A Bearing Fault Diagnosis Method Using Multi-Branch Deep Neural Network
Feature extraction from a signal is the most important step in signal-based fault diagnosis. Deep learning or deep neural network (DNN) is an effective method to extract features from signals. In this paper, a novel vibration signal-based bearing fault diagnosis method using DNN is proposed. First,...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Series: | Machines |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-1702/9/12/345 |
| _version_ | 1797502830647443456 |
|---|---|
| author | Van-Cuong Nguyen Duy-Tang Hoang Xuan-Toa Tran Mien Van Hee-Jun Kang |
| author_facet | Van-Cuong Nguyen Duy-Tang Hoang Xuan-Toa Tran Mien Van Hee-Jun Kang |
| author_sort | Van-Cuong Nguyen |
| collection | DOAJ |
| description | Feature extraction from a signal is the most important step in signal-based fault diagnosis. Deep learning or deep neural network (DNN) is an effective method to extract features from signals. In this paper, a novel vibration signal-based bearing fault diagnosis method using DNN is proposed. First, the measured vibration signals are transformed into a new data form called multiple-domain image-representation. By this transformation, the task of signal-based fault diagnosis is transferred into the task of image classification. After that, a DNN with a multi-branch structure is proposed to handle the multiple-domain image representation data. The multi-branch structure of the proposed DNN helps to extract features in multiple domains simultaneously, and to lead to better feature extraction. Better feature extraction leads to a better performance of fault diagnosis. The effectiveness of the proposed method was verified via the experiments conducted with actual bearing fault signals and its comparisons with well-established published methods. |
| first_indexed | 2024-03-10T03:41:45Z |
| format | Article |
| id | doaj.art-2f2edb95ebde4cfe8588f0633d5009f6 |
| institution | Directory Open Access Journal |
| issn | 2075-1702 |
| language | English |
| last_indexed | 2024-03-10T03:41:45Z |
| publishDate | 2021-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Machines |
| spelling | doaj.art-2f2edb95ebde4cfe8588f0633d5009f62023-11-23T09:16:53ZengMDPI AGMachines2075-17022021-12-0191234510.3390/machines9120345A Bearing Fault Diagnosis Method Using Multi-Branch Deep Neural NetworkVan-Cuong Nguyen0Duy-Tang Hoang1Xuan-Toa Tran2Mien Van3Hee-Jun Kang4Department of Electrical, Electronic and Computer Engineering, University of Ulsan, Ulsan 44610, KoreaDepartment of Electrical, Electronic and Computer Engineering, University of Ulsan, Ulsan 44610, KoreaNTT Hi-Tech Institute, Nguyen Tat Thanh University, 300A Nguyen Tat Thanh Street, Ho Chi Minh City 70000, VietnamSchool of Electronics, Electrical Engineering and Computer Science, Queen’s University Belfast, Belfast BT7 1NN, UKDepartment of Electrical, Electronic and Computer Engineering, University of Ulsan, Ulsan 44610, KoreaFeature extraction from a signal is the most important step in signal-based fault diagnosis. Deep learning or deep neural network (DNN) is an effective method to extract features from signals. In this paper, a novel vibration signal-based bearing fault diagnosis method using DNN is proposed. First, the measured vibration signals are transformed into a new data form called multiple-domain image-representation. By this transformation, the task of signal-based fault diagnosis is transferred into the task of image classification. After that, a DNN with a multi-branch structure is proposed to handle the multiple-domain image representation data. The multi-branch structure of the proposed DNN helps to extract features in multiple domains simultaneously, and to lead to better feature extraction. Better feature extraction leads to a better performance of fault diagnosis. The effectiveness of the proposed method was verified via the experiments conducted with actual bearing fault signals and its comparisons with well-established published methods.https://www.mdpi.com/2075-1702/9/12/345bearing fault diagnosisdeep learningdeep neural network |
| spellingShingle | Van-Cuong Nguyen Duy-Tang Hoang Xuan-Toa Tran Mien Van Hee-Jun Kang A Bearing Fault Diagnosis Method Using Multi-Branch Deep Neural Network Machines bearing fault diagnosis deep learning deep neural network |
| title | A Bearing Fault Diagnosis Method Using Multi-Branch Deep Neural Network |
| title_full | A Bearing Fault Diagnosis Method Using Multi-Branch Deep Neural Network |
| title_fullStr | A Bearing Fault Diagnosis Method Using Multi-Branch Deep Neural Network |
| title_full_unstemmed | A Bearing Fault Diagnosis Method Using Multi-Branch Deep Neural Network |
| title_short | A Bearing Fault Diagnosis Method Using Multi-Branch Deep Neural Network |
| title_sort | bearing fault diagnosis method using multi branch deep neural network |
| topic | bearing fault diagnosis deep learning deep neural network |
| url | https://www.mdpi.com/2075-1702/9/12/345 |
| work_keys_str_mv | AT vancuongnguyen abearingfaultdiagnosismethodusingmultibranchdeepneuralnetwork AT duytanghoang abearingfaultdiagnosismethodusingmultibranchdeepneuralnetwork AT xuantoatran abearingfaultdiagnosismethodusingmultibranchdeepneuralnetwork AT mienvan abearingfaultdiagnosismethodusingmultibranchdeepneuralnetwork AT heejunkang abearingfaultdiagnosismethodusingmultibranchdeepneuralnetwork AT vancuongnguyen bearingfaultdiagnosismethodusingmultibranchdeepneuralnetwork AT duytanghoang bearingfaultdiagnosismethodusingmultibranchdeepneuralnetwork AT xuantoatran bearingfaultdiagnosismethodusingmultibranchdeepneuralnetwork AT mienvan bearingfaultdiagnosismethodusingmultibranchdeepneuralnetwork AT heejunkang bearingfaultdiagnosismethodusingmultibranchdeepneuralnetwork |