A Novel Semi-Supervised Feature Extraction Method and Its Application in Automotive Assembly Fault Diagnosis Based on Vision Sensor Data
The fault diagnosis of dimensional variation plays an essential role in the production of an automotive body. However, it is difficult to identify faults based on small labeled sample data using traditional supervised learning methods. The present study proposed a novel feature extraction method nam...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2018-08-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1424-8220/18/8/2545 |
| _version_ | 1817989839309504512 |
|---|---|
| author | Xuan Zeng Shi-Bin Yin Yin Guo Jia-Rui Lin Ji-Gui Zhu |
| author_facet | Xuan Zeng Shi-Bin Yin Yin Guo Jia-Rui Lin Ji-Gui Zhu |
| author_sort | Xuan Zeng |
| collection | DOAJ |
| description | The fault diagnosis of dimensional variation plays an essential role in the production of an automotive body. However, it is difficult to identify faults based on small labeled sample data using traditional supervised learning methods. The present study proposed a novel feature extraction method named, semi-supervised complete kernel Fisher discriminant (SS-CKFDA), and a new fault diagnosis flow for automotive assembly was introduced based on this method. SS-CKFDA is a combination of traditional complete kernel Fisher discriminant (CKFDA) and semi-supervised learning. It adjusts the Fisher criterion with the data global structure extracted from large unlabeled samples. When the number of labeled samples is small, the global structure that exists in the measured data can effectively improve the extraction effects of the projected vector. The experimental results on Tennessee Eastman Process (TEP) data demonstrated that the proposed method can improve diagnostic performance, when compared to other Fisher discriminant algorithms. Finally, the experimental results on the optical coordinate data proves that the method can be applied in the automotive assembly process, and achieve a better performance. |
| first_indexed | 2024-04-14T00:51:19Z |
| format | Article |
| id | doaj.art-05deeb8cd5e04a2d9b1cd7fd472878d4 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-14T00:51:19Z |
| publishDate | 2018-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-05deeb8cd5e04a2d9b1cd7fd472878d42022-12-22T02:21:46ZengMDPI AGSensors1424-82202018-08-01188254510.3390/s18082545s18082545A Novel Semi-Supervised Feature Extraction Method and Its Application in Automotive Assembly Fault Diagnosis Based on Vision Sensor DataXuan Zeng0Shi-Bin Yin1Yin Guo2Jia-Rui Lin3Ji-Gui Zhu4State Key Laboratory of Precision Measuring Technology and Instruments, Tianjin University, Tianjin 30072, ChinaState Key Laboratory of Precision Measuring Technology and Instruments, Tianjin University, Tianjin 30072, ChinaState Key Laboratory of Precision Measuring Technology and Instruments, Tianjin University, Tianjin 30072, ChinaState Key Laboratory of Precision Measuring Technology and Instruments, Tianjin University, Tianjin 30072, ChinaState Key Laboratory of Precision Measuring Technology and Instruments, Tianjin University, Tianjin 30072, ChinaThe fault diagnosis of dimensional variation plays an essential role in the production of an automotive body. However, it is difficult to identify faults based on small labeled sample data using traditional supervised learning methods. The present study proposed a novel feature extraction method named, semi-supervised complete kernel Fisher discriminant (SS-CKFDA), and a new fault diagnosis flow for automotive assembly was introduced based on this method. SS-CKFDA is a combination of traditional complete kernel Fisher discriminant (CKFDA) and semi-supervised learning. It adjusts the Fisher criterion with the data global structure extracted from large unlabeled samples. When the number of labeled samples is small, the global structure that exists in the measured data can effectively improve the extraction effects of the projected vector. The experimental results on Tennessee Eastman Process (TEP) data demonstrated that the proposed method can improve diagnostic performance, when compared to other Fisher discriminant algorithms. Finally, the experimental results on the optical coordinate data proves that the method can be applied in the automotive assembly process, and achieve a better performance.http://www.mdpi.com/1424-8220/18/8/2545automotive assemblyfeature extractionsemi-supervised learningcomplete kernel Fisher discriminant analysisfault classification |
| spellingShingle | Xuan Zeng Shi-Bin Yin Yin Guo Jia-Rui Lin Ji-Gui Zhu A Novel Semi-Supervised Feature Extraction Method and Its Application in Automotive Assembly Fault Diagnosis Based on Vision Sensor Data Sensors automotive assembly feature extraction semi-supervised learning complete kernel Fisher discriminant analysis fault classification |
| title | A Novel Semi-Supervised Feature Extraction Method and Its Application in Automotive Assembly Fault Diagnosis Based on Vision Sensor Data |
| title_full | A Novel Semi-Supervised Feature Extraction Method and Its Application in Automotive Assembly Fault Diagnosis Based on Vision Sensor Data |
| title_fullStr | A Novel Semi-Supervised Feature Extraction Method and Its Application in Automotive Assembly Fault Diagnosis Based on Vision Sensor Data |
| title_full_unstemmed | A Novel Semi-Supervised Feature Extraction Method and Its Application in Automotive Assembly Fault Diagnosis Based on Vision Sensor Data |
| title_short | A Novel Semi-Supervised Feature Extraction Method and Its Application in Automotive Assembly Fault Diagnosis Based on Vision Sensor Data |
| title_sort | novel semi supervised feature extraction method and its application in automotive assembly fault diagnosis based on vision sensor data |
| topic | automotive assembly feature extraction semi-supervised learning complete kernel Fisher discriminant analysis fault classification |
| url | http://www.mdpi.com/1424-8220/18/8/2545 |
| work_keys_str_mv | AT xuanzeng anovelsemisupervisedfeatureextractionmethodanditsapplicationinautomotiveassemblyfaultdiagnosisbasedonvisionsensordata AT shibinyin anovelsemisupervisedfeatureextractionmethodanditsapplicationinautomotiveassemblyfaultdiagnosisbasedonvisionsensordata AT yinguo anovelsemisupervisedfeatureextractionmethodanditsapplicationinautomotiveassemblyfaultdiagnosisbasedonvisionsensordata AT jiaruilin anovelsemisupervisedfeatureextractionmethodanditsapplicationinautomotiveassemblyfaultdiagnosisbasedonvisionsensordata AT jiguizhu anovelsemisupervisedfeatureextractionmethodanditsapplicationinautomotiveassemblyfaultdiagnosisbasedonvisionsensordata AT xuanzeng novelsemisupervisedfeatureextractionmethodanditsapplicationinautomotiveassemblyfaultdiagnosisbasedonvisionsensordata AT shibinyin novelsemisupervisedfeatureextractionmethodanditsapplicationinautomotiveassemblyfaultdiagnosisbasedonvisionsensordata AT yinguo novelsemisupervisedfeatureextractionmethodanditsapplicationinautomotiveassemblyfaultdiagnosisbasedonvisionsensordata AT jiaruilin novelsemisupervisedfeatureextractionmethodanditsapplicationinautomotiveassemblyfaultdiagnosisbasedonvisionsensordata AT jiguizhu novelsemisupervisedfeatureextractionmethodanditsapplicationinautomotiveassemblyfaultdiagnosisbasedonvisionsensordata |