Fault Diagnosis Method Based on MTF-ResDSCNN Two-dimensional Image
In order to effectively capture the fault features contained in the vibration signals of the rotating machinery and complete the fault diagnosis task efficiently, a fault diagnosis model combining two-dimensional image features and lightweight neural network is designed. Firstly, the collected one-d...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Office of Journal of Mechanical Transmission
2024-02-01
|
| Series: | Jixie chuandong |
| Subjects: | |
| Online Access: | http://www.jxcd.net.cn/thesisDetails#10.16578/j.issn.1004.2539.2024.02.024 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841546935997038592 |
|---|---|
| author | Hu Mengnan Yang Xiwang Huang Jinying Hu Hongjun Wang Cheng |
| author_facet | Hu Mengnan Yang Xiwang Huang Jinying Hu Hongjun Wang Cheng |
| author_sort | Hu Mengnan |
| collection | DOAJ |
| description | In order to effectively capture the fault features contained in the vibration signals of the rotating machinery and complete the fault diagnosis task efficiently, a fault diagnosis model combining two-dimensional image features and lightweight neural network is designed. Firstly, the collected one-dimensional vibration signals are decomposed by modified ensemble empirical mode decomposition (MEEMD) to obtain the intrinsic mode function (IMF) components, and the corresponding IMF components are selected for sum reconstruction to enhance the amplitude fluctuation of vibration signals. Then, Markov transition field (MTF) could be used to more effectively characterize the fault features in the reconstructed signals. Secondly, the 2D feature map generated by MTF is input into residual depth separable convolutional neural network (ResDSCNN) for feature extraction and fault diagnosis. The planetary gearbox fault data set is used to verify the performance of the model, and the results show that the diagnosis accuracy of the model for all kinds of gear faults can reach more than 98%. |
| format | Article |
| id | doaj-art-3e05e92201b24c558f27bf3c833073fe |
| institution | Kabale University |
| issn | 1004-2539 |
| language | zho |
| publishDate | 2024-02-01 |
| publisher | Editorial Office of Journal of Mechanical Transmission |
| record_format | Article |
| series | Jixie chuandong |
| spelling | doaj-art-3e05e92201b24c558f27bf3c833073fe2025-01-10T14:59:47ZzhoEditorial Office of Journal of Mechanical TransmissionJixie chuandong1004-25392024-02-014817017649593252Fault Diagnosis Method Based on MTF-ResDSCNN Two-dimensional ImageHu MengnanYang XiwangHuang JinyingHu HongjunWang ChengIn order to effectively capture the fault features contained in the vibration signals of the rotating machinery and complete the fault diagnosis task efficiently, a fault diagnosis model combining two-dimensional image features and lightweight neural network is designed. Firstly, the collected one-dimensional vibration signals are decomposed by modified ensemble empirical mode decomposition (MEEMD) to obtain the intrinsic mode function (IMF) components, and the corresponding IMF components are selected for sum reconstruction to enhance the amplitude fluctuation of vibration signals. Then, Markov transition field (MTF) could be used to more effectively characterize the fault features in the reconstructed signals. Secondly, the 2D feature map generated by MTF is input into residual depth separable convolutional neural network (ResDSCNN) for feature extraction and fault diagnosis. The planetary gearbox fault data set is used to verify the performance of the model, and the results show that the diagnosis accuracy of the model for all kinds of gear faults can reach more than 98%.http://www.jxcd.net.cn/thesisDetails#10.16578/j.issn.1004.2539.2024.02.024Markov transition fieldDepth separable convolutionFault diagnosisMEEMD |
| spellingShingle | Hu Mengnan Yang Xiwang Huang Jinying Hu Hongjun Wang Cheng Fault Diagnosis Method Based on MTF-ResDSCNN Two-dimensional Image Jixie chuandong Markov transition field Depth separable convolution Fault diagnosis MEEMD |
| title | Fault Diagnosis Method Based on MTF-ResDSCNN Two-dimensional Image |
| title_full | Fault Diagnosis Method Based on MTF-ResDSCNN Two-dimensional Image |
| title_fullStr | Fault Diagnosis Method Based on MTF-ResDSCNN Two-dimensional Image |
| title_full_unstemmed | Fault Diagnosis Method Based on MTF-ResDSCNN Two-dimensional Image |
| title_short | Fault Diagnosis Method Based on MTF-ResDSCNN Two-dimensional Image |
| title_sort | fault diagnosis method based on mtf resdscnn two dimensional image |
| topic | Markov transition field Depth separable convolution Fault diagnosis MEEMD |
| url | http://www.jxcd.net.cn/thesisDetails#10.16578/j.issn.1004.2539.2024.02.024 |
| work_keys_str_mv | AT humengnan faultdiagnosismethodbasedonmtfresdscnntwodimensionalimage AT yangxiwang faultdiagnosismethodbasedonmtfresdscnntwodimensionalimage AT huangjinying faultdiagnosismethodbasedonmtfresdscnntwodimensionalimage AT huhongjun faultdiagnosismethodbasedonmtfresdscnntwodimensionalimage AT wangcheng faultdiagnosismethodbasedonmtfresdscnntwodimensionalimage |