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 5
Sep.  2020

IEEE/CAA Journal of Automatica Sinica

  • JCR Impact Factor: 6.171, Top 11% (SCI Q1)
    CiteScore: 11.2, Top 5% (Q1)
    Google Scholar h5-index: 51, TOP 8
Turn off MathJax
Article Contents
Yinghua Yang, Xiang Shi, Xiaozhi Liu and Hongru Li, "A Novel MDFA-MKECA Method With Application to Industrial Batch Process Monitoring," IEEE/CAA J. Autom. Sinica, vol. 7, no. 5, pp. 1446-1454, Sept. 2020. doi: 10.1109/JAS.2019.1911555
Citation: Yinghua Yang, Xiang Shi, Xiaozhi Liu and Hongru Li, "A Novel MDFA-MKECA Method With Application to Industrial Batch Process Monitoring," IEEE/CAA J. Autom. Sinica, vol. 7, no. 5, pp. 1446-1454, Sept. 2020. doi: 10.1109/JAS.2019.1911555

A Novel MDFA-MKECA Method With Application to Industrial Batch Process Monitoring

doi: 10.1109/JAS.2019.1911555
Funds:  This work was supported by National Key R & D Program of China (Smart process control technology for aluminum & copper strip based on industrial big data) (2017YFB0306405)
More Information
  • For the complex batch process with characteristics of unequal batch data length, a novel data-driven batch process monitoring method is proposed based on mixed data features analysis and multi-way kernel entropy component analysis (MDFA-MKECA) in this paper. Combining the mechanistic knowledge, different mixed data features of each batch including statistical and thermodynamics entropy features, are extracted to finish data pre-processing. After that, MKECA is applied to reduce data dimensionality and finally establish a monitoring model. The proposed method is applied to a reheating furnace industry process, and the experimental results demonstrate that the MDFA-MKECA method can reduce the calculated amount and effectively provide on-line monitoring of the batch process.

     

  • loading
  • [1]
    Z. Ge, Z. Song, and F. Gao, “Review of recent research on data-based process monitoring,” Industrial &Engineering Chemistry Research, vol. 52, no. 10, pp. 3543–3562, 2013.
    [2]
    Y. Gao, X. Wang, Z. Wang, and L. Zhao, “External analysis and moving window loop based monitoring for a class of multi-mode timevarying process,” IEEE/CAA J. Autom. Sinica, pp. 1–10, 2017. doi: 10.1109/JAS.2017.7510703
    [3]
    H. Abdi and L. J. Williams, “Principal component analysis,” Wiley Interdisciplinary Reviews Computational Statistics, vol. 2, no. 4, pp. 433–459, 2010.
    [4]
    K. X. Peng, M. A. Liang, and Z. Kai, “Review of quality-related fault detection and diagnosis techniques for complex industrial processes,” Acta Automatica Sinica, vol. 43, no. 3, pp. 349–365, 2017.
    [5]
    N. A. A. Majid, M. P. Taylor, J. J. J. Chen, M. A. Stam, A. Mulder, and B. R. Young, “Aluminium process fault detection by multiway principal component analysis,” Control Engineering Practice, vol. 19, no. 4, pp. 367–379, 2011. doi: 10.1016/j.conengprac.2010.12.005
    [6]
    S. Stubbs, J. Zhang, and J. Morris, “Multiway interval partial least squares for batch process performance monitoring,” Industrial &Engineering Chemistry Research, vol. 52, no. 35, pp. 12399–12407, 2013.
    [7]
    G. Hui and L. Hongguang, “On-line batch process monitoring with improved multi-way independent component analysis,” Chinese J. Chemical Engineering, vol. 21, no. 3, pp. 263–270, 2013. doi: 10.1016/S1004-9541(13)60485-4
    [8]
    J.-M. Lee, C. Yoo, and I.-B. Lee, “Fault detection of batch processes using multiway kernel principal component analysis,” Computers &chemical engineering, vol. 28, no. 9, pp. 1837–1847, 2004.
    [9]
    J. Mori and J. Yu, “Quality relevant nonlinear batch process performance monitoring using a kernel based multiway non-gaussian latent subspace projection approach,” J. Process Control, vol. 24, no. 1, pp. 57–71, 2014. doi: 10.1016/j.jprocont.2013.10.017
    [10]
    L. Di, Z. Xiong, and X. Yang, “Nonlinear process modeling and optimization based on multiway kernel partial least squares model,” in Proc. IEEE Winter Simulation Conf., 2008, pp. 1645–1651.
    [11]
    P. Chang, P. Wang, and X. Gao, “Microbial pharmaceutical process monitoring based on projection kernel entropy component,” Information and Control, vol. 43, no. 4, pp. 490–494, 2014.
    [12]
    T. Kourti, “Multivariate dynamic data modeling for analysis and statistical process control of batch processes, start-ups and grade transitions,” J. Chemometrics, vol. 17, no. 1, pp. 93–109, 2003. doi: 10.1002/(ISSN)1099-128X
    [13]
    P. Nomikos and J. F. MacGregor, “Multivariate spc charts for monitoring batch processes,” Technometrics, vol. 37, no. 1, pp. 41–59, 1995. doi: 10.1080/00401706.1995.10485888
    [14]
    H. Sakoe and S. Chiba, “Dynamic programming algorithm optimization for spoken word recognition,” IEEE Trans. Acoustics,Speech,and Signal Processing, vol. 26, no. 1, pp. 43–49, 1978. doi: 10.1109/TASSP.1978.1163055
    [15]
    K. Zhang, K. Peng, and J. Dong, “A common and individual feature extraction-based multimode process monitoring method with application to the finishing mill process,” IEEE Trans. Industrial Informatics, vol. 14, no. 11, pp. 4841–4850, 2018.
    [16]
    K. Zhang, H. Hao, Z. Chen, S. X. Ding, and K. Peng, “A comparison and evaluation of key performance indicator-based multivariate statistics process monitoring approaches,” J. Process Control, vol. 33, pp. 112–126, 2015. doi: 10.1016/j.jprocont.2015.06.007
    [17]
    Y. J. Jang and S. W. Kim, “An estimation of a billet temperature during reheating furnace operation,” Int. J. Control,Automation,and Systems, vol. 5, no. 1, pp. 43–50, 2007.
    [18]
    C. Miao, H.-G. Chen, X. Li, and W. Bin, “Total heat exchange factor based on non-gray radiation properties of gas in reheating furnace,” J. Iron and Steel Research,International, vol. 16, no. 3, pp. 27–63, 2009. doi: 10.1016/S1006-706X(09)60039-X
    [19]
    Q. P. He and J. Wang, “Statistics pattern analysis: A new process monitoring framework and its application to semiconductor batch processes,” AIChE J., vol. 57, no. 1, pp. 107–121, 2011. doi: 10.1002/aic.12247
    [20]
    Z. Jj, “Thermodynamic entropy and information entropy,” J. Wuhan University of Science and Technology (Natural Science Edition), vol. 1988, no. 4, pp. 21–23, 1988.
    [21]
    D. Aguado, A. Ferrer, J. Ferrer, and A. Seco, “Multivariate spc of a sequencing batch reactor for wastewater treatment,” Chemometrics and Intelligent Laboratory Systems, vol. 85, no. 1, pp. 82–93, 2007. doi: 10.1016/j.chemolab.2006.05.003
    [22]
    S. Wold, N. Kettaneh, H. Fridén, and A. Holmberg, “Modelling and diagnostics of batch processes and analogous kinetic experiments,” Chemometrics and Intelligent Laboratory Systems, vol. 44, no. 1–2, pp. 331–340, 1998. doi: 10.1016/S0169-7439(98)00162-2
    [23]
    Y. Yinghua, L. Huaqing, L. Chenlong, Q. Shukai, and C. Xiaobo, “Kernel entropy component analysis based process monitoring method with process subsystem division,” in Proc. 27th IEEE Conf. Control and Decision, 2015, pp. 2684–2688.

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(4)  / Tables(2)

    Article Metrics

    Article views (1080) PDF downloads(34) Cited by()

    Highlights

    • In this paper, a novel batch process monitoring method MDFA-MKECA is proposed for on-line process monitoring of industry process. The method achieve real-time monitoring with great performance by combining prior mechanistic knowledge and statistical and thermodynamic theory. Computational results demonstrate that the monitoring performance of MDFA-MKECA is superior to its competitors.
    • The proposed data feature extraction method, namely MDFA, can not only effectively extract the feature information of process data with complex characteristics in industrial processes, but also make up for the shortcoming of traditional multivariate statistical process monitoring that cannot handle batch data whose batch length are unequal.
    • For the reheating furnace process, we provide a more refined monitoring method based on MKECA in process monitoring, which can establish different monitoring models in differentiated physical zones to ensure that the abnormalities of the running state can be more accurately located.

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return