SCI和EI收录∣中国化工学会会刊

Chinese Journal of Chemical Engineering ›› 2014, Vol. 22 ›› Issue (6): 643-650.DOI: 10.1016/S1004-9541(14)60087-2

• 催化、动力学与反应工程 • 上一篇    下一篇

Fault Prediction Based on Dynamic Model and Grey Time Series Model in Chemical Processes

田文德1, 胡明刚2, 李传坤3   

  1. 1. College of Chemical Engineering, Qingdao University of Science & Technology, Qingdao 266042, China;
    2. Zibo Weichuang Petrochemical Design Co., Ltd, Zibo 255400, China;
    3. State Key Laboratory of Chemicals Safety, Qingdao Safety Engineering Institute, SINOPEC, Qingdao 266071, China
  • 收稿日期:2013-08-13 修回日期:2013-11-13 出版日期:2014-06-28 发布日期:2014-06-06
  • 通讯作者: LI Chunxi
  • 基金资助:

    Supported by the Shandong Natural Science Foundation (ZR2013BL008)

Fault Prediction Based on Dynamic Model and Grey Time Series Model in Chemical Processes

TIAN Wende1, HU Minggang2, LI Chuankun 3   

  1. 1. College of Chemical Engineering, Qingdao University of Science & Technology, Qingdao 266042, China;
    2. Zibo Weichuang Petrochemical Design Co., Ltd, Zibo 255400, China;
    3. State Key Laboratory of Chemicals Safety, Qingdao Safety Engineering Institute, SINOPEC, Qingdao 266071, China
  • Received:2013-08-13 Revised:2013-11-13 Online:2014-06-28 Published:2014-06-06
  • Supported by:

    Supported by the Shandong Natural Science Foundation (ZR2013BL008)

摘要: This paper combines grey model with time series model and then dynamic model for rapid and in-depth fault prediction in chemical processes. Two combination methods are proposed. In one method, historical data is introduced into the grey time series model to predict future trend of measurement values in chemical process. These predicted measurements are then used in the dynamic model to retrieve the change of fault parameters by model based diagnosis algorithm. In another method, historical data is introduced directly into the dynamic model to retrieve historical fault parameters by model based diagnosis algorithm. These parameters are then predicted by the grey time series model. The two methods are applied to a gravity tank example. The case study demonstrates that the first method is more accurate for fault prediction.

关键词: fault prediction, dynamic model, grey model, time series model

Abstract: This paper combines grey model with time series model and then dynamic model for rapid and in-depth fault prediction in chemical processes. Two combination methods are proposed. In one method, historical data is introduced into the grey time series model to predict future trend of measurement values in chemical process. These predicted measurements are then used in the dynamic model to retrieve the change of fault parameters by model based diagnosis algorithm. In another method, historical data is introduced directly into the dynamic model to retrieve historical fault parameters by model based diagnosis algorithm. These parameters are then predicted by the grey time series model. The two methods are applied to a gravity tank example. The case study demonstrates that the first method is more accurate for fault prediction.

Key words: fault prediction, dynamic model, grey model, time series model