RESEARCH PAPER
Fault diagnosis method of automobile rolling bearing based on transfer learning and improved DenseNet
More details
Hide details
1
School of Aviation and Transportation, Jiansu College of Engineering and Technology, China
2
School of Mechanical Engineering, Xinjiang University, China
Submission date: 2024-08-27
Final revision date: 2024-09-23
Acceptance date: 2024-10-15
Online publication date: 2024-10-20
Publication date: 2024-10-20
Corresponding author
Xinxin Lu
School of Aviation and Transportation, Jiansu College of Engineering and Technology, 87 Qingnian Middle Road, Nantong City, Jiangsu Pro, 226001, Nantong, China
Eksploatacja i Niezawodność – Maintenance and Reliability 2025;27(2):194675
HIGHLIGHTS
- The conversion of vibration data into image data improves diagnostic accuracy.
- Sub domain adaptation improves the diagnostic ability for cross condition data.
- Attention mechanism improves diagnostic efficiency and reduces diagnostic time.
KEYWORDS
TOPICS
ABSTRACT
Aiming at the problems caused by ignoring the time series characteristics, the scarcity of labeled data and the long diagnosis time in the fault diagnosis of one-dimensional vibration signals of automobile bearings, a new method combining improved DenseNet and transfer learning is proposed in this study. This method uses Recurrent Plot (RP) technology to convert one-dimensional vibration data into two-dimensional images to fully tap the potential value of time series. By optimizing the DenseNet network structure, the fault features are extracted effectively. Lightweight network design and MobileViT Attention mechanism are used to reduce the number of parameters and improve computing efficiency. With the help of transfer learning technology, the fault features in the source domain are transferred to the target domain, which solves the problem of cross-condition diagnosis and greatly reduces the diagnosis time. The experimental results show that the proposed method can improve the accuracy of fault identification and diagnosis efficiency, and achieve accurate classification.
ACKNOWLEDGEMENTS
The work is supported by theNational Vocational Education Teacher Teaching Innovation Team Project (ZI2021020406), Higher Education Project of Jiangsu Province (2021JSJG036), Nantong Basic Science Research Youth Innovation Project (JC12022090), Nantong Scientific Research Project (MS2023013),Research Projects of Jiangsu College of Engineering and Technology (GYKY/2022/13, GYKY/2022/14). The authors also wish to thank them for their financial support.
REFERENCES (21)
1.
Wang X, Yao Y, Gao C. Wasserstein Distance- EEMD Enhanced Multi-Head Graph Attention Network for Rolling Bearing Fault Diagnosis Under Different Working Conditions. Eksploatacja i Niezawodność – Maintenance and Reliability. 2024;26(2),
https://doi.org/10.17531/ein/1....
2.
Li Tao1, Duan Lixiang, Zhang Dongning, Zhao Shangxin, Huang Hui, Bi Caixia, Yuan Zhuang. Application of adaptive convolutional neural network in rotating machinery fault diagnosis. Journal of Vibration and Shock, 2020, 39(16): 275-282,
https://doi.org/10.13465/j.cnk....
3.
Huang Xundi, Pang Xiongwen. Research review on Fault diagnosis of intelligent devices based on Deep learning. Computer Science,2023,50(05):93-102,
https://doi.org/10.11896/jsjkx....
4.
Antosz K. Maintenance – identification and analysis of the competency gap. Eksploatacja i Niezawodność–Maintenance and Reliability. 2018;20(3):484-94,
https://doi.org/10.17531/ein.2....
5.
Alexakos C T, Karnavas Y L, Drakaki M,et al.A Combined Short Time Fourier Transform and Image Classification Transformer Model for Rolling Element Bearings Fault Diagnosis in Electric Motors. 2021,
https://doi.org/10.3390/make30....
6.
Lu Zhi-Jie, Wang Zhi-Liang, Yan Xiao-An, et al. Application of variational mode decompositionmethod in bearing fault diagnosis. Lubrication and sealing :1-15[2024-04-25],
http://kns.cnki.net/kcms/detai....
7.
TANG Jikai, Lu Yixiang, Bai Zhuangzhuang, et al. Fault diagnosis of Rolling Bearing based on synchronous compression Wavelet transform and CNN. Sensors and Microsystems,2022,41(06):130-133,
https://doi.org/10.13873/J.100....
8.
Lei Yaguo, Jia Feng, Kong Detong, et al. Opportunities and Challenges of Mechanical Intelligent Fault Diagnosis Based on Big Data. Chinese Journal of Mechanical Engineering,2018,54(05):94-104,
https://doi.org/10.3901/JME.20....
9.
Barshikar RR, Ghongade HP, Bhadre A, Pawar HU, Rane HS. Defect Categorization of Ribbon Blender Worm Gearbox Worm Wheel and Bearing Based on Artificial Neural Network. Eksploatacja i Niezawodność–Maintenance and Reliability. 2024;26(2),
https://doi.org/10.17531/ein/1....
10.
Wang Peng, Li Danqing, Wang Heng. Fault Diagnosis Algorithm of Rolling Bearing Based on Improved Alternate Transfer Learning. Journal of Vibration and Shock, 2019,43(05):239-249,
https://doi.org/10.13465/j.cnk....
11.
Jiang Kaizheng, Lv Liping. Optimization of Engine fault diagnosis with Stack noise reduction autoencoder based on improved Sand Cat swarm optimization algorithm. Journal of Mechanical Design, 2019,40(08):56-62,
https://doi.org/10.13841/j.cnk....
12.
Chen Xiang, Liu Qinming, Hu Jiarui. Bearing fault diagnosis and life prediction based on attentionmechanism and long and short term memory network based on multi-source sensor data. Information and Control :1-15[2024-04-25],
https://doi.org/10.13976/j.cnk....
13.
Du Y, Wang A, Wang S,et al. Fault Diagnosis under Variable Working Conditions Based on STFT and Transfer Deep Residual Network. Shock and Vibration, 2020.
https://doi.org/10.1155/2020/1....
14.
Shao Haidong, Zhang Xiaoyang, Cheng Junsheng, et al. Bearing Intelligent Fault Diagnosis Based on uplifting Deep Migration Autoencoder. Chinese Journal of Mechanical Engineering, 2019,56(09):84-90,
https://doi.org/10.3901/JME.20....
15.
Wang Jian, Wu Na, Yang Jianwei, et al. Axle box fault diagnosis method based on improved DANN and attention mechanism. Machine tools and Hydraulics :1-9[2024-04-25],
https://doi.org/10.3969/j.issn....
16.
Wang Keding, Li Jingzhao, Shi Qing, et al. Fault Diagnosis of Mine Fan Bearing Based on Deep Transfer Learning. Machine Tool & Hydraulics,2023,51(22):209-214,
https://doi.org/10.3969/j.issn....
17.
Gong Xiaoyun, Zhi Zeheng, Du Wenliao, et al. Multi-source heterogeneous Adaptive Transfer Learning for Small Sample Complex Faults of Rotary motor. Machine Tools & Hydraulics, 2019,52(03):209-216,
https://doi.org/10.3969/j.issn....
18.
Cui Fuwei, Wu Xuanxuan, Chen Yufeng, et al. A review of domain adaptive methods for fusion ofknowledge.Computer Science,2023,50(08):142-149. (in Chinese),
https://doi.org/10.11896/jsjkx....
19.
Chen Pan, Yuan Yiping, Ma Junyan, et al. Fault diagnosis of rolling bearings based on CNN-SN and unsupervised domain adaptation. Bearing:1-9[2024-04-25],
http://kns.cnki.net/kcms/detai....
20.
Yajing Zhou, Xinyu Long, Mingwei Sun, Zengqiang Chen. Bearing fault diagnosis based on Gramian angular field and DenseNet. Mathematical Biosciences and Engineering, 2022, 19(12): 14086-14101,
https://doi.org/10.3934/mbe.20....
21.
T.Zhao and N.Qiao, "Research on Target Detection Technology of Aircraft Satellite Images Based on Improved YOLOv5 Model," 2023 4th International Conference on Big Data & Artificial Intelligence & Software Engineering (ICBASE), Nanjing, China, 2023, pp.89-94,
https://doi.org/10.1109/ICBASE....