|
|
基于无源域自适应的滚动轴承故障诊断策略研究
|
Abstract:
本文提出了一种基于无源域自适应的滚动轴承故障诊断策略，旨在解决源域数据缺失时的领域自适应问题。该策略通过源域模型的预训练与目标域数据的伪标签生成与过滤相结合，实现了无源域条件下的有效领域适应。具体地，利用源域模型对目标域数据进行伪标签生成，通过信息熵计算和阈值过滤筛选出可靠的故障原型，进而计算每个目标域样本与故障原型的余弦相似度，从而生成噪声较低的伪标签。实验结果表明，本文方法在多个迁移任务中均表现出优异的性能，平均准确率达95.03%，尤其在处理源域和目标域数据分布差异较大的情况下，能够有效提高故障诊断的准确率。与传统的深度学习和领域自适应方法相比，本文方法在无源域自适应故障诊断中具有显著优势。
This paper proposes a source free domain adaptation strategy for rolling bearing fault diagnosis, aiming to address the domain adaptation problem when source domain data is missing. The method combines pretraining a source domain model with pseudo-label generation and filtering for target domain data to achieve effective domain adaptation under source-free conditions. Specifically, the source domain model is used to generate pseudo-labels for the target domain data. Reliable fault prototypes are selected through information entropy calculation and threshold filtering. Then, the cosine similarity between each target domain sample and the fault prototypes is computed to generate pseudo-labels with reduced noise. Experimental results demonstrate that the proposed method performs excellently across multiple transfer tasks, with an average accuracy of 95.03%. In particular, it significantly improves fault diagnosis accuracy when dealing with large distribution differences between source and target domain data. Compared with traditional deep learning and domain adaptation methods, the proposed method shows significant advantages in source free domain adaptation for fault diagnosis.
| [1] | Zhang, S., Zhang, S., Wang, B. and Habetler, T.G. (2020) Deep Learning Algorithms for Bearing Fault Diagnostics—A Comprehensive Review. IEEE Access, 8, 29857-29881. https://doi.org/10.1109/access.2020.2972859 |
| [2] | Bediaga, I., Mendizabal, X., Arnaiz, A. and Munoa, J. (2013) Ball Bearing Damage Detection Using Traditional Signal Processing Algorithms. IEEE Instrumentation & Measurement Magazine, 16, 20-25. https://doi.org/10.1109/mim.2013.6495676 |
| [3] | Hoang, D. and Kang, H. (2019) A Survey on Deep Learning Based Bearing Fault Diagnosis. Neurocomputing, 335, 327-335. https://doi.org/10.1016/j.neucom.2018.06.078 |
| [4] | Chen, X., Yang, R., Xue, Y., Huang, M., Ferrero, R. and Wang, Z. (2023) Deep Transfer Learning for Bearing Fault Diagnosis: A Systematic Review since 2016. IEEE Transactions on Instrumentation and Measurement, 72, 1-21. https://doi.org/10.1109/tim.2023.3244237 |
| [5] | Lu, W., Liang, B., Cheng, Y., Meng, D., Yang, J. and Zhang, T. (2017) Deep Model Based Domain Adaptation for Fault Diagnosis. IEEE Transactions on Industrial Electronics, 64, 2296-2305. https://doi.org/10.1109/tie.2016.2627020 |
| [6] | Tian, Y., Lou, Y., Ou, J., Huang, X. and Sun, Z. (2025) Fault Diagnostic Method Based on Transfer Dynamic Deep Learning for Few Shot Temporal-Spatial Correlation Industry Process. The Canadian Journal of Chemical Engineering. https://doi.org/10.1002/cjce.25614 |
| [7] | Jia, T., Tian, Y., Yin, Z., Zhang, W. and Sun, Z. (2025) Data-Free Stealing Attack and Defense Strategy for Industrial Fault Diagnosis System. Chemical Engineering Research and Design, 216, 200-215. https://doi.org/10.1016/j.cherd.2025.02.031 |
| [8] | Li, J., Yu, Z., Du, Z., Zhu, L. and Shen, H.T. (2024) A Comprehensive Survey on Source-Free Domain Adaptation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46, 5743-5762. https://doi.org/10.1109/tpami.2024.3370978 |
| [9] | Nayana, B.R. and Geethanjali, P. (2017) Analysis of Statistical Time-Domain Features Effectiveness in Identification of Bearing Faults from Vibration Signal. IEEE Sensors Journal, 17, 5618-5625. https://doi.org/10.1109/jsen.2017.2727638 |
| [10] | Fang, X., Zheng, J. and Jiang, B. (2024) A Rolling Bearing Fault Diagnosis Method Based on Vibro-Acoustic Data Fusion and Fast Fourier Transform (FFT). International Journal of Data Science and Analytics. https://doi.org/10.1007/s41060-024-00609-7 |
| [11] | Kankar, P.K., Sharma, S.C. and Harsha, S.P. (2011) Rolling Element Bearing Fault Diagnosis Using Wavelet Transform. Neurocomputing, 74, 1638-1645. https://doi.org/10.1016/j.neucom.2011.01.021 |
| [12] | Liu, Y., Chai, Y., Liu, B. and Wang, Y. (2021) Bearing Fault Diagnosis Based on Energy Spectrum Statistics and Modified Mayfly Optimization Algorithm. Sensors, 21, Article 2245. https://doi.org/10.3390/s21062245 |
| [13] | Zhou, J., Xiao, M., Niu, Y. and Ji, G. (2022) Rolling Bearing Fault Diagnosis Based on WGWOA-VMD-SVM. Sensors, 22, Article 6281. https://doi.org/10.3390/s22166281 |
| [14] | Wan, L., Gong, K., Zhang, G., Yuan, X., Li, C. and Deng, X. (2021) An Efficient Rolling Bearing Fault Diagnosis Method Based on Spark and Improved Random Forest Algorithm. IEEE Access, 9, 37866-37882. https://doi.org/10.1109/access.2021.3063929 |
| [15] | Tian, J., Morillo, C., Azarian, M.H. and Pecht, M. (2016) Motor Bearing Fault Detection Using Spectral Kurtosis-Based Feature Extraction Coupled with k-Nearest Neighbor Distance Analysis. IEEE Transactions on Industrial Electronics, 63, 1793-1803. https://doi.org/10.1109/tie.2015.2509913 |
| [16] | Guo, Z., Yang, M. and Huang, X. (2022) Bearing Fault Diagnosis Based on Speed Signal and CNN Model. Energy Reports, 8, 904-913. https://doi.org/10.1016/j.egyr.2022.08.041 |
| [17] | Liu, J., Pan, C., Lei, F., Hu, D. and Zuo, H. (2021) Fault Prediction of Bearings Based on LSTM and Statistical Process Analysis. Reliability Engineering & System Safety, 214, Article ID: 107646. https://doi.org/10.1016/j.ress.2021.107646 |
| [18] | Tian, Y., Shen, J., Wang, A., Li, Z. and Huang, X. (2024) Data Augmentation and Fault Diagnosis for Imbalanced Industrial Process Data Based on Residual Wasserstein Generative Adversarial Network with Gradient Penalty. Journal of Chemometrics, 38, e3624. https://doi.org/10.1002/cem.3624 |
| [19] | Zou, Y., Liu, Y., Deng, J., Jiang, Y. and Zhang, W. (2021) A Novel Transfer Learning Method for Bearing Fault Diagnosis under Different Working Conditions. Measurement, 171, Article ID: 108767. https://doi.org/10.1016/j.measurement.2020.108767 |
| [20] | Yang, B., Lei, Y., Jia, F. and Xing, S. (2019) An Intelligent Fault Diagnosis Approach Based on Transfer Learning from Laboratory Bearings to Locomotive Bearings. Mechanical Systems and Signal Processing, 122, 692-706. https://doi.org/10.1016/j.ymssp.2018.12.051 |
| [21] | Li, X., Yuan, P., Su, K., Li, D., Xie, Z. and Kong, X. (2024) Innovative Integration of Multi-Scale Residual Networks and MK-MMD for Enhanced Feature Representation in Fault Diagnosis. Measurement Science and Technology, 35, Article ID: 086108. https://doi.org/10.1088/1361-6501/ad4380 |
| [22] | Ganin, Y., Ustinova, E., Ajakan, H., et al. (2016) Domain-Adversarial Training of Neural Networks. Journal of Machine Learning Research, 17, 1-35. |
| [23] | Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., et al. (2020) Generative Adversarial Networks. Communications of the ACM, 63, 139-144. https://doi.org/10.1145/3422622 |
| [24] | Wu, H., Li, J., Zhang, Q., Tao, J. and Meng, Z. (2022) Intelligent Fault Diagnosis of Rolling Bearings under Varying Operating Conditions Based on Domain-Adversarial Neural Network and Attention Mechanism. ISA Transactions, 130, 477-489. https://doi.org/10.1016/j.isatra.2022.04.026 |
| [25] | Fang, Y., Yap, P., Lin, W., Zhu, H. and Liu, M. (2024) Source-Free Unsupervised Domain Adaptation: A Survey. Neural Networks, 174, Article ID: 106230. https://doi.org/10.1016/j.neunet.2024.106230 |
| [26] | Kurmi, V.K., Subramanian, V.K. and Namboodiri, V.P. (2021) Domain Impression: A Source Data Free Domain Adaptation Method. 2021 IEEE Winter Conference on Applications of Computer Vision (WACV), Waikoloa, 3-8 January 2021, 615-625. https://doi.org/10.1109/wacv48630.2021.00066 |
| [27] | Agarwal, P., Paudel, D.P., Zaech, J. and Van Gool, L. (2022) Unsupervised Robust Domain Adaptation without Source Data. 2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Waikoloa, 3-8 January 2022, 2805-2814. https://doi.org/10.1109/wacv51458.2022.00286 |
| [28] | Cascante-Bonilla, P., Tan, F., Qi, Y. and Ordonez, V. (2021) Curriculum Labeling: Revisiting Pseudo-Labeling for Semi-Supervised Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 35, 6912-6920. https://doi.org/10.1609/aaai.v35i8.16852 |
| [29] | Neupane, D. and Seok, J. (2020) Bearing Fault Detection and Diagnosis Using Case Western Reserve University Dataset with Deep Learning Approaches: A Review. IEEE Access, 8, 93155-93178. https://doi.org/10.1109/access.2020.2990528 |
