IDEAS home Printed from https://ideas.repec.org/a/gam/jmathe/v10y2022i15p2796-d882154.html
   My bibliography  Save this article

SMoCo: A Powerful and Efficient Method Based on Self-Supervised Learning for Fault Diagnosis of Aero-Engine Bearing under Limited Data

Author

Listed:
  • Zitong Yan

    (School of Reliability and Systems Engineering, Beihang University, Beijing 100191, China)

  • Hongmei Liu

    (School of Reliability and Systems Engineering, Beihang University, Beijing 100191, China)

Abstract

Vibration signals collected in real industrial environments are usually limited and unlabeled. In this case, fault diagnosis methods based on deep learning tend to perform poorly. Previous work mainly used the unlabeled data of the same diagnostic object to improve the diagnostic accuracy, but it did not make full use of the easily available unlabeled signals from different sources. In this study, a signal momentum contrast for unsupervised representation learning (SMoCo) based on the contrastive learning algorithm—momentum contrast for unsupervised visual representation Learning (MoCo)—is proposed. It can learn how to automatically extract fault features from unlabeled data collected from different diagnostic objects and then transfer this ability to target diagnostic tasks. On the structure, SMoCo increases the stability by adding batch normalization to the multilayer perceptron (MLP) layer of MoCo and increases the flexibility by adding a predictor to the query network. Using the data augmentation method, SMoCo performs feature extraction on vibration signals from both time and frequency domains, which is called signal multimodal learning (SML). It has been proved by experiments that after pre-training with artificially injected fault bearing data, SMoCo can learn a powerful and robust feature extractor, which can greatly improve the accuracy no matter the target diagnostic data with different working conditions, different failure modes, or even different types of equipment from the pre-training dataset. When faced with the target diagnosis task, SMoCo can achieve accuracy far better than other representative methods in only a very short time, and its excellent robustness regarding the amount of data in both the unlabeled pre-training dataset and the target diagnosis dataset as well as the strong noise demonstrates its great potential and superiority in fault diagnosis.

Suggested Citation

  • Zitong Yan & Hongmei Liu, 2022. "SMoCo: A Powerful and Efficient Method Based on Self-Supervised Learning for Fault Diagnosis of Aero-Engine Bearing under Limited Data," Mathematics, MDPI, vol. 10(15), pages 1-24, August.
  • Handle: RePEc:gam:jmathe:v:10:y:2022:i:15:p:2796-:d:882154
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/2227-7390/10/15/2796/pdf
    Download Restriction: no

    File URL: https://www.mdpi.com/2227-7390/10/15/2796/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Ding, Yifei & Zhuang, Jichao & Ding, Peng & Jia, Minping, 2022. "Self-supervised pretraining via contrast learning for intelligent incipient fault detection of bearings," Reliability Engineering and System Safety, Elsevier, vol. 218(PA).
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Yanxin Xu & Dongjian Zheng & Chenfei Shao & Sen Zheng & Hao Gu, 2023. "Structural Modal Parameter Identification Method Based on the Delayed Transfer Rate Function under Periodic Excitations," Mathematics, MDPI, vol. 11(4), pages 1-17, February.

    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. Mohammed Majid Abdulrazzaq & Nehad T. A. Ramaha & Alaa Ali Hameed & Mohammad Salman & Dong Keon Yon & Norma Latif Fitriyani & Muhammad Syafrudin & Seung Won Lee, 2024. "Consequential Advancements of Self-Supervised Learning (SSL) in Deep Learning Contexts," Mathematics, MDPI, vol. 12(5), pages 1-42, March.
    2. Shi, Yaowei & Deng, Aidong & Deng, Minqiang & Xu, Meng & Liu, Yang & Ding, Xue & Li, Jing, 2022. "Transferable adaptive channel attention module for unsupervised cross-domain fault diagnosis," Reliability Engineering and System Safety, Elsevier, vol. 226(C).
    3. Fang, Xiaoyu & Qu, Jianfeng & Chai, Yi, 2023. "Self-supervised intermittent fault detection for analog circuits guided by prior knowledge," Reliability Engineering and System Safety, Elsevier, vol. 233(C).
    4. Zuo, Lin & Xu, Fengjie & Zhang, Changhua & Xiahou, Tangfan & Liu, Yu, 2022. "A multi-layer spiking neural network-based approach to bearing fault diagnosis," Reliability Engineering and System Safety, Elsevier, vol. 225(C).
    5. Shi, Yaowei & Deng, Aidong & Deng, Minqiang & Xu, Meng & Liu, Yang & Ding, Xue & Bian, Wenbin, 2023. "Domain augmentation generalization network for real-time fault diagnosis under unseen working conditions," Reliability Engineering and System Safety, Elsevier, vol. 235(C).
    6. Ding, Yifei & Jia, Minping & Zhuang, Jichao & Cao, Yudong & Zhao, Xiaoli & Lee, Chi-Guhn, 2023. "Deep imbalanced domain adaptation for transfer learning fault diagnosis of bearings under multiple working conditions," Reliability Engineering and System Safety, Elsevier, vol. 230(C).
    7. Zheng, Niannian & Luan, Xiaoli & Shardt, Yuri A.W. & Liu, Fei, 2024. "Dynamic-controlled principal component analysis for fault detection and automatic recovery," Reliability Engineering and System Safety, Elsevier, vol. 241(C).
    8. Panjapornpon, Chanin & Bardeeniz, Santi & Hussain, Mohamed Azlan, 2023. "Deep learning approach for energy efficiency prediction with signal monitoring reliability for a vinyl chloride monomer process," Reliability Engineering and System Safety, Elsevier, vol. 231(C).
    9. Dong, Shaojiang & Xiao, Jiafeng & Hu, Xiaolin & Fang, Nengwei & Liu, Lanhui & Yao, Jinbao, 2023. "Deep transfer learning based on Bi-LSTM and attention for remaining useful life prediction of rolling bearing," Reliability Engineering and System Safety, Elsevier, vol. 230(C).
    10. Li, Xin & Li, Yong & Yan, Ke & Shao, Haidong & (Jing) Lin, Janet, 2023. "Intelligent fault diagnosis of bevel gearboxes using semi-supervised probability support matrix machine and infrared imaging," Reliability Engineering and System Safety, Elsevier, vol. 230(C).
    11. Liu, Shaowei & Jiang, Hongkai & Wu, Zhenghong & Yi, Zichun & Wang, Ruixin, 2023. "Intelligent fault diagnosis of rotating machinery using a multi-source domain adaptation network with adversarial discrepancy matching," Reliability Engineering and System Safety, Elsevier, vol. 231(C).
    12. Shao, Kaixuan & He, Yigang & Xing, Zhikai & Du, Bolun, 2023. "Detecting wind turbine anomalies using nonlinear dynamic parameters-assisted machine learning with normal samples," Reliability Engineering and System Safety, Elsevier, vol. 233(C).
    13. Zheng, Jianqin & Wang, Chang & Liang, Yongtu & Liao, Qi & Li, Zhuochao & Wang, Bohong, 2022. "Deeppipe: A deep-learning method for anomaly detection of multi-product pipelines," Energy, Elsevier, vol. 259(C).
    14. Wang, Yilin & Li, Yuanxiang & Zhang, Yuxuan & Lei, Jia & Yu, Yifei & Zhang, Tongtong & Yang, Yongshen & Zhao, Honghua, 2024. "Incorporating prior knowledge into self-supervised representation learning for long PHM signal," Reliability Engineering and System Safety, Elsevier, vol. 241(C).
    15. Xiaobo Liu & Hantao Guo & Yibing Liu, 2022. "One-Shot Fault Diagnosis of Wind Turbines Based on Meta-Analogical Momentum Contrast Learning," Energies, MDPI, vol. 15(9), pages 1-14, April.

    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:gam:jmathe:v:10:y:2022:i:15:p:2796-:d:882154. 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: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.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.