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
Volume 13 Issue 8
Aug.  2026

IEEE/CAA Journal of Automatica Sinica

  • JCR Impact Factor: 18.3, Top 1 (SCI Q1)
    CiteScore: 28.2, Top 1% (Q1)
    Google Scholar h5-index: 95， TOP 5
Turn off MathJax
Article Contents
Article Navigation >  IEEE/CAA Journal of Automatica Sinica  > 2026  >  13(8): 1865-1882
S. Wang, K. Wang, S. Zhang, and C. Yang, “Uncertainty explicit learning: An interval generalized neural network with adaptivity for anomaly identification under data uncertainty,” IEEE/CAA J. Autom. Sinica, vol. 13, no. 8, pp. 1865–1882, Aug. 2026. doi: 10.1109/JAS.2025.125939
Citation: S. Wang, K. Wang, S. Zhang, and C. Yang, “Uncertainty explicit learning: An interval generalized neural network with adaptivity for anomaly identification under data uncertainty,” IEEE/CAA J. Autom. Sinica, vol. 13, no. 8, pp. 1865–1882, Aug. 2026. doi: 10.1109/JAS.2025.125939
shu

Uncertainty Explicit Learning: An Interval Generalized Neural Network With Adaptivity for Anomaly Identification Under Data Uncertainty

doi: 10.1109/JAS.2025.125939
Funds:  This work was supported in part by the National Natural Science Foundation of China (62373277, 62394340, 62373378, 62373271), the Hunan Young Talents in Science and Technology Innovation (2024RC3028), and the Natural Science Foundation of Tianjin (23JCZDJC01140)
More Information
    Abstract
  • In real industrial processes, the collected process data often suffer from measurement uncertainty due to noise interference, sensor drift, and harsh operating environment. The existence of uncertainty may undermine the correlation structure of original data, resulting in the failure of traditional machine learning methods in anomaly identification. In this study, an interval generalized radial basis function neural network (IGRBFNN) based on key fault feature extraction is proposed for abnormal condition identification under data uncertainty. Specifically, kernel density estimation (KDE) is first introduced to explicitly characterize the uncertainty-contaminated data in interval form. For interval process data, an interval linear discriminant analysis (ILDA) method is developed to maximize the projection distance between different fault categories and minimize the projection distance within the same fault category, thus achieving key fault feature extraction under the mask of uncertainty. Subsequently, by embedding a generalized Gaussian function with adaptive characteristics and combining the mathematical theory of interval analysis, an IGRBFNN model is further constructed to enhance the generalization ability of traditional neural networks. Finally, motivated by autonomous clustering, an interval generalized self-organizing map (IGSOM) network is developed to intelligently learn the model parameters of IGRBFNN. Extensive experiments on two cases demonstrate the flexibility and applicability of the constructed anomaly identification model.

     

    • FullText(HTML)
  • loading
    • References(42)
  • [1]
    X. Yuan, W. Xu, Y. Wang, C. Yang, and W. Gui, “A deep residual PLS for data-driven quality prediction modeling in industrial process,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 8, pp. 1777–1785, Aug. 2024. doi: 10.1109/JAS.2024.124578
    [2]
    K. Wang, C. Yan, Y. Mo, Y. Wang, X. Yuan, and C. Liu, “Anomaly detection using large-scale multimode industrial data: An integration method of nonstationary kernel and autoencoder,” Eng. Appl. Artif. Intell., vol. 131, Art. no. 107839, May 2024.
    [3]
    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
    [4]
    W. Yu, C. Zhao, B. Huang, and M. Xie, “An unsupervised fault detection and diagnosis with distribution dissimilarity and lasso penalty,” IEEE. Trans. Control Syst. Technol., vol. 32, no. 3, pp. 767–779, May 2024. doi: 10.1109/TCST.2023.3330443
    [5]
    Y. Zhu, N. Xu, F. Wu, X. Chen, and D. Zhou, “Fault estimation for a class of Markov jump piecewise-affine systems: Current feedback based iterative learning approach,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 2, pp. 418–429, Feb. 2024. doi: 10.1109/JAS.2023.123990
    [6]
    W. Shabbir, A. Li, M. Taimoor, and Y. Cui, “Global fast terminal sliding mode based radial basis function neural network for accurate fault estimation in nonlinear systems,” J. Intell. Fuzzy Syst., vol. 42, no. 3, pp. 2229–2245, Feb. 2022. doi: 10.3233/jifs-211547
    [7]
    G. S. Lumacad and R. A. Namoco, “Multilayer perceptron neural network approach to classifying learning modalities under the new normal,” IEEE Trans. Comput. Soc. Syst., vol. 11, no. 1, pp. 1169–1181, Feb. 2024. doi: 10.1109/TCSS.2023.3251566
    [8]
    S. Jiang, Q. Li, R. Gan, and W. Chen, “Fault diagnosis for PEMFC water management subsystem based on learning vector quantization neural network and kernel principal component analysis,” World Electr. Veh. J., vol. 12, no. 4, Art. no. 255, Dec. 2021.
    [9]
    W. Jiang, “A novel big data classification algorithm based on backpropagation neural network,” Rev. d’Intell. Artif., vol. 34, no. 2, pp. 203–208, Apr. 2020.
    [10]
    M. M. Islam, G. Lee, and S. N. Hettiwatte, “Application of a general regression neural network for health index calculation of power transformers,” Int. J. Electr. Power Energy Syst., vol. 93, pp. 308–315, Dec. 2017. doi: 10.1016/j.ijepes.2017.06.008
    [11]
    C.-C. Chang and C.-J. Lin, “LIBSVM: A Library for support vector machines,” ACM Trans. Intell. Syst. Technol., vol. 2, no. 3, Art. no. 27, Apr. 2011.
    [12]
    Y. Yuan, Y. Wang, and X. Luo, “A node-collaboration-informed graph convolutional network for highly accurate representation to undirected weighted graph,” IEEE Trans. Neural Netw. Learn. Syst., vol. 36, no. 6, pp. 11507–11519, Jun. 2025. doi: 10.1109/TNNLS.2024.3514652
    [13]
    L. Wang, K. Liu, and Y. Yuan, “GT-A2T: Graph tensor alliance attention network,” IEEE/CAA J. Autom. Sinica, vol. 12, no. 10, pp. 2165–2167, Oct. 2025. doi: 10.1109/JAS.2024.124863
    [14]
    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
    [15]
    S. Zhang, S. Du, and F. Dong, “Concurrent analysis of static deviation and dynamic oscillation for momentum wheel bearing health monitoring and prognostication,” J. Process Control, vol. 141, Art. no. 103278, Sep. 2024.
    [16]
    C. Li, Y. Yu, L. Shang, H. Zhang, and Y. Jiang, “Fault diagnosis of air handling unit via combining probabilistic slow feature analysis and attention residual network,” Neural Comput. Appl., vol. 35, no. 30, pp. 22449–22467, Oct. 2023. doi: 10.1007/s00521-023-08910-5
    [17]
    Z. Chen, Y. Yang, C. He, Y. Liu, X. Liu, and Z. Gao, “Feature extraction based on hierarchical improved envelope spectrum entropy for rolling bearing fault diagnosis,” IEEE Trans. Instrum. Meas., vol. 72, Art. no. 3518912, Jan. 2023.
    [18]
    S.-K. S. Fan, C.-Y. Hsu, D.-M. Tsai, M. C. Chou, C.-H. Jen, and J.-H. Tsou, “Key feature identification for monitoring wafer-to-wafer variation in semiconductor manufacturing,” IEEE Trans. Autom. Sci. Eng., vol. 19, no. 3, pp. 1530–1541, Jul. 2022. doi: 10.1109/TASE.2022.3141426
    [19]
    S. Zhang, S. Wang, Q. Lei, and C. Zhao, “Cross-domain bilateral transfer learning for fault diagnosis under incomplete multisource domains,” IEEE Trans. Autom. Sci. Eng., vol. 22, pp. 4298–4310, Jun. 2025. doi: 10.1109/TASE.2024.3409621
    [20]
    J. Yuan, S. Zhang, S. Wang, F. Wang, and L. Zhao, “Process abnormity identification by fuzzy logic rules and expert estimated thresholds derived certainty factor,” Chemometr. Intell. Lab. Syst., vol. 209, Art. no. 104232, Feb. 2021.
    [21]
    M. M. Elsutohy, B. Fuladpanjeh-Hojaghan, E. P. L. Roberts, and M. Trifkovic, “Mechanistic insight into electrode processes by operando visualization of interfacial pH using fluorescent nanosensors,” Environ. Sci. Technol., vol. 57, pp. 9865–9873, Jun. 2023. doi: 10.1021/acs.est.2c08763
    [22]
    W.-H. Gui, Y.-G. Li, and Y.-L. Wang, “Soft sensor for ratio of soda to aluminate based on PCA-RBF multiple network,” J. Cent. South Univ. Technol., vol. 12, no. 1, pp. 88–92, Oct. 2005. doi: 10.1007/s11771-005-0210-y
    [23]
    K. Wang, W. Zhao, L. Lin, T. Wang, P. Wei, R. Ledesma-Amaro, A.-H. Zhang, and X.-J. Ji, “A robust soft sensor based on artificial neural network for monitoring microbial lipid fermentation processes using Yarrowia lipolytica,” Biotechnol. Bioeng., vol. 120, no. 4, pp. 1015–1025, Apr. 2023. doi: 10.1002/bit.28310
    [24]
    L. Hsu, P. R. Selvaganapathy, J. Brash, Q. Fang, C.-Q. Xu, M. J. Deen, and H. Chen, “Development of a low-cost hemin-based dissolved oxygen sensor with anti-biofouling coating for water monitoring,” IEEE Sensors J., vol. 14, no. 10, pp. 3400–3407, Oct. 2014. doi: 10.1109/JSEN.2014.2332513
    [25]
    H. Ke, Y. Chen, and Y. Liu, “Data processing of small samples based on grey distance information approach,” J. Syst. Eng. Electron., vol. 18, no. 2, pp. 281–289, Jun. 2007.
    [26]
    J. Yuan, S. Wang, F. Wang, and S. Zhang, “Abnormal condition identification via OVR-IRBF-NN for the process industry with imprecise data and semantic information,” Ind. Eng. Chem. Res., vol. 59, no. 11, pp. 5072–5086, Feb. 2020. doi: 10.1021/acs.iecr.9b06554
    [27]
    L. Rouani, M. F. Harkat, A. Kouadri, and S. Mekhilef, “Shading fault detection in a grid-connected PV system using vertices principal component analysis,” Renew. Energy, vol. 164, pp. 1527–1539, Feb. 2021. doi: 10.1016/j.renene.2020.10.059
    [28]
    N. Li, H. Ding, X. Sun, Z. Liu, and G. Pu, “Intelligent fault diagnosis for nonlinear uncertain industrial processes based on simplified interval kernel global-local feature embedding,” IEEE Sensors J., vol. 24, no. 4, pp. 5414–5431, Feb. 2024. doi: 10.1109/JSEN.2023.3349296
    [29]
    S. Zhang, S. Wang, and F. Dong, “Generalized Gaussian distribution-based interval principal component analysis (GGD-IPCA) for anomaly detection of processes with uncertainty,” IEEE Trans. Instrum. Meas., vol. 73, Art. no. 2516315, Jan. 2024.
    [30]
    S. Zhang, S. Wang, and C. Zhao, “Vertices packaging-based interval independent component analysis (VP-I2CA) for fault detection with process uncertainty,” IEEE Trans. Ind. Inform., vol. 20, no. 1, pp. 919–930, Jan. 2024. doi: 10.1109/TII.2023.3271737
    [31]
    Y. Xiao, Y. Zhao, F. Han, K. Peng, and F. Wan, “A probabilistic neural network with adaptive capability to optimize fault trees for the intelligent fault diagnosis of rapier loom throughout its operating cycle,” J. Intell. Fuzzy Syst.: Appl. Eng. Technol., vol. 45, no. 5, pp. 7237–7257, Nov. 2023. doi: 10.3233/jifs-233009
    [32]
    B. Qi, L. Zhang, J. Liang, and J. Tong, “Combinatorial techniques for fault diagnosis in nuclear power plants based on Bayesian neural network and simplified Bayesian network-artificial neural network,” Front. Energy Res., vol. 10, Art. no. 920194, Jun. 2022.
    [33]
    A. Basalamah, M. Hasan, S. Bhowmik, and S. A. Shahriyar, “A highly accurate dysphonia detection system using linear discriminant analysis,” Comput. Syst. Sci. Eng., vol. 44, no. 3, pp. 1921−1938, 2023.
    [34]
    D. S. Broomhead, R. Jones, J. G. McWhirter, and T. J. Shepherd, “Systolic array for nonlinear multidimensional interpolation using radial basis functions,” Electron. Lett., vol. 26, no. 1, pp. 7–9, Jan. 1990. doi: 10.1049/el:19900005
    [35]
    W. D. Kahn, “Measurement uncertainty: Methods and applications,” Technometrics, vol. 36, no. 4, pp. 432–433, Nov. 1994.
    [36]
    Y. Lu, L. Cheng, T. Isenberg, C.-W. Fu, G. Chen, H. Liu, O. Deussen, and Y. Wang, “Curve complexity heuristic KD-trees for neighborhood-based exploration of 3D curves,” Comput. Graphics Forum, vol. 40, no. 2, pp. 461–474, May 2021.
    [37]
    R. Moore, Interval Analysis. Englewood Cliffs, USA: Prentice-Hall, 1966.
    [38]
    G.-F. Lin and L.-H. Chen, “Time series forecasting by combining the radial basis function network and the self-organizing map,” Hydrol. Processes, vol. 19, no. 10, pp. 1925–1937, Jun. 2005. doi: 10.1002/hyp.5637
    [39]
    J. Qian, L. Jiang, and Z. Song, “Locally linear back-propagation based contribution for nonlinear process fault diagnosis,” IEEE/CAA J. Autom. Sinica, vol. 7, no. 3, pp. 764–775, May 2020. doi: 10.1109/jas.2020.1003147
    [40]
    H. Lahdhiri and O. Taouali, “Interval valued data driven approach for sensor fault detection of nonlinear uncertain process,” Measurement, vol. 171, Art. no. 108776, Feb. 2021.
    [41]
    S. Zhang and S. Wang, “Spectral radius-based interval principal component analysis (SR-IPCA) for fault detection in industrial processes with imprecise data,” J. Process Control, vol. 114, pp. 105–119, Jun. 2022. doi: 10.1016/j.jprocont.2022.04.010
    [42]
    L. P. Russo and B. W. Bequette, “Effect of process design on the open-loop behavior of a jacketed exothermic CSTR,” Comput. Chem. Eng., vol. 20, no. 4, pp. 417–426, Apr. 1996. doi: 10.1016/0098-1354(95)00031-3
    • 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(21)  / Tables(11)

    Get Citation
    PDF
    XML

    Article Metrics

    Article views (13) PDF downloads(1) Cited by()

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return