IDEAS home Printed from https://ideas.repec.org/a/eee/reensy/v216y2021ics0951832021004506.html
   My bibliography  Save this article

Learning from Class-imbalanced Data with a Model-Agnostic Framework for Machine Intelligent Diagnosis

Author

Listed:
  • Wu, Jingyao
  • Zhao, Zhibin
  • Sun, Chuang
  • Yan, Ruqiang
  • Chen, Xuefeng

Abstract

Considering the difficulty of data acquisition in industry, especially for failure data of large-scale equipment, classification with these class-imbalanced datasets can lead to the problems of minority categories overfitting and majority categories domination. A model-agnostic framework towards class-imbalanced fault diagnosis requirement is proposed to systematically alleviate these problems. Four sub-modules, including Time-series Data Augmentation, Data-Rebalanced sampler, Balanced Margin Loss, and classifier with Dynamic Decision Boundary Balancing are performed to improve recognition accuracy of minority categories without performance degradation on majority categories. Meanwhile, the framework is compatible with general neural networks and provides flexible model candidates to meet the need of feature extraction for different data types. Three case studies on public datasets demonstrate that proposed framework outperformed various state-of-the-art methods.

Suggested Citation

  • Wu, Jingyao & Zhao, Zhibin & Sun, Chuang & Yan, Ruqiang & Chen, Xuefeng, 2021. "Learning from Class-imbalanced Data with a Model-Agnostic Framework for Machine Intelligent Diagnosis," Reliability Engineering and System Safety, Elsevier, vol. 216(C).
    • Handle: RePEc:eee:reensy:v:216:y:2021:i:c:s0951832021004506
    DOI: 10.1016/j.ress.2021.107934
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S0951832021004506
    Download Restriction: Full text for ScienceDirect subscribers only
    File URL: https://libkey.io/10.1016/j.ress.2021.107934?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. Ding, Yifei & Jia, Minping & Miao, Qiuhua & Huang, Peng, 2021. "Remaining useful life estimation using deep metric transfer learning for kernel regression," Reliability Engineering and System Safety, Elsevier, vol. 212(C).
    2. Wang, Xu & Shen, Changqing & Xia, Min & Wang, Dong & Zhu, Jun & Zhu, Zhongkui, 2020. "Multi-scale deep intra-class transfer learning for bearing fault diagnosis," Reliability Engineering and System Safety, Elsevier, vol. 202(C).
    3. Chujie Tian & Jian Ma & Chunhong Zhang & Panpan Zhan, 2018. "A Deep Neural Network Model for Short-Term Load Forecast Based on Long Short-Term Memory Network and Convolutional Neural Network," Energies, MDPI, vol. 11(12), pages 1-13, December.
    4. Ahmad, Wasim & Khan, Sheraz Ali & Islam, M M Manjurul & Kim, Jong-Myon, 2019. "A reliable technique for remaining useful life estimation of rolling element bearings using dynamic regression models," Reliability Engineering and System Safety, Elsevier, vol. 184(C), pages 67-76.
    5. Duan, Chaoqun & Makis, Viliam & Deng, Chao, 2020. "A two-level Bayesian early fault detection for mechanical equipment subject to dependent failure modes," Reliability Engineering and System Safety, Elsevier, vol. 193(C).
    6. Tolo, Silvia & Tian, Xiange & Bausch, Nils & Becerra, Victor & Santhosh, T.V. & Vinod, G. & Patelli, Edoardo, 2019. "Robust on-line diagnosis tool for the early accident detection in nuclear power plants," Reliability Engineering and System Safety, Elsevier, vol. 186(C), pages 110-119.
    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. Yin, Zhenqin & Zhuo, Yue & Ge, Zhiqiang, 2023. "Transfer adversarial attacks across industrial intelligent systems," Reliability Engineering and System Safety, Elsevier, vol. 237(C).
    2. Zhao, Chao & Shen, Weiming, 2022. "Dual adversarial network for cross-domain open set fault diagnosis," Reliability Engineering and System Safety, Elsevier, vol. 221(C).
    3. 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).
    4. Zhao, Chao & Shen, Weiming, 2022. "Adaptive open set domain generalization network: Learning to diagnose unknown faults under unknown working conditions," Reliability Engineering and System Safety, Elsevier, vol. 226(C).
    5. Guo, Junchao & He, Qingbo & Zhen, Dong & Gu, Fengshou & Ball, Andrew D., 2023. "Multi-sensor data fusion for rotating machinery fault detection using improved cyclic spectral covariance matrix and motor current signal analysis," Reliability Engineering and System Safety, Elsevier, vol. 230(C).
    6. Jin, Kyungho & Kim, Hyeonmin & Ryu, Seunghyoung & Kim, Seunggeun & Park, Jinkyun, 2022. "An approach to constructing effective training data for a classification model to evaluate the reliability of a passive safety system," Reliability Engineering and System Safety, Elsevier, vol. 222(C).

    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. Ma, Chenyang & Li, Yongbo & Wang, Xianzhi & Cai, Zhiqiang, 2023. "Early fault diagnosis of rotating machinery based on composite zoom permutation entropy," Reliability Engineering and System Safety, Elsevier, vol. 230(C).
    2. Zio, Enrico, 2022. "Prognostics and Health Management (PHM): Where are we and where do we (need to) go in theory and practice," Reliability Engineering and System Safety, Elsevier, vol. 218(PA).
    3. Li, Xin & Yang, Yu & Wu, Zhantao & Yan, Ke & Shao, Haidong & Cheng, Junsheng, 2022. "High-accuracy gearbox health state recognition based on graph sparse random vector functional link network," Reliability Engineering and System Safety, Elsevier, vol. 218(PB).
    4. Cheng, Han & Kong, Xianguang & Wang, Qibin & Ma, Hongbo & Yang, Shengkang, 2022. "The two-stage RUL prediction across operation conditions using deep transfer learning and insufficient degradation data," Reliability Engineering and System Safety, Elsevier, vol. 225(C).
    5. Bermeo-Ayerbe, Miguel Angel & Cocquempot, Vincent & Ocampo-Martinez, Carlos & Diaz-Rozo, Javier, 2023. "Remaining useful life estimation of ball-bearings based on motor current signature analysis," Reliability Engineering and System Safety, Elsevier, vol. 235(C).
    6. Wang, Han & Wang, Dongdong & Liu, Haoxiang & Tang, Gang, 2022. "A predictive sliding local outlier correction method with adaptive state change rate determining for bearing remaining useful life estimation," Reliability Engineering and System Safety, Elsevier, vol. 225(C).
    7. Xiang, Sheng & Qin, Yi & Luo, Jun & Pu, Huayan & Tang, Baoping, 2021. "Multicellular LSTM-based deep learning model for aero-engine remaining useful life prediction," Reliability Engineering and System Safety, Elsevier, vol. 216(C).
    8. Lee, Jinwook & Kim, Myungyon & Ko, Jin Uk & Jung, Joon Ha & Sun, Kyung Ho & Youn, Byeng D., 2022. "Asymmetric inter-intra domain alignments (AIIDA) method for intelligent fault diagnosis of rotating machinery," Reliability Engineering and System Safety, Elsevier, vol. 218(PB).
    9. 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).
    10. Md. Nazmul Hasan & Rafia Nishat Toma & Abdullah-Al Nahid & M M Manjurul Islam & Jong-Myon Kim, 2019. "Electricity Theft Detection in Smart Grid Systems: A CNN-LSTM Based Approach," Energies, MDPI, vol. 12(17), pages 1-18, August.
    11. Fei Teng & Yafei Song & Xinpeng Guo, 2021. "Attention-TCN-BiGRU: An Air Target Combat Intention Recognition Model," Mathematics, MDPI, vol. 9(19), pages 1-21, September.
    12. V. Y. Kondaiah & B. Saravanan, 2022. "Short-Term Load Forecasting with a Novel Wavelet-Based Ensemble Method," Energies, MDPI, vol. 15(14), pages 1-17, July.
    13. Neethu Elizabeth Michael & Manohar Mishra & Shazia Hasan & Ahmed Al-Durra, 2022. "Short-Term Solar Power Predicting Model Based on Multi-Step CNN Stacked LSTM Technique," Energies, MDPI, vol. 15(6), pages 1-20, March.
    14. Shree Krishna Acharya & Young-Min Wi & Jaehee Lee, 2019. "Short-Term Load Forecasting for a Single Household Based on Convolution Neural Networks Using Data Augmentation," Energies, MDPI, vol. 12(18), pages 1-19, September.
    15. Sepehr Moalem & Roya M. Ahari & Ghazanfar Shahgholian & Majid Moazzami & Seyed Mohammad Kazemi, 2022. "Long-Term Electricity Demand Forecasting in the Steel Complex Micro-Grid Electricity Supply Chain—A Coupled Approach," Energies, MDPI, vol. 15(21), pages 1-17, October.
    16. Tan, Hongchuang & Xie, Suchao & Ma, Wen & Yang, Chengxing & Zheng, Shiwei, 2023. "Correlation feature distribution matching for fault diagnosis of machines," Reliability Engineering and System Safety, Elsevier, vol. 231(C).
    17. Waqar Muhammad Ashraf & Ghulam Moeen Uddin & Syed Muhammad Arafat & Sher Afghan & Ahmad Hassan Kamal & Muhammad Asim & Muhammad Haider Khan & Muhammad Waqas Rafique & Uwe Naumann & Sajawal Gul Niazi &, 2020. "Optimization of a 660 MW e Supercritical Power Plant Performance—A Case of Industry 4.0 in the Data-Driven Operational Management Part 1. Thermal Efficiency," Energies, MDPI, vol. 13(21), pages 1-33, October.
    18. Bulent Haznedar & Huseyin Cagan Kilinc & Furkan Ozkan & Adem Yurtsever, 2023. "Streamflow forecasting using a hybrid LSTM-PSO approach: the case of Seyhan Basin," Natural Hazards: Journal of the International Society for the Prevention and Mitigation of Natural Hazards, Springer;International Society for the Prevention and Mitigation of Natural Hazards, vol. 117(1), pages 681-701, May.
    19. Xu, Gaowei & Azhari, Fae, 2022. "Data-driven optimization of repair schemes and inspection intervals for highway bridges," Reliability Engineering and System Safety, Elsevier, vol. 228(C).
    20. 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).

    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:eee:reensy:v:216:y:2021:i:c:s0951832021004506. 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: Catherine Liu (email available below). General contact details of provider: https://www.journals.elsevier.com/reliability-engineering-and-system-safety .

    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.