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: 15.3, Top 1 (SCI Q1)
    CiteScore: 23.5, Top 2% (Q1)
    Google Scholar h5-index: 77， TOP 5
Turn off MathJax
Article Contents
Article Navigation >  IEEE/CAA Journal of Automatica Sinica  > 2025  > In Press, Accepted Manuscript
M. Lv, Y. Li, H. Gao, B. Sun, K. Huang, C. Yang, and W. Gui, “A hierarchical stochastic network approach for fault diagnosis of complex industrial processes,” IEEE/CAA J. Autom. Sinica, 2025. doi: 10.1109/JAS.2025.125249
Citation: M. Lv, Y. Li, H. Gao, B. Sun, K. Huang, C. Yang, and W. Gui, “A hierarchical stochastic network approach for fault diagnosis of complex industrial processes,” IEEE/CAA J. Autom. Sinica, 2025. doi: 10.1109/JAS.2025.125249
shu

A Hierarchical Stochastic Network Approach for Fault Diagnosis of Complex Industrial Processes

doi: 10.1109/JAS.2025.125249
Funds:  This work was supported in part by the National Key Research and Development Program of China (2022YFB3304900), the Science and Technology Innovation Program of Hunan Province (2022RC1089), the Central South University Innovation Driven Research Programme (2023CXQD040), and the Fundamental Research Funds for the Central Universities of Central South University (1053320240497)
More Information
    Abstract
  • Complex industrial processes present typical uncertainty due to fluctuations in the composition of raw materials and frequently changing operating conditions. This poses three challenges for precise fault diagnosis, including random noise interference, less distinguishability between multi-class faults, and the new fault emerging. To address these issues, this study formulates fault diagnosis in uncertain industrial processes as a multi-level refined fault diagnosis problem. A hierarchical stochastic network approach is proposed to refine fault diagnosis of multi-class faults. This method considers the augmentation of fault categories as naturally following a hierarchical structure. At each hierarchical stage, stochastic network methods are designed according to the sources of uncertainty. For fault feature extraction, a doubly stochastic attention-based variational graph autoencoder is introduced to suppress noise during the message-passing process, ensuring the extraction of high-quality fault features and providing the provision of differentiated information. Subsequently, multiple stochastic configuration networks are deployed to realize multi-level fault diagnosis from coarse to fine granularity via a hierarchical structure rather than treating all faults equally. This approach effectively enhances the precision of multi-class fault diagnosis and ensures its robust generalization capability. Finally, the feasibility and effectiveness of the proposed method are validated using two industrial processes. The results demonstrate that the proposed method can effectively suppress the random noise interference and adapt to the emergence of small samples and imbalanced extreme fault-type data, achieving a satisfactory fault diagnosis performance.

     

    • FullText(HTML)
  • loading
    • References(55)
  • [1]
    X. Jiang, X. Kong, and Z. Ge, “Augmented industrial data-driven modeling under the curse of dimensionality,” IEEE/CAA J. Autom. Sinica, vol. 10, no. 6, pp. 1445–1461, Jun. 2023. doi: 10.1109/JAS.2023.123396
    [2]
    M. Lv, Y. Li, H. Liang, B. Sun, C. Yang, and W. Gui, “A spatial-temporal variational graph attention autoencoder using interactive information for fault detection in complex industrial processes,” IEEE Trans. Neural Netw. Learning Syst., vol. 35, no. 3, pp. 3062–3076, Mar. 2024. doi: 10.1109/TNNLS.2023.3328399
    [3]
    P. Singh and L. K. Singh, “Modeling and measuring common cause failures in measurement of reliability of nuclear power plant systems,” IEEE Trans. Instrum. Meas., vol. 70, p. 3001608, Aug. 2021. doi: 10.1109/TIM.2021.3105265
    [4]
    H. Chen, L. Wang, F. Peng, Q. Xu, Y. Xiong, S. Zhao, K. Tokunaga, Z. Wu, Y. Ma, P. Chen, L. Luo, and Y. Wu, “Hydrogen retention and affecting factors in rolled tungsten: Thermal desorption spectra and molecular dynamics simulations,” Int. J. Hydrogen Energy, vol. 48, no. 78, pp. 30522–30531, Sep. 2023. doi: 10.1016/j.ijhydene.2023.03.151
    [5]
    Z. Chang and T. Han, “Prognostics and health management of photovoltaic systems based on deep learning: A state-of-the-art review and future perspectives,” Renewable Sustainable Energy Rev., vol. 205, p. 114861, Nov. 2024. doi: 10.1016/j.rser.2024.114861
    [6]
    Y. Wang, H. Yang, X. Yuan, Y. A. Shardt, C. Yang, and W. Gui, “Deep learning for fault-relevant feature extraction and fault classification with stacked supervised auto-encoder,” J. Process Control, vol. 92, pp. 79–89, Aug. 2020. doi: 10.1016/j.jprocont.2020.05.015
    [7]
    K. Zhong, M. Han, and B. Han, “Data-driven based fault prognosis for industrial systems: A concise overview,” IEEE/CAA J. Autom. Sinica, vol. 7, no. 2, pp. 330–345, Mar. 2020. doi: 10.1109/JAS.2019.1911804
    [8]
    B. Yang, Y. Lei, X. Li, N. Li, and A. K. Nandi, “Label recovery and trajectory designable network for transfer fault diagnosis of machines with incorrect annotation,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 4, pp. 932–945, Apr. 2024. doi: 10.1109/JAS.2023.124083
    [9]
    S. Yin, X. Zhu, and O. Kaynak, “Improved PLS focused on key-performance-indicator-related fault diagnosis,” IEEE Trans. Ind. Electron., vol. 62, no. 3, pp. 1651–1658, Mar. 2015. doi: 10.1109/TIE.2014.2345331
    [10]
    J. Li, D. Ding, and F. Tsung, “Directional PCA for fast detection and accurate diagnosis: A unified framework,” IEEE Trans. Cybern., vol. 52, no. 11, pp. 11362–11372, Nov. 2021.
    [11]
    H. Chen, Z. Chen, Z. Chai, B. Jiang, and B. Huang, “A single-side neural network-aided canonical correlation analysis with applications to fault diagnosis,” IEEE Trans. Cybern., vol. 52, no. 9, pp. 9454–9466, Sep. 2022. doi: 10.1109/TCYB.2021.3060766
    [12]
    C. P. Mboó and K. Hameyer, “Fault diagnosis of bearing damage by means of the linear discriminant analysis of stator current features from the frequency selection,” IEEE Trans. Ind. Appl., vol. 52, no. 5, pp. 3861–3868, Sep.Oct. 2016. doi: 10.1109/TIA.2016.2581139
    [13]
    P. Wu, S. Lou, X. Zhang, J. He, Y. Liu, and J. Gao, “Data-driven fault diagnosis using deep canonical variate analysis and fisher discriminant analysis,” IEEE Trans. Ind. Inf., vol. 17, no. 5, pp. 3324–3334, May 2020.
    [14]
    Z. Ren, Y. Jiang, X. Yang, Y. Tang, and W. Zhang, “Learnable faster kernel-PCA for nonlinear fault detection: Deep autoencoder-based realization,” J. Ind. Inf. Integr., vol. 40, p. 100622, Jul. 2024.
    [15]
    Z. Ge, S. Zhong, and Y. Zhang, “Semisupervised kernel learning for FDA model and its application for fault classification in industrial processes,” IEEE Trans. Ind. Inf., vol. 12, no. 4, pp. 1403–1411, Aug. 2016. doi: 10.1109/TII.2016.2571680
    [16]
    G. Yang, Y. Zhao, and X. Gu, “A novel Bayesian framework with enhanced principal component analysis for chemical fault diagnosis,” IEEE Trans. Instrum. Meas., vol. 70, p. 3504909, 2021. doi: 10.1109/TIM.2020.3034975
    [17]
    S. Xing, Y. Lei, S. Wang, and F. Jia, “Distribution-invariant deep belief network for intelligent fault diagnosis of machines under new working conditions,” IEEE Trans. Ind. Electron., vol. 68, no. 3, pp. 2617–2625, Mar. 2021. doi: 10.1109/TIE.2020.2972461
    [18]
    M. Sun, H. Wang, P. Liu, S. Huang, P. Wang, and J. Meng, “Stack autoencoder transfer learning algorithm for bearing fault diagnosis based on class separation and domain fusion,” IEEE Trans. Ind. Electron., vol. 69, no. 3, pp. 3047–3058, Mar. 2022. doi: 10.1109/TIE.2021.3066933
    [19]
    N. Qin, K. Liang, D. Huang, L. Ma, and A. H. Kemp, “Multiple convolutional recurrent neural networks for fault identification and performance degradation evaluation of high-speed train bogie,” IEEE Trans. Neural Netw. Learning Syst., vol. 31, no. 12, pp. 5363–5376, Dec. 2020. doi: 10.1109/TNNLS.2020.2966744
    [20]
    K. Huang, S. Wu, F. Li, C. Yang, and W. Gui, “Fault diagnosis of hydraulic systems based on deep learning model with multirate data samples,” IEEE Trans. Neural Netw. Learning Syst., vol. 33, no. 11, pp. 6789–6801, Nov. 2022. doi: 10.1109/TNNLS.2021.3083401
    [21]
    H. Wang, R. Liu, S. X. Ding, Q. Hu, Z. Li, and H. Zhou, “Causal-trivial attention graph neural network for fault diagnosis of complex industrial processes,” IEEE Trans. Ind. Inf., vol. 20, no. 2, pp. 1987–1996, Feb. 2024. doi: 10.1109/TII.2023.3282979
    [22]
    D. Chen, Z. Xie, R. Liu, W. Yu, Q. Hu, X. Li, and S. X. Ding, “Bayesian hierarchical graph neural networks with uncertainty feedback for trustworthy fault diagnosis of industrial processes,” IEEE Trans. Neural Netw. Learning Syst., vol. 35, no. 12, pp. 18635–18648, Dec. 2024. doi: 10.1109/TNNLS.2023.3319468
    [23]
    Z. Wang, Z. Wu, X. Li, H. Shao, T. Han, and M. Xie, “Attention-aware temporal-spatial graph neural network with multi-sensor information fusion for fault diagnosis,” Knowl.-Based Syst., vol. 278, p. 110891, Oct. 2023. doi: 10.1016/j.knosys.2023.110891
    [24]
    X. Liu, M. Yan, L. Deng, G. Li, X. Ye, and D. Fan, “Sampling methods for efficient training of graph convolutional networks: A survey,” IEEE/CAA J. Autom. Sinica, vol. 9, no. 2, pp. 205–234, Feb. 2022. doi: 10.1109/JAS.2021.1004311
    [25]
    X. Hong, T. Zhang, Z. Cui, and J. Yang, “Variational gridded graph convolution network for node classification,” IEEE/CAA J. Autom. Sinica, vol. 8, no. 10, pp. 1697–1708, Oct. 2021. doi: 10.1109/JAS.2021.1004201
    [26]
    R. Wang, Z. Zhou, K. Li, T. Zhang, L. Wang, X. Xu, and X. Liao, “Learning to branch in combinatorial optimization with graph pointer networks,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 1, pp. 157–169, Jan. 2024. doi: 10.1109/JAS.2023.124113
    [27]
    M. J. A. Schuetz, J. K. Brubaker, and H. G. Katzgraber, “Combinatorial optimization with physics-inspired graph neural networks,” Nat. Mach. Intell., vol. 4, no. 4, pp. 367–377, Dec. 2022. doi: 10.1038/s42256-022-00468-6
    [28]
    J. Z. Kim, J. M. Soffer, A. E. Kahn, J. M. Vettel, F. Pasqualetti, and D. S. Bassett, “Role of graph architecture in controlling dynamical networks with applications to neural systems,” Nat. Phys., vol. 14, no. 1, pp. 91–98, Jan. 2018. doi: 10.1038/nphys4268
    [29]
    T. Li, Z. Zhao, C. Sun, R. Yan, and X. Chen, “Multireceptive field graph convolutional networks for machine fault diagnosis,” IEEE Trans. Ind. Electron., vol. 68, no. 12, pp. 12739–12749, Dec. 2021. doi: 10.1109/TIE.2020.3040669
    [30]
    Z. Chen, J. Xu, T. Peng, and C. Yang, “Graph convolutional network-based method for fault diagnosis using a hybrid of measurement and prior knowledge,” IEEE Trans. Cybern., vol. 52, no. 9, pp. 9157–9169, Sep. 2022. doi: 10.1109/TCYB.2021.3059002
    [31]
    M. Jia, J. Hu, Y. Liu, Z. Gao, and Y. Yao, “Topology-guided graph learning for process fault diagnosis,” Ind. Eng. Chem. Res., vol. 62, no. 7, pp. 3238–3248, Feb. 2023. doi: 10.1021/acs.iecr.2c03628
    [32]
    B. M. Dash, B. O. Bouamama, M. Boukerdja, and K. M. Pekpe, “Bond graph-CNN based hybrid fault diagnosis with minimum labeled data,” Eng. Appl. Artif. Intell., vol. 131, p. 107734, May 2024. doi: 10.1016/j.engappai.2023.107734
    [33]
    Y. Huang, J. Tao, J. Zhao, G. Sun, K. Yin, and J. Zhai, “Graph structure embedded with physical constraints-based information fusion network for interpretable fault diagnosis of aero-engine,” Energy, vol. 283, p. 129120, Nov. 2023. doi: 10.1016/j.energy.2023.129120
    [34]
    J. Xu, H. Ke, Z. Chen, X. Fan, T. Peng, and C. Yang, “Oversmoothing relief graph convolutional network-based fault diagnosis method with application to the rectifier of high-speed trains,” IEEE Trans. Ind. Inf., vol. 19, no. 1, pp. 771–779, Jan. 2023. doi: 10.1109/TII.2022.3167522
    [35]
    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
    [36]
    K. An, J. Lu, Q. Zhu, X. Wang, C. W. De Silva, M. Xia, and S. Lu, “Edge solution for real-time motor fault diagnosis based on efficient convolutional neural network,” IEEE Trans. Instrum. Meas., vol. 72, p. 3516912, May 2023.
    [37]
    Y. H. Pao, S. M. Phillips, and D. J. Sobajic, “Neural-net computing and the intelligent control of systems,” Int. J. Control, vol. 56, no. 2, pp. 263–289, 1992. doi: 10.1080/00207179208934315
    [38]
    M. Li and D. Wang, “Insights into randomized algorithms for neural networks: Practical issues and common pitfalls,” Inf. Sci., vol. 382-383, pp. 170–178, Mar. 2017. doi: 10.1016/j.ins.2016.12.007
    [39]
    D. Wang and M. Li, “Stochastic configuration networks: Fundamentals and algorithms,” IEEE Trans. Cybern., vol. 47, no. 10, pp. 3466–3479, Oct. 2017. doi: 10.1109/TCYB.2017.2734043
    [40]
    Q. Wang, W. Dai, X. Ma, and Z. Shang, “Driving amount based stochastic configuration network for industrial process modeling,” Neurocomputing, vol. 394, pp. 61–69, Jun. 2020. doi: 10.1016/j.neucom.2020.02.029
    [41]
    W. Dai, X. Zhou, D. Li, S. Zhu, and X. Wang, “Hybrid parallel stochastic configuration networks for industrial data analytics,” IEEE Trans. Ind. Inf., vol. 18, no. 4, pp. 2331–2341, Apr. 2022. doi: 10.1109/TII.2021.3096840
    [42]
    K. Li, J. Qiao, and D. Wang, “Online self-learning stochastic configuration networks for nonstationary data stream analysis,” IEEE Trans. Ind. Inf., vol. 20, no. 3, Mar. 2024.
    [43]
    L. Guo, J. Zhu, C. Zhang, and S. Ding, “Intuitionistic fuzzy stochastic configuration networks for solving binary classification problems,” IEEE Trans. Fuzzy Syst., vol. 32, no. 8, Aug. 2024.
    [44]
    Q. Zhang, W. Li, H. Li, and J. Wang, “Self-blast state detection of glass insulators based on stochastic configuration networks and a feedback transfer learning mechanism,” Inf. Sci., vol. 522, pp. 259–274, Jun. 2020. doi: 10.1016/j.ins.2020.02.058
    [45]
    K. Li, J. Qiao, and D. Wang, “Fuzzy stochastic configuration networks for nonlinear system modeling,” IEEE Trans. Fuzzy Syst., vol. 32, no. 3, pp. 948–957, Mar. 2024. doi: 10.1109/TFUZZ.2023.3315368
    [46]
    J. Liu, R. Hao, T. Zhang, and X. Wang, “Vibration fault diagnosis based on stochastic configuration neural networks,” Neurocomputing, vol. 434, pp. 98–125, Apr. 2021. doi: 10.1016/j.neucom.2020.12.080
    [47]
    W. Li, Q. Zhang, D. Wang, W. Sun, and Q. Li, “Stochastic configuration networks for self-blast state recognition of glass insulators with adaptive depth and multi-scale representation,” Inf. Sci., vol. 604, pp. 61–79, Aug. 2022. doi: 10.1016/j.ins.2022.04.061
    [48]
    W. Li, Y. Deng, M. Ding, D. Wang, W. Sun, and Q. Li, “Industrial data classification using stochastic configuration networks with self-attention learning features,” Neural Comput. Appl., vol. 34, no. 24, pp. 22047–22069, Aug. 2022. doi: 10.1007/s00521-022-07657-9
    [49]
    J. Ren, J. Wen, Z. Zhao, R. Yan, X. Chen, and A. K. 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
    [50]
    Y. Yao, T. Han, J. Yu, and M. Xie, “Uncertainty-aware deep learning for reliable health monitoring in safety-critical energy systems,” Energy, vol. 291, p. 130419, Mar. 2024. doi: 10.1016/j.energy.2024.130419
    [51]
    T. Zhou, T. Han, and E. L. Droguett, “Towards trustworthy machine fault diagnosis: A probabilistic Bayesian deep learning framework,” Reliab. Eng. Syst. Saf., vol. 224, p. 108525, Aug. 2022. doi: 10.1016/j.ress.2022.108525
    [52]
    K. Nagami and M. Schwager, “State estimation and belief space planning under epistemic uncertainty for learning-based perception systems,” IEEE Robot. Autom. Lett., vol. 9, no. 6, pp. 5118–5125, Jun. 2024. doi: 10.1109/LRA.2024.3387139
    [53]
    A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, Ł. Kaiser, and I. Polosukhin, “Attention is all you need,” in Proc. 31st Int. Conf. Neural Information Processing Systems, Long Beach, USA, 2017, pp. 6000-6010.
    [54]
    M. Beck, K. Pöppel, M. Spanring, A. Auer, O. Prudnikova, M. Kopp, G. Klambauer, J. Brandstetter, and S. Hochreiter, “xLSTM: Extended long short-term memory,” Proc. 38th Annu. Conf. Neural Information Processing Systems, Vancouver, Canada, 2024.
    [55]
    T. Han, W. Xie, and Z. Pei, “Semi-supervised adversarial discriminative learning approach for intelligent fault diagnosis of wind turbine,” Inf. Sci., vol. 648, p. 119496, Nov. 2023. doi: 10.1016/j.ins.2023.119496
    • 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(9)

    Get Citation
    PDF
    XML

    Article Metrics

    Article views (5) PDF downloads(0) Cited by()

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return