SCI和EI收录∣中国化工学会会刊

Chinese Journal of Chemical Engineering ›› 2015, Vol. 23 ›› Issue (12): 1970-1980.DOI: 10.1016/j.cjche.2015.09.007

• 第25届中国过程控制会议专栏 • 上一篇    下一篇

A novel multimode processmonitoring method integrating LCGMMwith modified LFDA

Shijin Ren1,2, Zhihuan Song1, Maoyun Yang2, Jianguo Ren 2   

  1. 1 National Laboratory of Industrial Control Technology, Zhejiang University, Hangzhou 310027, China;
    2 School of Computer Science & Technology, Jiangsu Normal University, Jiangsu, 221116, China
  • 收稿日期:2015-05-25 修回日期:2015-07-27 出版日期:2015-12-28 发布日期:2016-01-19
  • 通讯作者: Shijin Ren
  • 基金资助:

    Supported by the National Natural Science Foundation of China (61273167).

A novel multimode processmonitoring method integrating LCGMMwith modified LFDA

Shijin Ren1,2, Zhihuan Song1, Maoyun Yang2, Jianguo Ren 2   

  1. 1 National Laboratory of Industrial Control Technology, Zhejiang University, Hangzhou 310027, China;
    2 School of Computer Science & Technology, Jiangsu Normal University, Jiangsu, 221116, China
  • Received:2015-05-25 Revised:2015-07-27 Online:2015-12-28 Published:2016-01-19
  • Contact: Shijin Ren
  • Supported by:

    Supported by the National Natural Science Foundation of China (61273167).

摘要: Complex processes often work with multiple operation regions, it is critical to develop effective monitoring approaches to ensure the safety of chemical processes. In this work, a discriminant local consistency Gaussianmixture model (DLCGMM) for multimode process monitoring is proposed for multimode process monitoring by integrating LCGMMwith modified local Fisher discriminant analysis (MLFDA).Different fromFisher discriminant analysis (FDA) that aims to discover the global optimal discriminant directions, MLFDA is capable of uncovering multimodality and local structure of the data by exploiting the posterior probabilities of observations within clusters calculated fromthe results of LCGMM. This may enableMLFDA to capturemoremeaningful discriminant information hidden in the high-dimensional multimode observations comparing to FDA. Contrary to most existing multimode process monitoring approaches, DLCGMMperforms LCGMMandMFLDA iteratively, and the optimal subspaces with multi-Gaussianity and the optimal discriminant projection vectors are simultaneously achieved in the framework of supervised and unsupervised learning. Furthermore, monitoring statistics are established on each cluster that represents a specific operation condition and two global Bayesian inference-based faultmonitoring indexes are established by combining with all themonitoring results of all clusters. The efficiency and effectiveness of the proposed method are evaluated through UCI datasets, a simulated multimode model and the Tennessee Eastman benchmark process.

关键词: Multimode process monitoring, Discriminant local consistency Gaussian, mixture model, Modified local Fisher discriminant analysis, Global fault detection index, Tennessee Eastman process

Abstract: Complex processes often work with multiple operation regions, it is critical to develop effective monitoring approaches to ensure the safety of chemical processes. In this work, a discriminant local consistency Gaussianmixture model (DLCGMM) for multimode process monitoring is proposed for multimode process monitoring by integrating LCGMMwith modified local Fisher discriminant analysis (MLFDA).Different fromFisher discriminant analysis (FDA) that aims to discover the global optimal discriminant directions, MLFDA is capable of uncovering multimodality and local structure of the data by exploiting the posterior probabilities of observations within clusters calculated fromthe results of LCGMM. This may enableMLFDA to capturemoremeaningful discriminant information hidden in the high-dimensional multimode observations comparing to FDA. Contrary to most existing multimode process monitoring approaches, DLCGMMperforms LCGMMandMFLDA iteratively, and the optimal subspaces with multi-Gaussianity and the optimal discriminant projection vectors are simultaneously achieved in the framework of supervised and unsupervised learning. Furthermore, monitoring statistics are established on each cluster that represents a specific operation condition and two global Bayesian inference-based faultmonitoring indexes are established by combining with all themonitoring results of all clusters. The efficiency and effectiveness of the proposed method are evaluated through UCI datasets, a simulated multimode model and the Tennessee Eastman benchmark process.

Key words: Multimode process monitoring, Discriminant local consistency Gaussian, mixture model, Modified local Fisher discriminant analysis, Global fault detection index, Tennessee Eastman process