A journal of IEEE and CAA , publishes high-quality papers in English on original theoretical/experimental research and development in all areas of automation
Advanced Search

IEEE/CAA Journal of Automatica Sinica

  • JCR Impact Factor: 18.3, Top 1 (SCI Q1)
    CiteScore: 28.2, Top 1% (Q1)
    Google Scholar h5-index: 95， TOP 5
Turn off MathJax
Article Contents
Article Navigation >  IEEE/CAA Journal of Automatica Sinica  > 2026  > In Press, Accepted Manuscript
G. Chen, Z. Yang, J. Li, X. Chen, and C. Luo, “Towards the bi-imbalance: A pruning-based contrastive domain adaptation framework for industrial fault diagnosis,” IEEE/CAA J. Autom. Sinica, early access, 2026. doi: 10.1109/JAS.2026.126002
Citation: G. Chen, Z. Yang, J. Li, X. Chen, and C. Luo, “Towards the bi-imbalance: A pruning-based contrastive domain adaptation framework for industrial fault diagnosis,” IEEE/CAA J. Autom. Sinica, early access, 2026. doi: 10.1109/JAS.2026.126002
shu

Towards the Bi-Imbalance: A Pruning-Based Contrastive Domain Adaptation Framework for Industrial Fault Diagnosis

doi: 10.1109/JAS.2026.126002
Funds:  This work was supported by the National Key R&D Program of China (2023YFB4704900), the National Natural Science Foundation of China (62503337, 62203134, 62203169, 62422312, U25A20478), the National Natural Science Funds for Distinguished Young Scholar (62325307), Shenzhen Science and Technology Innovation Commission (KJZD20230923113801004), the Key-Area Research and Development Program of Guangdong Province (2025B0909020002), and the Open Project of State Key Laboratory of Synthetical Automation for Process Industries (SAPI-2025-KFKT-11). This work was also supported by the Intelligent Computing Center of Shenzhen University
More Information
    Abstract
  • Industrial fault diagnosis often encounters both distributional shift and severe class imbalance across domains, termed bi-imbalance. Existing unsupervised domain adaptation (UDA) methods largely overlook this, leading to poor generalization or negative transfer. We propose a Pruning-based Contrastive Domain Adaptation (PCDA) framework to address bi-imbalance without relying on pseudo labels or manual weighting. PCDA integrates two key components: 1) An imbalance-aware contrastive learning (Ia-CLR) module that leverages model pruning to detect and emphasize minority samples during self-supervised pretraining; 2) A boundary-aware adversarial domain adaptation (Ba-ADA) module that enhances feature discriminability via pruned supervised contrastive learning. The pruning-induced perturbation implicitly re-weights hard-to-learn samples from both domains. Extensive experiments on benchmark datasets demonstrate that PCDA significantly outperforms state-of-the-art UDA methods under bi-imbalanced conditions.

     

    • FullText(HTML)
  • loading
    • References(34)
  • [1]
    Z. Yang and Z. Ge, “On paradigm of industrial big data analytics: From evolution to revolution,” IEEE Trans. Ind. Inform., vol. 18, no. 12, pp. 8373–8388, Dec. 2022. doi: 10.1109/TII.2022.3190394
    [2]
    J. Zheng, Z. Yang, and Z. Ge, “Deep residual principal component analysis as feature engineering for industrial data analytics,” IEEE Trans. Instrum. Meas., vol. 73, Art. no. 2523310, Jun. 2024.
    [3]
    K. Wang, X. Yuan, X. Lang, X. Yuan, J. Han, and Y. Wang, “Concurrent historical data clustering and common feature learning for new-mode zero-shot industrial anomaly detection,” Eng. Appl. Artif. Intell., vol. 165, Art. no. 113423, Feb. 2026. doi: 10.1016/j.engappai.2025.113423
    [4]
    Y. Qi, L. Yao, B. Shen, Z. Zhu, J. Zeng, Y. Chai, and Z. Song, “Local feature augmented graph transformer for enhanced industrial process fault diagnosis,” IEEE Trans. Instrum. Meas., vol. 74, Art. no. 3559514, Sep. 2025. doi: 10.1109/tim.2025.3612657
    [5]
    J. Shen, L. Yao, J. Zeng, L. Zhou, Y. Liu, and S. Liu, “Semi-supervised learning of multiscale graph neural networks for industrial process fault diagnosis,” IEEE Sens. J., vol. 26, no. 5, pp. 7226–7241, Mar. 2026. doi: 10.1109/JSEN.2026.3652362
    [6]
    H. Chen, H. Luo, B. Huang, B. Jiang, and O. Kaynak, “Transfer learning-motivated intelligent fault diagnosis designs: A survey, insights, and perspectives,” IEEE Trans. Neural Netw. Learn. Syst., vol. 35, no. 3, pp. 2969–2983, Mar. 2024. doi: 10.1109/TNNLS.2023.3290974
    [7]
    Y. Ganin, E. Ustinova, H. Ajakan, P. Germain, H. Larochelle, F. Laviolette, M. March, and V. Lempitsky, “Domain-adversarial training of neural networks,” J. Mach. Learn. Res., vol. 17, no. 1, pp. 2096–2030, Jan. 2016.
    [8]
    T. Chen, S. Kornblith, M. Norouzi, and G. E. Hinton, “A simple framework for contrastive learning of visual representations,” arXiv preprint arXiv: abs/2002.05709, 2020.
    [9]
    Z. Huang, Z. Lei, G. Wen, X. Huang, H. Zhou, R. Yan, and X. Chen, “A multisource dense adaptation adversarial network for fault diagnosis of machinery,” IEEE Trans. Ind. Electron., vol. 69, no. 6, pp. 6298–6307, Jun. 2022. doi: 10.1109/TIE.2021.3086707
    [10]
    J. Jiao, H. Li, and J. Lin, “Self-training reinforced adversarial adaptation for machine fault diagnosis,” IEEE Trans. Ind. Electron., vol. 70, no. 11, pp. 11649–11658, Nov. 2023. doi: 10.1109/TIE.2022.3229344
    [11]
    Y. Ding, M. Jia, J. Zhuang, Y. Cao, X. Zhao, and C.-G. Lee, “Deep imbalanced domain adaptation for transfer learning fault diagnosis of bearings under multiple working conditions,” Reliab. Eng. Syst. Saf., vol. 230, Art. no. 8890, Feb. 2023. doi: 10.1016/j.ress.2022.108890
    [12]
    Z. Jiang, T. Chen, B. J. Mortazavi, and Z. Wang, “Self-damaging contrastive learning,” in Proc. 38th Int. Conf. Machine Learning, 2021, pp. 4927−4939.
    [13]
    K. Saito, K. Watanabe, Y. Ushiku, and T. Harada, “Maximum classifier discrepancy for unsupervised domain adaptation,” in Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition, Salt Lake City, USA, 2018, pp. 3723−3732.
    [14]
    Z. Chai and C. Zhao, “A fine-grained adversarial network method for cross-domain industrial fault diagnosis,” IEEE Trans. Autom. Sci. Eng., vol. 17, no. 3, pp. 1432–1442, Jul. 2020. doi: 10.1109/TASE.2019.2957232
    [15]
    M. Zareapoor, P. Shamsolmoali, and J. Yang, “Oversampling adversarial network for class-imbalanced fault diagnosis,” Mech. Syst. Signal Process., vol. 149, Art. no. 7175, Feb. 2021. doi: 10.1016/j.ymssp.2020.107175
    [16]
    D. Xiao, Y. Huang, C. Qin, Z. Liu, Y. Li, and C. Liu, “Transfer learning with convolutional neural networks for small sample size problem in machinery fault diagnosis,” Proc. Inst. Mech. Eng. Part C: J. Mech. Eng. Sci., vol. 233, no. 14, pp. 5131–5143, Jul. 2019. doi: 10.1177/0954406219840381
    [17]
    J. Kuang, G. Xu, T. Tao, and Q. Wu, “Class-imbalance adversarial transfer learning network for cross-domain fault diagnosis with imbalanced data,” IEEE Trans. Instrum. Meas., vol. 71, Art. no. 3501111, 2022.
    [18]
    X. Liu, J. Chen, K. Zhang, S. Liu, S. He, and Z. Zhou, “Cross-domain intelligent bearing fault diagnosis under class imbalanced samples via transfer residual network augmented with explicit weight self-assignment strategy based on meta data,” Knowl.-Based Syst., vol. 251, Art. no. 9272, Sep. 2022. doi: 10.1016/j.knosys.2022.109272
    [19]
    Z. Wu, H. Zhang, J. Guo, Y. Ji, and M. Pecht, “Imbalanced bearing fault diagnosis under variant working conditions using cost-sensitive deep domain adaptation network,” Expert Syst. Appl., vol. 193, Art. no. 116459, May 2022. doi: 10.1016/j.eswa.2021.116459
    [20]
    D. Arpit, S. Jastrzębski, N. Ballas, D. Krueger, E. Bengio, M. S. Kanwal, et al., “A closer look at memorization in deep networks,” in Proc. 34th Int. Conf. Machine Learning, Sydney, Australia, 2017, pp. 233−242.
    [21]
    B. Han, G. Niu, X. Yu, Q. Yao, M. Xu, I. Tsang, and M. Sugiyama, “SIGUA: Forgetting may make learning with noisy labels more robust,” in Proc. 37th Int. Conf. Machine Learning, 2020, pp. 4006−4016.
    [22]
    S. Hooker, A. Courville, G. Clark, Y. Dauphin, and A. Frome, “What do compressed deep neural networks forget?” arXiv preprint arXiv: 1911.05248, 2019.
    [23]
    P. Khosla, P. Teterwak, C. Wang, A. Sarna, Y. Tian, P. Isola, A. Maschinot, C. Liu, and D. Krishnan, “Supervised contrastive learning,” in Proc. 34th Int. Conf. Neural Information Processing Systems, Vancouver, Canada, 2020, Art. no. 1567.
    [24]
    M. Noroozi and P. Favaro, “Unsupervised learning of visual representations by solving jigsaw puzzles,” in Proc. 14th European Conf. Computer Vision, Amsterdam, The Netherlands, 2016, pp. 69−84.
    [25]
    P. Bachman, R. D. Hjelm, and W. Buchwalter, “Learning representations by maximizing mutual information across views,” in Proc. 33rd Int. Conf. Neural Information Processing Systems, Vancouver, Canada, 2019, Art. no. 1392.
    [26]
    N. Lu, H. Xiao, Z. Ma, T. Yan, and M. Han, “Domain adaptation with self-supervised learning and feature clustering for intelligent fault diagnosis,” IEEE Trans. Neural Netw. Learn. Syst., vol. 35, no. 6, pp. 7657–7670, Jun. 2024. doi: 10.1109/TNNLS.2022.3219896
    [27]
    C. Azuma, T. Ito, and T. Shimobaba, “Adversarial domain adaptation using contrastive learning,” Eng. Appl. Artif. Intell., vol. 123, Art. no. 6394, Aug. 2023.
    [28]
    Y. Le Cun, J. S. Denker, and S. A. Solla, “Optimal brain damage,” in Proc. 3rd Int. Conf. Neural Information Processing Systems, Denver, USA, 1989, pp. 598−605.
    [29]
    S. Han, J. Pool, J. Tran, and W. J. Dally, “Learning both weights and connections for efficient neural networks,” in Proc. 29th Int. Conf. Neural Information Processing Systems, Montreal, Canada, 2015, pp. 1135−1143.
    [30]
    S. Han, H. Mao, and W. J. Dally, “Deep compression: Compressing deep neural network with pruning, trained quantization and Huffman coding,” in Proc. 4th Int. Conf. Learning Representations, San Juan, Puerto Rico, 2016.
    [31]
    M. Long, J. Wang, G. Ding, J. Sun, and P. S. Yu, “Transfer joint matching for unsupervised domain adaptation,” in Proc. IEEE Conf. Computer Vision and Pattern Recognition, Columbus, USA, 2014, pp. 1410−1417.
    [32]
    W. A. Smith and R. B. Randall, “Rolling element bearing diagnostics using the Case Western Reserve University data: A benchmark study,” Mech. Syst. Signal Process., vol. 64−65, pp. 100–131, Dec. 2015. doi: 10.1016/j.ymssp.2015.04.021
    [33]
    S. Shao, S. McAleer, R. Yan, and P. Baldi, “Highly accurate machine fault diagnosis using deep transfer learning,” IEEE Trans. Ind. Inform., vol. 15, no. 4, pp. 2446–2455, Apr. 2019. doi: 10.1109/TII.2018.2864759
    [34]
    C. Ruiz-Cárcel, Y. Cao, D. Mba, L. Lao, and R. T. Samuel, “Statistical process monitoring of a multiphase flow facility,” Control Eng. Pract., vol. 42, pp. 74–88, Sep. 2015. doi: 10.1016/j.conengprac.2015.04.012
    • Related Articles
    • Supplements(0)

Catalog

    通讯作者: 陈斌, bchen63@163.com
    • 1. 

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索

    Figures(10)  / Tables(5)

    Get Citation
    PDF
    XML

    Article Metrics

    Article views (415) PDF downloads(47) Cited by()

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return