SCI和EI收录∣中国化工学会会刊

Chinese Journal of Chemical Engineering ›› 2022, Vol. 47 ›› Issue (7): 54-70.DOI: 10.1016/j.cjche.2021.03.058

Previous Articles     Next Articles

Cycle temporal algorithm-based multivariate statistical methods for fault diagnosis in chemical processes

Jiaxin Zhang1, Wenjia Luo1, Yiyang Dai2, Yuman Yao1   

  1. 1. School of Chemistry and Chemical Engineering, Southwest Petroleum University, Chengdu 610500, China;
    2. School of Chemical Engineering, Sichuan University, Chengdu 610065, China
  • Received:2021-01-05 Revised:2021-03-10 Online:2022-08-19 Published:2022-07-28
  • Contact: Wenjia Luo,E-mail:luowenjia@swpu.edu.cn;Yiyang Dai,E-mail:daiyy@scu.edu.cn
  • Supported by:
    The authors gratefully acknowledge financial support from the National Natural Science Foundation of China (21706220).

Cycle temporal algorithm-based multivariate statistical methods for fault diagnosis in chemical processes

Jiaxin Zhang1, Wenjia Luo1, Yiyang Dai2, Yuman Yao1   

  1. 1. School of Chemistry and Chemical Engineering, Southwest Petroleum University, Chengdu 610500, China;
    2. School of Chemical Engineering, Sichuan University, Chengdu 610065, China
  • 通讯作者: Wenjia Luo,E-mail:luowenjia@swpu.edu.cn;Yiyang Dai,E-mail:daiyy@scu.edu.cn
  • 基金资助:
    The authors gratefully acknowledge financial support from the National Natural Science Foundation of China (21706220).

Abstract: Multivariate statistical process monitoring methods are often used in chemical process fault diagnosis. In this article, (I) the cycle temporal algorithm (CTA) combined with the dynamic kernel principal component analysis (DKPCA) and the multiway dynamic kernel principal component analysis (MDKPCA) fault detection algorithms are proposed, which are used for continuous and batch process fault detections, respectively. In addition, (II) a fault variable identification model based on reconstructed-based contribution (RBC) model that paves the way for determining the cause of the fault are proposed. The proposed fault diagnosis model was applied to Tennessee Eastman (TE) process and penicillin fermentation process for fault diagnosis. And compare with other fault diagnosis methods. The results show that the proposed method has better detection effects than other methods. Finally, the reconstruction-based contribution (RBC) model method is used to accurately locate the root cause of the fault and determine the fault path.

Key words: Cycle temporal algorithm, Fault diagnosis, Dynamic kernel principal component analysis, Multiway dynamic kernel principal component analysis, Reconstruction-based contribution

摘要: Multivariate statistical process monitoring methods are often used in chemical process fault diagnosis. In this article, (I) the cycle temporal algorithm (CTA) combined with the dynamic kernel principal component analysis (DKPCA) and the multiway dynamic kernel principal component analysis (MDKPCA) fault detection algorithms are proposed, which are used for continuous and batch process fault detections, respectively. In addition, (II) a fault variable identification model based on reconstructed-based contribution (RBC) model that paves the way for determining the cause of the fault are proposed. The proposed fault diagnosis model was applied to Tennessee Eastman (TE) process and penicillin fermentation process for fault diagnosis. And compare with other fault diagnosis methods. The results show that the proposed method has better detection effects than other methods. Finally, the reconstruction-based contribution (RBC) model method is used to accurately locate the root cause of the fault and determine the fault path.

关键词: Cycle temporal algorithm, Fault diagnosis, Dynamic kernel principal component analysis, Multiway dynamic kernel principal component analysis, Reconstruction-based contribution