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 7 Issue 3
Apr.  2020

IEEE/CAA Journal of Automatica Sinica

  • JCR Impact Factor: 11.8, Top 4% (SCI Q1)
    CiteScore: 17.6, Top 3% (Q1)
    Google Scholar h5-index: 77, TOP 5
Turn off MathJax
Article Contents
Jinchuan Qian, Li Jiang and Zhihuan 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
Citation: Jinchuan Qian, Li Jiang and Zhihuan 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

Locally Linear Back-propagation Based Contribution for Nonlinear Process Fault Diagnosis

doi: 10.1109/JAS.2020.1003147
Funds:  This work was supported by the Key Project of National Natural Science Foundation of China (61933013) and Ningbo 13th Five-year Marine Economic Innovation and Development Demonstration Project (NBH Y-2017-Z1)
More Information
  • This paper proposes a novel locally linear back-propagation based contribution (LLBBC) for nonlinear process fault diagnosis. As a method based on the deep learning model of auto-encoder (AE), LLBBC can deal with the fault diagnosis problem through extracting nonlinear features. When the on-line fault diagnosis task is in progress, a locally linear model is firstly built at the current fault sample. According to the basic idea of reconstruction based contribution (RBC), the propagation of fault information is described by using back-propagation (BP) algorithm. Then, a contribution index is established to measure the correlation between the variable and the fault, and the final diagnosis result is obtained by searching variables with large contributions. The smearing effect, which is an important factor affecting the performance of fault diagnosis, can be suppressed as well, and the theoretical analysis reveals that the correct diagnosis can be guaranteed by LLBBC. Finally, the feasibility and effectiveness of the proposed method are verified through a nonlinear numerical example and the Tennessee Eastman benchmark process.

     

  • loading
  • [1]
    S. J. Qin, “Survey on data-driven industrial process monitoring and diagnosis,” Annual Reviews in Control, vol. 36, no. 2, pp. 220–234, 2012. doi: 10.1016/j.arcontrol.2012.09.004
    [2]
    Z. Q. Ge, Z. H. Song, and F. R. Gao, “Review of recent research on data-based process monitoring,” Industrial &Engineering Chemistry Research, vol. 52, no. 10, pp. 3543–3562, 2013.
    [3]
    Z. Q. Ge, Z. H. Song, S. X. Ding and H. Biao, “Data mining and analytics in the process industry: the role of machine learning,” IEEE Access, vol. 5, pp. 20590–20616, 2017. doi: 10.1109/ACCESS.2017.2756872
    [4]
    J.-M. Lee, C. Yoo, S. W. Choi, P. A. Vanrolleghem, and I.-B. Lee, “Nonlinear process monitoring using kernel principal component analysis,” Chemical Engineering Science, vol. 59, no. 1, pp. 223–234, 2004. doi: 10.1016/j.ces.2003.09.012
    [5]
    Z. Q. Ge and Z. H. Song, “Bagging support vector data description model for batch process monitoring,” J. Process Control, vol. 23, no. 8, pp. 1090–1096, 2013. doi: 10.1016/j.jprocont.2013.06.010
    [6]
    M. A. Kramer, “Nonlinear principal component analysis using autoas-sociative neural networks,” AIChE Journal, vol. 37, no. 2, pp. 233–243, 1991. doi: 10.1002/aic.690370209
    [7]
    D. Dong and T. J. McAvoy, “Nonlinear principal component analysis-based on principal curves and neural networks,” Computer &Chemical Engineering, vol. 20, no. 1, pp. 65–78, 1996.
    [8]
    K. Wang, J. H. Chen, and Z. H. Song, “Fault diagnosis for processes with feedback control loops by shifted output sampling approach,” J. Franklin Institute, vol. 355, no. 7, pp. 3249–3273, 2018. doi: 10.1016/j.jfranklin.2018.02.027
    [9]
    J. A. Westerhuis, S. P. Gurden, and A. K. Smilde, “Generalized contribution plots in multivariate statistical process monitoring,” Chemometrics and Intelligent Laboratory Systems, vol. 51, no. 1, pp. 95–114, 2000. doi: 10.1016/S0169-7439(00)00062-9
    [10]
    R. M. Tan and Y. Cao, “Multi-layer contribution propagation analysis for fault diagnosis,” Int. J. Autom. and Computing, vol. 16, no. 1, pp. 40–51, 2019. doi: 10.1007/s11633-018-1142-y
    [11]
    R. M. Tan and Y. Cao, “Deviation contribution plots of multivariate statistics,” IEEE Trans. Industrial Informatics, vol. 15, no. 2, pp. 833–841, 2018.
    [12]
    C. F. Alcala and S. J. Qin, “Reconstruction-based contribution for process monitoring,” Automatica, vol. 45, no. 7, pp. 1593–1600, 2009. doi: 10.1016/j.automatica.2009.02.027
    [13]
    C. F. Alcala and S. J. Qin, “Reconstruction-based contribution for process monitoring with kernel principal component analysis,” Industrial &Engineering Chemistry Research, vol. 49, no. 17, pp. 7849–7857, 2010.
    [14]
    Z. Q. Ge, M. G. Zhang, and Z. H. Song, “Nonlinear process monitoring based on linear subspace and bayesian inference,” J. Process Control, vol. 20, no. 5, pp. 676–688, 2010. doi: 10.1016/j.jprocont.2010.03.003
    [15]
    Z. B. Yan and Y. Yao, “Variable selection method for fault isolation using least absolute shrinkage and selection operator (LASSO),” Chemometrics and Intelligent Laboratory Systems, vol. 146, pp. 136–146, 2015. doi: 10.1016/j.chemolab.2015.05.019
    [16]
    Z. B. Yan, T.-H Kuang, and Y. Yao, “Multivariate fault isolation of batch processes via variable selection in partial least squares discriminant analysis,” ISA Trans., vol. 70, pp. 389–399, 2017. doi: 10.1016/j.isatra.2017.06.014
    [17]
    J. X. Yu, K. Wang, L. J. Ye, and Z. H. Song, “Accelerated kernel canonical correlation analysis with fault relevance for nonlinear process fault isolation,” Industrial &Engineering Chemistry Research, vol. 58, no. 39, pp. 18280–18291, 2019.
    [18]
    Y. Bengio, A. Courville, and P. Vincent, “Representation learning: A review and new perspectives,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 35, no. 8, pp. 1798–1828, 2013. doi: 10.1109/TPAMI.2013.50
    [19]
    G. E. Hinton and R. R. Salakhutdinov, “Reducing the dimensionality of data with neural networks,” Science, vol. 313, no. 5786, pp. 504–507, 2006. doi: 10.1126/science.1127647
    [20]
    X. F. Yuan, B. Huang, Y. L. Wang, C. H. Yang, and W. H. Gui, “Deep learning-based feature representation and its application for soft sensor modeling with variable-wise weighted SAE,” IEEE Trans. Industrial Information, vol. 14, no. 7, pp. 3235–3243, 2018. doi: 10.1109/TII.2018.2809730
    [21]
    X. F. Yuan, C. Ou, Y. L. Wang, C. H. Yang, and W. H. Gui, “Deep quality-related feature extraction for soft sensing modeling: a deep learning approach with hybrid VM-SAE,” Neurocomputing, Apr. 2019.
    [22]
    X. F. Yuan, L. Li, and Y. L. Wang, “Nonlinear dynamic soft sensor modeling with supervised long short-term memory network,” IEEE Trans. Industrial Information, Feb. 2019.
    [23]
    W. W. Yan, P. J. Guo, L. Gong, and Z. K. Li, “Nonlinear and robust statistical process monitoring based on variant autoencoders,” Chemometrics and Intelligent Laboratory Systems, vol. 158, pp. 31–40, 2016. doi: 10.1016/j.chemolab.2016.08.007
    [24]
    L. Jiang, Z. H. Song, Z. Q. Ge, and J. H. Chen, “Robust self-supervised model and its application for fault detection,” Industrial &Engineering Chemistry Research, vol. 56, no. 26, pp. 7503–7515, 2017.
    [25]
    H. T. Zhao, “Neural component analysis for fault detection,” Chemo- metrics and Intelligent Laboratory Systems, vol. 176, pp. 11–21, 2018. doi: 10.1016/j.chemolab.2018.02.001
    [26]
    H. D. Shao, H. K. Jiang, K. Zhao, D. D. Wei, and X. Q. Li, “A novel tracking deep wavelet auto-encoder method for intelligent fault diagnosis of electric locomotive bearings,” Mechanical Systems and Signal Processing, vol. 110, pp. 193–209, 2018. doi: 10.1016/j.ymssp.2018.03.011
    [27]
    P. Tamilselvan and P. F. Wang, “Failure diagnosis using deep belief learning based health state classification,” Reliability Engineering &System Safety, vol. 115, pp. 124–135, 2013.
    [28]
    Y. L. Wang, Z. F. Pan, X. F. Yuan, C. H. Yang, and W. H. Gui, “A novel deep learning based fault diagnosis approach for chemical process with extended deep belief network,” ISA Trans., 2019.
    [29]
    G. Alain and Y. Bengio, “What regularized auto-encoders learn from the data-generating distribution,” The J. Machine Learning Research, vol. 15, no. 1, pp. 3563–3593, 2014.
    [30]
    P. Vincent, H. Larochelle, I. Lajoie, Y. Bengio, and P.-A. Manzagol, “Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion,” J. Machine Learning Research, vol. 11, no. 12, pp. 3371–3408, Dec. 2010.
    [31]
    L. Jiang, Z. Q. Ge, and Z. H. Song, “Semi-supervised fault classification based on dynamic sparse stacked auto-encoders model,” Chemometrics and Intelligent Laboratory Systems, vol. 168, pp. 72–83, 2017. doi: 10.1016/j.chemolab.2017.06.010
    [32]
    P. R. Lyman and C. Georgakis, “Plant-wide control of the tennessee eastman problem,” Computer &Chemical Engineering, vol. 19, no. 3, pp. 321–331, 1995.

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(13)  / Tables(5)

    Article Metrics

    Article views (1274) PDF downloads(86) Cited by()

    Highlights

    • Improving the reconstructed contribution based fault diagnosis for auto-encoder.
    • Describing the propagation of the fault by the back-propagation algorithm.
    • Building the locally linear model for online fault diagnosis.
    • Proposing a special contribution index for suppressing the smearing effect.

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return