
| collection | DOAJ |
| description | Aiming at solving the acquisition problems of wear particle data of large-modulus gear teeth and few training datasets, an integrated model of LCNNE based on transfer learning is proposed in this paper. Firstly, the wear particles are diagnosed and classified by connecting a new joint loss function and two pretrained models VGG19 and GoogLeNet. Subsequently, the wear particles in gearbox lubricating oil are chosen as the experimental object to make a comparison. Compared with the other four models’ experimental results, the model superiority in wear particle identification and classification is verified. Taking five models as feature extractors and support vector machines as classifiers, the experimental results and comparative analysis reveal that the LCNNE model is better than the other four models because its feature expression ability is stronger than that of the other four models. |
| format | Article |
| id | doaj-art-aa04d3d6788c45f3afcdcd7961273473 |
| institution | Kabale University |
| issn | 1875-9203 |
| language | English |
| publishDate | 2022-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Shock and Vibration |
| spelling | doaj-art-aa04d3d6788c45f3afcdcd79612734732025-02-03T01:30:39ZengWileyShock and Vibration1875-92032022-01-01202210.1155/2022/3696091A New Transfer Learning Ensemble Model with New Training Methods for Gear Wear Particle RecognitionChunhua Zhao0zhangwen Lin1Jinling Tan2Hengxing Hu3Qian Li4Hubei Key Laboratory of Hydroelectric Machinery Design & MaintenanceCollege of Mechanical and Power EngineeringQuality Education Center for College StudentsCollege of Mechanical and Power EngineeringCollege of Mechanical and Power EngineeringAiming at solving the acquisition problems of wear particle data of large-modulus gear teeth and few training datasets, an integrated model of LCNNE based on transfer learning is proposed in this paper. Firstly, the wear particles are diagnosed and classified by connecting a new joint loss function and two pretrained models VGG19 and GoogLeNet. Subsequently, the wear particles in gearbox lubricating oil are chosen as the experimental object to make a comparison. Compared with the other four models’ experimental results, the model superiority in wear particle identification and classification is verified. Taking five models as feature extractors and support vector machines as classifiers, the experimental results and comparative analysis reveal that the LCNNE model is better than the other four models because its feature expression ability is stronger than that of the other four models.http://dx.doi.org/10.1155/2022/3696091 |
| spellingShingle | Chunhua Zhao zhangwen Lin Jinling Tan Hengxing Hu Qian Li A New Transfer Learning Ensemble Model with New Training Methods for Gear Wear Particle Recognition Shock and Vibration |
| title | A New Transfer Learning Ensemble Model with New Training Methods for Gear Wear Particle Recognition |
| title_full | A New Transfer Learning Ensemble Model with New Training Methods for Gear Wear Particle Recognition |
| title_fullStr | A New Transfer Learning Ensemble Model with New Training Methods for Gear Wear Particle Recognition |
| title_full_unstemmed | A New Transfer Learning Ensemble Model with New Training Methods for Gear Wear Particle Recognition |
| title_short | A New Transfer Learning Ensemble Model with New Training Methods for Gear Wear Particle Recognition |
| title_sort | new transfer learning ensemble model with new training methods for gear wear particle recognition |
| url | http://dx.doi.org/10.1155/2022/3696091 |
| work_keys_str_mv | AT chunhuazhao anewtransferlearningensemblemodelwithnewtrainingmethodsforgearwearparticlerecognition AT zhangwenlin anewtransferlearningensemblemodelwithnewtrainingmethodsforgearwearparticlerecognition AT jinlingtan anewtransferlearningensemblemodelwithnewtrainingmethodsforgearwearparticlerecognition AT hengxinghu anewtransferlearningensemblemodelwithnewtrainingmethodsforgearwearparticlerecognition AT qianli anewtransferlearningensemblemodelwithnewtrainingmethodsforgearwearparticlerecognition AT chunhuazhao newtransferlearningensemblemodelwithnewtrainingmethodsforgearwearparticlerecognition AT zhangwenlin newtransferlearningensemblemodelwithnewtrainingmethodsforgearwearparticlerecognition AT jinlingtan newtransferlearningensemblemodelwithnewtrainingmethodsforgearwearparticlerecognition AT hengxinghu newtransferlearningensemblemodelwithnewtrainingmethodsforgearwearparticlerecognition AT qianli newtransferlearningensemblemodelwithnewtrainingmethodsforgearwearparticlerecognition |