A journal of IEEE and CAA , publishes high-quality papers in English on original theoretical/experimental research and development in all areas of automation
Volume 11 Issue 6
Jun.  2024

IEEE/CAA Journal of Automatica Sinica

  • JCR Impact Factor: 11.8, Top 4% (SCI Q1)
    CiteScore: 23.5, Top 2% (Q1)
    Google Scholar h5-index: 77, TOP 5
Turn off MathJax
Article Contents
J. Ren, J. Wen, Z. Zhao, R. Yan, X. Chen, and  A. Nandi,  “Uncertainty-aware deep learning: A promising tool for trustworthy fault diagnosis,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 6, pp. 1317–1330, Jun. 2024. doi: 10.1109/JAS.2024.124290
Citation: J. Ren, J. Wen, Z. Zhao, R. Yan, X. Chen, and  A. Nandi,  “Uncertainty-aware deep learning: A promising tool for trustworthy fault diagnosis,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 6, pp. 1317–1330, Jun. 2024. doi: 10.1109/JAS.2024.124290

Uncertainty-Aware Deep Learning: A Promising Tool for Trustworthy Fault Diagnosis

doi: 10.1109/JAS.2024.124290
Funds:  This work was supported in part by the National Natural Science Foundation of China (52105116), Science Center for gas turbine project (P2022-DC-I-003-001), and the Royal Society award (IEC\NSFC\223294) to Professor Asoke K. Nandi
More Information
  • Recently, intelligent fault diagnosis based on deep learning has been extensively investigated, exhibiting state-of-the-art performance. However, the deep learning model is often not truly trusted by users due to the lack of interpretability of “black box”, which limits its deployment in safety-critical applications. A trusted fault diagnosis system requires that the faults can be accurately diagnosed in most cases, and the human in the decision-making loop can be found to deal with the abnormal situation when the models fail. In this paper, we explore a simplified method for quantifying both aleatoric and epistemic uncertainty in deterministic networks, called SAEU. In SAEU, Multivariate Gaussian distribution is employed in the deep architecture to compensate for the shortcomings of complexity and applicability of Bayesian neural networks. Based on the SAEU, we propose a unified uncertainty-aware deep learning framework (UU-DLF) to realize the grand vision of trustworthy fault diagnosis. Moreover, our UU-DLF effectively embodies the idea of “humans in the loop”, which not only allows for manual intervention in abnormal situations of diagnostic models, but also makes corresponding improvements on existing models based on traceability analysis. Finally, two experiments conducted on the gearbox and aero-engine bevel gears are used to demonstrate the effectiveness of UU-DLF and explore the effective reasons behind.

     

  • loading
  • [1]
    S. Sankararaman, “Significance, interpretation, and quantification of uncertainty in prognostics and remaining useful life prediction,” Mech. Syst. Signal Process., vol. 52–53, pp. 228–247, Feb. 2015. doi: 10.1016/j.ymssp.2014.05.029
    [2]
    A. White, A. Karimoddini, and M. Karimadini, “Resilient fault diagnosis under imperfect observations–A need for Industry 4.0 era,” IEEE/CAA J. Autom. Sinica, vol. 7, no. 5, pp. 1279–1288, Sep. 2020. doi: 10.1109/JAS.2020.1003333
    [3]
    Z. Zhu, Y. Lei, G. Qi, Y. Chai, N. Mazur, Y. An, and X. Huang, “A review of the application of deep learning in intelligent fault diagnosis of rotating machinery,” Measurement, vol. 206, p. 112346, Jan. 2023. doi: 10.1016/j.measurement.2022.112346
    [4]
    J. Lee, F. Wu, W. Zhao, M. Ghaffari, L. Liao, and D. Siegel, “Prognostics and health management design for rotary machinery systems–Reviews, methodology and applications,” Mech. Syst. Signal Process., vol. 42, no. 1-2, pp. 314–334, Jan. 2014. doi: 10.1016/j.ymssp.2013.06.004
    [5]
    Y. Hu, X. Miao, Y. Si, E. Pan, and E. Zio, “Prognostics and health management: A review from the perspectives of design, development and decision,” Reliab. Eng. Syst. Saf., vol. 217, p. 108063, Jan. 2022. doi: 10.1016/j.ress.2021.108063
    [6]
    R. Flage, T. Aven, E. Zio, and P. Baraldi, “Concerns, challenges, and directions of development for the issue of representing uncertainty in risk assessment,” Risk Anal., vol. 34, no. 7, pp. 1196–1207, Jul. 2014. doi: 10.1111/risa.12247
    [7]
    J. Long, H. Wang, P. Li, and H. Fan, “Applications of fractional lower order time-frequency representation to machine bearing fault diagnosis,” IEEE/CAA J. Autom. Sinica, vol. 4, no. 4, pp. 734–750, 2017. doi: 10.1109/JAS.2016.7510190
    [8]
    R. Zhao, R. Yan, Z. Chen, K. Mao, P. Wang, and R. X. Gao, “Deep learning and its applications to machine health monitoring,” Mech. Syst. Signal Process., vol. 115, pp. 213–237, Jan. 2019. doi: 10.1016/j.ymssp.2018.05.050
    [9]
    Z. Zhao, T. Li, J. Wu, C. Sun, S. Wang, R. Yan, and X. Chen, “Deep learning algorithms for rotating machinery intelligent diagnosis: An open source benchmark study,” ISA Trans., vol. 107, pp. 224–255, Dec. 2020. doi: 10.1016/j.isatra.2020.08.010
    [10]
    A. Kumar, A. Glowacz, H. Tang, and J. Xiang, “Knowledge addition for improving the transfer learning from the laboratory to identify defects of hydraulic machinery,” Eng. Appl. Artif. Intell., vol. 126, p. 106756, Nov. 2023. doi: 10.1016/j.engappai.2023.106756
    [11]
    Z. He, H. Shao, Z. Ding, H. Jiang, and J. Cheng, “Modified deep autoencoder driven by multisource parameters for fault transfer prognosis of aeroengine,” IEEE Trans. Ind. Electron., vol. 69, no. 1, pp. 845–855, Jan. 2022. doi: 10.1109/TIE.2021.3050382
    [12]
    D.-T. Hoang and H.-J. Kang, “A survey on deep learning based bearing fault diagnosis,” Neurocomputing, vol. 335, pp. 327–335, Mar. 2019. doi: 10.1016/j.neucom.2018.06.078
    [13]
    M. Ma and Z. Mao, “Deep-convolution-based LSTM network for remaining useful life prediction,” IEEE Trans. Ind. Inf., vol. 17, no. 3, pp. 1658–1667, Mar. 2021. doi: 10.1109/TII.2020.2991796
    [14]
    J. Wang, Y. Ma, L. Zhang, R. X. Gao, and D. Wu, “Deep learning for smart manufacturing: Methods and applications,” J. Manuf. Syst., vol. 48, pp. 144–156, Jul. 2018. doi: 10.1016/j.jmsy.2018.01.003
    [15]
    X. Wang, X. Liu, and Y. Li, “An incremental model transfer method for complex process fault diagnosis,” IEEE/CAA J. Autom. Sinica, vol. 6, no. 5, pp. 1268–1280, Sep. 2019. doi: 10.1109/JAS.2019.1911618
    [16]
    Y. Zhang, K. Yu, Z. Lei, J. Ge, Y. Xu, Z. Li, Z. Ren, and K. Feng, “Integrated intelligent fault diagnosis approach of offshore wind turbine bearing based on information stream fusion and semi-supervised learning,” Expert Syst. Appl., vol. 232, p. 120854, Dec. 2023. doi: 10.1016/j.eswa.2023.120854
    [17]
    Q. Qian, Y. Qin, J. Luo, Y. Wang, and F. Wu, “Deep discriminative transfer learning network for cross-machine fault diagnosis,” Mech. Syst. Signal Process., vol. 186, p. 109884, Mar. 2023. doi: 10.1016/j.ymssp.2022.109884
    [18]
    H. Shao, W. Li, B. Cai, J. Wan, Y. Xiao, and S. Yan, “Dual-threshold attention-guided GAN and limited infrared thermal images for rotating machinery fault diagnosis under speed fluctuation,” IEEE Trans. Ind. Inf., vol. 19, no. 9, pp. 9933–9942, Sep. 2023. doi: 10.1109/TII.2022.3232766
    [19]
    P. Shi, S. Wu, X. Xu, B. Zhang, P. Liang, and Z. Qiao, “TSN: A novel intelligent fault diagnosis method for bearing with small samples under variable working conditions,” Reliab. Eng. Syst. Saf., vol. 240, p. 109575, Dec. 2023. doi: 10.1016/j.ress.2023.109575
    [20]
    S. Tang, Y. Zhu, and S. Yuan, “A novel adaptive convolutional neural network for fault diagnosis of hydraulic piston pump with acoustic images,” Adv. Eng. Inf., vol. 52, p. 101554, Apr. 2022. doi: 10.1016/j.aei.2022.101554
    [21]
    A. Glowacz, “Thermographic fault diagnosis of shaft of BLDC motor,” Sensors, vol. 22, no. 21, p. 8537, Nov. 2022. doi: 10.3390/s22218537
    [22]
    A. Glowacz, “Thermographic fault diagnosis of electrical faults of commutator and induction motors,” Eng. Appl. Artif. Intell., vol. 121, p. 105962, May 2023. doi: 10.1016/j.engappai.2023.105962
    [23]
    A. Choudhary, R. K. Mishra, S. Fatima, and B. K. Panigrahi, “Multi-input CNN based vibro-acoustic fusion for accurate fault diagnosis of induction motor,” Eng. Appl. Artif. Intell., vol. 120, p. 105872, Apr. 2023. doi: 10.1016/j.engappai.2023.105872
    [24]
    Z. Feng, A. Gao, K. Li, and H. Ma, “Planetary gearbox fault diagnosis via rotary encoder signal analysis,” Mech. Syst. Signal Process., vol. 149, p. 107325, Feb. 2021. doi: 10.1016/j.ymssp.2020.107325
    [25]
    J. Jiao, M. Zhao, J. Lin, and J. Zhao, “A multivariate encoder information based convolutional neural network for intelligent fault diagnosis of planetary gearboxes,” Knowl. Based Syst., vol. 160, pp. 237–250, Nov. 2018. doi: 10.1016/j.knosys.2018.07.017
    [26]
    T. Han, Y.-F. Li, and M. Qian, “A hybrid generalization network for intelligent fault diagnosis of rotating machinery under unseen working conditions,” IEEE Trans. Instrum. Meas., vol. 70, p. 3520011, Jun. 2021.
    [27]
    G. Michau and O. Fink, “Unsupervised transfer learning for anomaly detection: Application to complementary operating condition transfer,” Knowl. Based Syst., vol. 216, p. 106816, Mar. 2021. doi: 10.1016/j.knosys.2021.106816
    [28]
    Z. Chen, G. He, J. Li, Y. Liao, K. Gryllias, and W. Li, “Domain adversarial transfer network for cross-domain fault diagnosis of rotary machinery,” IEEE Trans. Instrum. Meas., vol. 69, no. 11, pp. 8702–8712, Nov. 2020. doi: 10.1109/TIM.2020.2995441
    [29]
    J. Jiao, M. Zhao, J. Lin, and K. Liang, “Residual joint adaptation adversarial network for intelligent transfer fault diagnosis,” Mech. Syst. Signal Process., vol. 145, p. 106962, Nov.–Dec. 2020. doi: 10.1016/j.ymssp.2020.106962
    [30]
    J. Huang, Z. Li, and Z. Zhou, “A simple framework to generalized zero-shot learning for fault diagnosis of industrial processes,” IEEE/CAA J. Autom. Sinica, vol. 10, no. 6, pp. 1504–1506, Jun. 2023. doi: 10.1109/JAS.2023.123426
    [31]
    B. Yang, S. Xu, Y. Lei, C.-G. Lee, E. Stewart, and C. Roberts, “Multi-source transfer learning network to complement knowledge for intelligent diagnosis of machines with unseen faults,” Mech. Syst. Signal Process., vol. 162, p. 108095, Jan. 2022. doi: 10.1016/j.ymssp.2021.108095
    [32]
    W. Zhang, X. Li, H. Ma, Z. Luo, and X. Li, “Open-set domain adaptation in machinery fault diagnostics using instance-level weighted adversarial learning,” IEEE Trans. Ind. Inf., vol. 17, no. 11, pp. 7445–7455, Nov. 2021. doi: 10.1109/TII.2021.3054651
    [33]
    X. Yu, Z. Zhao, X. Zhang, Q. Zhang, Y. Liu, C. Sun, and X. Chen, “Deep-learning-based open set fault diagnosis by extreme value theory,” IEEE Trans. Ind. Inf., vol. 18, no. 1, pp. 185–196, Jan. 2022. doi: 10.1109/TII.2021.3070324
    [34]
    M. Abdar, F. Pourpanah, S. Hussain, D. Rezazadegan, L. Liu, M. Ghavamzadeh, P. Fieguth, X. Cao, A. Khosravi, U. R. Acharya, V. Makarenkov, and S. Nahavandi, “A review of uncertainty quantification in deep learning: Techniques, applications and challenges,” Inf. Fusion, vol. 76, pp. 243–297, Dec. 2021. doi: 10.1016/j.inffus.2021.05.008
    [35]
    E. Zio, “Prognostics and health management (PHM): Where are we and where do we (need to) go in theory and practice,” Reliab. Eng. Syst. Saf., vol. 218, p. 108119, Feb. 2022. doi: 10.1016/j.ress.2021.108119
    [36]
    O. Fink, Q. Wang, M. Svensén, P. Dersin, W.-J. Lee, and M. Ducoffe, “Potential, challenges and future directions for deep learning in prognostics and health management applications,” Eng. Appl. Artif. Intell., vol. 92, p. 103678, Jun. 2020. doi: 10.1016/j.engappai.2020.103678
    [37]
    T. Zhou, L. Zhang, T. Han, E. L. Droguett, A. Mosleh, and F. T. S. Chan, “An uncertainty-informed framework for trustworthy fault diagnosis in safety-critical applications,” Reliab. Eng. Syst. Saf., vol. 229, p. 108865, Jan. 2023. doi: 10.1016/j.ress.2022.108865
    [38]
    Y. Xiao, H. Shao, M. Feng, T. Han, J. Wan, and B. Liu, “Towards trustworthy rotating machinery fault diagnosis via attention uncertainty in transformer,” J. Manuf. Syst., vol. 70, pp. 186–201, Oct. 2023. doi: 10.1016/j.jmsy.2023.07.012
    [39]
    J. Xia, M. Xu, H. Zhang, J. Zhang, W. Huang, H. Cao, and S. Wen, “Robust face alignment via inherent relation learning and uncertainty estimation,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 45, no. 8, pp. 10358–10375, Aug. 2023. doi: 10.1109/TPAMI.2023.3260926
    [40]
    J. M. Dolezal, A. Srisuwananukorn, D. Karpeyev, S. Ramesh, S. Kochanny, B. Cody, A. S. Mansfield, S. Rakshit, R. Bansal, M. C. Bois, A. O. Bungum, J. J. Schulte, E. E. Vokes, M. C. Garassino, A. N. Husain, and A. T. Pearson, “Uncertainty-informed deep learning models enable high-confidence predictions for digital histopathology,” Nat. Commun., vol. 13, no. 1, p. 6572, Nov. 2022. doi: 10.1038/s41467-022-34025-x
    [41]
    C. Sakaridis, D. Dai, and L. Van Gool, “Map-guided curriculum domain adaptation and uncertainty-aware evaluation for semantic nighttime image segmentation,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 44, no. 6, pp. 3139–3153, Jun. 2022. doi: 10.1109/TPAMI.2020.3045882
    [42]
    X. Li, J. Liu, B. Liu, Q. Zhang, K. Li, Z. Dong, and L. Mou, “Impacts of data uncertainty on the performance of data-driven-based building fault diagnosis,” J. Build. Eng., vol. 43, p. 103153, Nov. 2021. doi: 10.1016/j.jobe.2021.103153
    [43]
    T. Han and Y.-F. Li, “Out-of-distribution detection-assisted trustworthy machinery fault diagnosis approach with uncertainty-aware deep ensembles,” Reliab. Eng. Syst. Saf., vol. 226, p. 108648, Oct. 2022. doi: 10.1016/j.ress.2022.108648
    [44]
    M. Sensoy, L. Kaplan, and M. Kandemir, “Evidential deep learning to quantify classification uncertainty,” in Proc. 32nd Int. Conf. Neural Information Processing Systems, Montreal, Canada, 2018, pp. 3183–3193.
    [45]
    H. Zhou, W. Chen, L. Cheng, D. Williams, C. W. De Silva, and M. Xia, “Reliable and intelligent fault diagnosis with evidential VGG neural networks,” IEEE Trans. Instrum. Meas., vol. 72, p. 3508612, Feb. 2023.
    [46]
    H. Zhou, W. Chen, L. Cheng, J. Liu, and M. Xia, “Trustworthy fault diagnosis with uncertainty estimation through evidential convolutional neural networks,” IEEE Trans. Ind. Inf., vol. 19, no. 11, pp. 10842–10852, Nov. 2023. doi: 10.1109/TII.2023.3241587
    [47]
    N. Meinert, J. Gawlikowski, and A. Lavin, “The unreasonable effectiveness of deep evidential regression,” in Proc. 37th AAAI Conf. Artificial Intelligence, Washington, USA, 2023, pp. 9134–9142.
    [48]
    C. Blundell, J. Cornebise, K. Kavukcuoglu, and D. Wierstra, “Weight uncertainty in neural networks,” in Proc. 32nd Int. Conf. Machine Learning, Lille, France, 2015, pp. 1613–1622.
    [49]
    Y. Gal, “Uncertainty in deep learning,” Ph.D. dissertation, Univ. Cambridge, Cambridge, UK, 2016.
    [50]
    Y. Gal and Z. Ghahramani, “Dropout as a Bayesian approximation: Representing model uncertainty in deep learning,” in Proc. 33rd Int. Conf. Machine Learning, New York, USA, 2016, pp. 1050–1059.
    [51]
    B. Lakshminarayanan, A. Pritzel, and C. Blundell, “Simple and scalable predictive uncertainty estimation using deep ensembles,” in Proc. 31st Conf. Neural Information Processing Systems, Long Beach, USA, 2017, pp. 6405–6416.
    [52]
    W. Xie, T. Han, Z. Pei, and M. Xie, “A unified out-of-distribution detection framework for trustworthy prognostics and health management in renewable energy systems,” Eng. Appl. Artif. Intell., vol. 125, p. 106707, Oct. 2023. doi: 10.1016/j.engappai.2023.106707
    [53]
    L. Hirschfeld, K. Swanson, K. Yang, R. Barzilay, and C. W. Coley, “Uncertainty quantification using neural networks for molecular property prediction,” J. Chem. Inf. Model., vol. 60, no. 8, pp. 3770–3780, Jul. 2020. doi: 10.1021/acs.jcim.0c00502
    [54]
    K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proc. IEEE Conf. Computer Vision and Pattern Recognition, Las Vegas, USA, 2016, pp. 770–778.
    [55]
    S. Shao, S. McAleer, R. Yan, and P. Baldi, “Highly accurate machine fault diagnosis using deep transfer learning,” IEEE Trans. Ind. Inf., vol. 15, no. 4, pp. 2446–2455, Apr. 2019. doi: 10.1109/TII.2018.2864759
    [56]
    S. Niu, Y. Liu, J. Wang, and H. Song, “A decade survey of transfer learning (2010–2020),” IEEE Trans. Artif. Intell., vol. 1, no. 2, pp. 151–166, Oct. 2020. doi: 10.1109/TAI.2021.3054609
    [57]
    Z. Wan, R. Yang, M. Huang, N. Zeng, and X. Liu, “A review on transfer learning in EEG signal analysis,” Neurocomputing, vol. 421, pp. 1–14, Jan. 2021. doi: 10.1016/j.neucom.2020.09.017
    [58]
    W. Zhang and D. Wu, “Manifold embedded knowledge transfer for brain-computer interfaces,” IEEE Trans. Neural Syst. Rehabil. Eng., vol. 28, no. 5, pp. 1117–1127, May 2020. doi: 10.1109/TNSRE.2020.2985996
    [59]
    X. Wang, R. Yang, and M. Huang, “An unsupervised deep-transfer-learning-based motor imagery EEG classification scheme for brain-computer interface,” Sensors, vol. 22, no. 6, p. 2241, Mar. 2022. doi: 10.3390/s22062241

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(16)  / Tables(5)

    Article Metrics

    Article views (191) PDF downloads(79) Cited by()

    Highlights

    • The Multivariate Gaussian distribution is employed into the deep architecture and some methods of representing diversity are combined to quantify both aleatoric and epistemic uncertainties simultaneously, which can effectively reduce the computational complexity of quantifying aleatoric and epistemic uncertainties in intelligent fault diagnosis
    • On the basis of uncertainty decomposition graph given by our simplified algorithm, we proposed a unified trustworthy fault diagnosis framework, named as UU-DLF. It gives the “black box” models a certain degree of post-hoc interpretability, which helps to realize model failure warning and model improvement from the perspective of uncertainty decomposition
    • Through the powerful performance and promising prospects shown by experiments, the uncertainty of deep learning proposed by our paper may provide a promising way for deep learning models to gain industrial users’ trust

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return