IDEAS home Printed from https://ideas.repec.org/a/spr/joinma/v35y2024i4d10.1007_s10845-023-02131-2.html
   My bibliography  Save this article

A dual-attention feature fusion network for imbalanced fault diagnosis with two-stream hybrid generated data

Author

Listed:
  • Chenze Wang

    (Tongji University)

  • Han Wang

    (Tongji University)

  • Min Liu

    (Tongji University)

Abstract

Deep learning-based fault diagnosis models achieve great success with sufficient balanced data, but the imbalanced dataset in real industrial scenarios will seriously affect the performance of various popular deep learning models. Data generation-based strategy provides a solution by expanding the number of minority samples. However, many data-generation methods cannot generate high-quality samples when the imbalanced ratio is high. To address these problems, a dual-attention feature fusion network (DAFFN) with two-stream hybrid-generated data is proposed. First, the two-stream hybrid generator including a generative model and an oversampling technique is adopted to generate minority fault data. Then, the convolutional neural network is used to extract features from hybrid-generated data. In particular, a feature fusion network with a dual-attention mechanism, i.e., a channel attention mechanism and a layer attention mechanism are designed to learn channel-level and layer-level weights of the features. Extensive results on two bearing datasets indicate that the proposed framework achieves outstanding performance in various high imbalanced-ratio cases.

Suggested Citation

  • Chenze Wang & Han Wang & Min Liu, 2024. "A dual-attention feature fusion network for imbalanced fault diagnosis with two-stream hybrid generated data," Journal of Intelligent Manufacturing, Springer, vol. 35(4), pages 1707-1719, April.
    • Handle: RePEc:spr:joinma:v:35:y:2024:i:4:d:10.1007_s10845-023-02131-2
    DOI: 10.1007/s10845-023-02131-2
    as

    Download full text from publisher

    File URL: http://link.springer.com/10.1007/s10845-023-02131-2
    File Function: Abstract
    Download Restriction: Access to the full text of the articles in this series is restricted.
    File URL: https://libkey.io/10.1007/s10845-023-02131-2?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to search for a different version of it.

    References listed on IDEAS

    as
    1. Qifa Xu & Shixiang Lu & Weiyin Jia & Cuixia Jiang, 2020. "Imbalanced fault diagnosis of rotating machinery via multi-domain feature extraction and cost-sensitive learning," Journal of Intelligent Manufacturing, Springer, vol. 31(6), pages 1467-1481, August.
    2. Jia Luo & Jinying Huang & Hongmei Li, 2021. "A case study of conditional deep convolutional generative adversarial networks in machine fault diagnosis," Journal of Intelligent Manufacturing, Springer, vol. 32(2), pages 407-425, February.
    3. Gang Wang & Feng Zhang & Bayi Cheng & Fang Fang, 2021. "DAMER: a novel diagnosis aggregation method with evidential reasoning rule for bearing fault diagnosis," Journal of Intelligent Manufacturing, Springer, vol. 32(1), pages 1-20, January.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Gao, Bixuan & Kong, Xiangyu & Li, Shangze & Chen, Yi & Zhang, Xiyuan & Liu, Ziyu & Lv, Weijia, 2024. "Enhancing anomaly detection accuracy and interpretability in low-quality and class imbalanced data: A comprehensive approach," Applied Energy, Elsevier, vol. 353(PB).
    2. Wang, Zixuan & Qin, Bo & Sun, Haiyue & Zhang, Jian & Butala, Mark D. & Demartino, Cristoforo & Peng, Peng & Wang, Hongwei, 2023. "An imbalanced semi-supervised wind turbine blade icing detection method based on contrastive learning," Renewable Energy, Elsevier, vol. 212(C), pages 251-262.
    3. Cuixia Jiang & Hao Chen & Qifa Xu & Xiangxiang Wang, 2023. "Few-shot fault diagnosis of rotating machinery with two-branch prototypical networks," Journal of Intelligent Manufacturing, Springer, vol. 34(4), pages 1667-1681, April.
    4. Rombach, Katharina & Michau, Gabriel & Fink, Olga, 2023. "Controlled generation of unseen faults for Partial and Open-Partial domain adaptation," Reliability Engineering and System Safety, Elsevier, vol. 230(C).
    5. Rui Zhang & Na Zhao & Liuhu Fu & Xiaolu Bai & Jianghui Cai, 2023. "Recognizing defects in stainless steel welds based on multi-domain feature expression and self-optimization," Journal of Intelligent Manufacturing, Springer, vol. 34(3), pages 1293-1309, March.
    6. Elaheh Jafarigol & Theodore B. Trafalis, 2024. "A distributed approach to meteorological predictions: addressing data imbalance in precipitation prediction models through federated learning and GANs," Computational Management Science, Springer, vol. 21(1), pages 1-23, June.
    7. Jia Luo & Jingying Huang & Jiancheng Ma & Siyuan Liu, 2024. "Application of self-attention conditional deep convolutional generative adversarial networks in the fault diagnosis of planetary gearboxes," Journal of Risk and Reliability, , vol. 238(2), pages 260-273, April.
    8. Yi Zhang & Peng Peng & Chongdang Liu & Yanyan Xu & Heming Zhang, 2022. "A sequential resampling approach for imbalanced batch process fault detection in semiconductor manufacturing," Journal of Intelligent Manufacturing, Springer, vol. 33(4), pages 1057-1072, April.
    9. Xie, Tianming & Xu, Qifa & Jiang, Cuixia & Lu, Shixiang & Wang, Xiangxiang, 2023. "The fault frequency priors fusion deep learning framework with application to fault diagnosis of offshore wind turbines," Renewable Energy, Elsevier, vol. 202(C), pages 143-153.
    10. Bowen Zhang & Xianli Liu & Caixu Yue & Shaoyang Liu & Xuebing Li & Steven Y. Liang & Lihui Wang, 2025. "An imbalanced data learning approach for tool wear monitoring based on data augmentation," Journal of Intelligent Manufacturing, Springer, vol. 36(1), pages 399-420, January.
    11. Peng Jieyang & Andreas Kimmig & Wang Dongkun & Zhibin Niu & Fan Zhi & Wang Jiahai & Xiufeng Liu & Jivka Ovtcharova, 2023. "A systematic review of data-driven approaches to fault diagnosis and early warning," Journal of Intelligent Manufacturing, Springer, vol. 34(8), pages 3277-3304, December.
    12. Liu, Jiaquan & Hou, Lei & Zhang, Rui & Sun, Xingshen & Yu, Qiaoyan & Yang, Kai & Zhang, Xinru, 2023. "Explainable fault diagnosis of oil-gas treatment station based on transfer learning," Energy, Elsevier, vol. 262(PA).
    13. Chuanxia Jian & Yinhui Ao, 2023. "Imbalanced fault diagnosis based on semi-supervised ensemble learning," Journal of Intelligent Manufacturing, Springer, vol. 34(7), pages 3143-3158, October.
    14. Jin, Zhenglei & Xu, Qifa & Jiang, Cuixia & Wang, Xiangxiang & Chen, Hao, 2023. "Ordinal few-shot learning with applications to fault diagnosis of offshore wind turbines," Renewable Energy, Elsevier, vol. 206(C), pages 1158-1169.
    15. Shixu Sun & Xiaofeng Hu & Yingchao Liu, 2022. "An imbalanced data learning method for tool breakage detection based on generative adversarial networks," Journal of Intelligent Manufacturing, Springer, vol. 33(8), pages 2441-2455, December.
    16. Yifan Qie & Benjamin Schleich & Nabil Anwer, 2025. "Generative adversarial networks and hessian locally linear embedding for geometric variations management in manufacturing," Journal of Intelligent Manufacturing, Springer, vol. 36(2), pages 1033-1062, February.
    17. Chao Huang & Siqi Bu & Hiu Hung Lee & Kwong Wah Chan & Winco K. C. Yung, 2024. "Prognostics and health management for induction machines: a comprehensive review," Journal of Intelligent Manufacturing, Springer, vol. 35(3), pages 937-962, March.
    18. Hanting Zhou & Wenhe Chen & Jing Liu & Longsheng Cheng & Min Xia, 2024. "Trustworthy and intelligent fault diagnosis with effective denoising and evidential stacked GRU neural network," Journal of Intelligent Manufacturing, Springer, vol. 35(7), pages 3523-3542, October.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:spr:joinma:v:35:y:2024:i:4:d:10.1007_s10845-023-02131-2. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Sonal Shukla or Springer Nature Abstracting and Indexing (email available below). General contact details of provider: http://www.springer.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.