A Small-Sample Fault Diagnosis Method for Rolling Bearings Based on Balanced Distribution Adaptation and Support Vector Machine

Downloads

Authors

  • Dong Chen Jinan Technician College, China
  • Mingshan Zhang Jinan Technician College, China
  • Yaguang Gao Jinan Technician College, China

Abstract

To address the issue of low diagnostic accuracy caused by distribution differences between the source and target domains in rolling bearing fault diagnosis, this study proposes a method combining balanced distribution adaptation (BDA) and support vector machines (SVMs). The approach utilizes BDA to simultaneously minimize discrepancies in both the marginal and conditional distributions between domains, enabling effective feature alignment and enhancing the model’s cross-domain generalization in small-sample scenarios. After extracting time- and frequency-domain features, BDA adaptively adjusts the feature distributions, and SVMs are employed for fault classification. Experimental results demonstrate that the BDA-SVM method achieves over 94 % diagnostic accuracy, showcasing strong performance and robustness in bearing fault diagnosis. Compared with traditional SVMs and other methods without transfer learning, the proposed approach shows a significant improvement in diagnostic accuracy under cross-domain conditions.

Keywords:

rolling bearings, fault diagnosis, balanced distribution adaptation, transfer learning, support vector machines (SVMs)

References


  1. Xu H., Zhao Z., Xiao X., Wang Z., Bearing fault diagnosis method based on multi-adversarial and balanced distribution adaptation [in Chinese], Journal of Vibration and Shock, 44(05): 302–313, 2025.

  2. Lu H., Zheng D., Liu Y., Chang B., Bearing fault diagnosis method based on multicomponent sparse representation [in Chinese], Journal of Harbin University of Commerce (Natural Science Edition), 41(04): 442–449, 2025, https://doi.org/10.19492/j.cnki.1672-0946.2025.04.012

  3. Chen J., Tang Z., Zhou J., Rolling bearing fault diagnosis based on improved SDP and FasterNet-GCAM [in Chinese], Modern Manufacturing Engineering, (07): 129–138+41, 2025, https://doi.org/10.16731/j.cnki.1671-3133.2025.07.016

  4. Zhang Y., Research progress on rolling bearing fault diagnosis based on 2D data sets [in Chinese], Mechanical Management and Development, 40(07): 114–117+320, 2025, https://doi.org/10.16525/j.cnki.cn14-1134/th.2025.07.042

  5. Chen R., Zhu J., Hu X., Wu H., Xu X., Han X., Fault diagnosis method of rolling bearing based on multiple classifier ensemble of the weighted and balanced distribution adaptation under limited sample imbalance, ISA Transactions, 114: 434–443, 2021, https://doi.org/10.1016/j.isatra.2020.12.034

  6. Zhou Q., Ma W., Zhang Y., Guo J., A multi-source domain adaptation approach with learning domain-specific representations for bearing fault diagnosis under limited samples, Applied Soft Computing Journal, 184(Part A): 113727, 2025, https://doi.org/10.1016/j.asoc.2025.113727

  7. Ma J., Li C., Zhang G., Rolling bearing fault diagnosis based on deep learning and autoencoder information fusion, Symmetry, 14(1): 13, 2021, https://doi.org/10.3390/sym14010013

  8. Lei Y., Yang B., Jiang X., Jia F., Li N., Nandi A.K., Applications of machine learning to machine fault diagnosis: A review and roadmap, Mechanical Systems and Signal Processing, 138: 106587, 2020, https://doi.org/10.1016/j.ymssp.2019.106587

  9. Chen R., Zhu Y., Hu X., Zhao S., Zhang X., Rolling bearing fault diagnosis under different working conditions based on adaptive regularized transfer learning [in Chinese], Chinese Journal of Scientific Instrument, 42(08): 95–103, 2021, https://doi.org/10.19650/j.cnki.cjsi.J2107721

  10. Zhou H., Wang Z., Tao Q., Rolling bearing fault diagnosis based on joint structure-preserving transfer of multi-source domains [in Chinese], Journal of Vibration and Shock, 44(14): 302–310, 2025.

  11. Fu J., Zhang G., Zhang S., Bearing fault diagnosis of cross-working grinding mill based on transfer learning [in Chinese], Journal of Fujian University of Technology, 22(04): 393–400, 2024.

  12. Pan X., Ge K., Dong F., Intelligent fault diagnosis of hoist bearing based on feature transfer learning [in Chinese], Industrial and Mine Automation, 48(09): 1–7+32, 2022, https://doi.org/10.13272/j.issn.1671-251x.17980

  13. Wan A., Yang J., Wang J., Chen T., Liao X., Huang J., Du X., Aero engine gear fault diagnosis based on deep learning vibration [in Chinese], Test and Diagnosis, 42(06): 1062–1067+1239, 2022, https://doi.org/10.16450/j.cnki.issn.1004-6801.2022.06.002

  14. Hu W., Zhang Y., Centrifugal pump rolling bearing fault diagnosis based on VMD and random forest [in Chinese], Mechanical and Electrical Engineering Technology, 51(03): 78–82, 2022.

  15. Wang J., Zhou C., Zhang Z., Meng N., Du G., Jin X., Zhang C., A fault diagnosis method using decomposition denoising improved multiscale weighted permutation entropy and one-versus-one least squares twin SVM, Measurement, 255: 118012, 2025, https://doi.org/10.1016/j.measurement.2025.118012

  16. Liu J., Maimaitireyim A., Xiang Z., Xie L., Fan bearing fault diagnosis based on improved grey wolf optimization algorithm and SVM, Journal of Mechanical Transmission, 47(09): 160–169, 2023, https://doi.org/10.16578/j.issn.1004.2539.2023.09.022

  17. Bu C., Liu Y., Zhang W., Fault diagnosis model of shearer bearing based on PSO-SVM [in Chinese], Industrial and Mine Automation, 51(S1): 44–46, 2025.

  18. Guo Y., Liu Y., Zhang Z., Wang Y., Xue P., Du C., Li W., Research on fault detection and diagnosis of carbon dioxide heat pump systems in buildings based on transfer learning, Journal of Building Engineering, 85: 108774, 2024, https://doi.org/10.1016/j.jobe.2024.108774

  19. Wang B., Liu Y., Liao Y., Sensitivity analysis of time-domain characteristic indicators of rolling bearing fault signals [in Chinese], Bearing, (10): 45–48, 2015, https://doi.org/10.19533/j.issn1000-3762.2015.10.014

  20. Tang J., Wang E., Zhu J., Tan W., Research on fault diagnosis of automotive water pump bearings based on frequency domain features and support vector machines [in Chinese], Machine Tool and Hydraulic, 46(13): 163–167+155, 2018, https://doi.org/10.3969/j.issn.1001-3881.2018.13.040

  21. Li D., Feng J., Fault diagnosis of rolling bearings in medical devices based on vibration signal analysis [in Chinese], Value Engineering, 44(24): 21–23, 2025, https://doi.org/10.3969/j.issn.1006-4311.2025.24.007

  22. Wang T., Liu T., Liu Y., Wang Z., Bearing fault transfer diagnosis with balanced distribution adaptation under variable working conditions [in Chinese], Mechanical Science and Technology, 42(08): 1316–1323, 2023, https://doi.org/10.13433/j.cnki.1003-8728.20220058

  23. Lei Y., Yang B., Jiang X., Jia F., Li N., Nandi A.K., Applications of machine learning to machine fault diagnosis: A review and roadmap, Mechanical Systems and Signal Processing, 138: 106587, 2020, https://doi.org/10.1016/j.ymssp.2019.106587

  24. Weiss K., Khoshgoftaar T.M., Wang D., A survey of transfer learning, Journal of Big Data, 3(1): 1–40, 2016, https://doi.org/10.1186/s40537-016-0043-6

  25. Wang J., Chen Y., Hao S., Feng W., Shen Z., Balanced distribution adaptation for transfer learning, [in:] 2017 IEEE International Conference on Data Mining (ICDM), pp. 1129–1134, 2017, https://doi.org/10.1109/ICDM.2017.150

  26. Cortes C., Vapnik V., Support-vector networks, Machine Learning, 20: 273–297, 1995, https://doi.org/10.1007/BF00994018

  27. Scholkopf B., Smola A.J., Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond, MIT Press, 2002, https://doi.org/10.7551/mitpress/4175.001.0001