SCI和EI收录∣中国化工学会会刊

Chinese Journal of Chemical Engineering ›› 2018, Vol. 26 ›› Issue (8): 1599-1604.DOI: 10.1016/j.cjche.2017.09.023

• Selected Papers from the Chinese Process Systems Engineering Annual Meeting 2017 •    下一篇

Feature selection for chemical process fault diagnosis by artificial immune systems

Liang Ming, Jinsong Zhao   

  1. Department of Chemical Engineering, Tsinghua University, Beijing 100084, China;Beijing Key Laboratory of Industrial Big Data System and Application, Tsinghua University, Beijing 100084, China
  • 收稿日期:2017-09-08 出版日期:2018-08-28 发布日期:2018-09-21
  • 通讯作者: Jinsong Zhao,E-mail address:jinsongzhao@tsinghua.edu.cne
  • 基金资助:

    Supported by the National Natural Science Foundation of China (61433001).

Feature selection for chemical process fault diagnosis by artificial immune systems

Liang Ming, Jinsong Zhao   

  1. Department of Chemical Engineering, Tsinghua University, Beijing 100084, China;Beijing Key Laboratory of Industrial Big Data System and Application, Tsinghua University, Beijing 100084, China
  • Received:2017-09-08 Online:2018-08-28 Published:2018-09-21
  • Contact: Jinsong Zhao,E-mail address:jinsongzhao@tsinghua.edu.cne
  • Supported by:

    Supported by the National Natural Science Foundation of China (61433001).

摘要: With the Industry 4.0 era coming, modern chemical plants will be gradually transformed into smart factories, which sets higher requirements for fault detection and diagnosis (FDD) to enhance operation safety intelligence. In a typical chemical process, there are hundreds of process variables. Feature selection is a key to the efficiency and effectiveness of FDD. Even though artificial immune system has advantages in adaptation and independency on a large number of fault samples, antibody library construction used to be based on experience. It is not only time consuming, but also lack of scientific foundation in fault feature selection, which may deteriorate the FDD performance of the AIS. In this paper, a fault antibody feature selection optimization (FAFSO) algorithm is proposed based on genetic algorithm to optimize the fault antibody features and the antibody libraries' thresholds simultaneously. The performance of the proposed FAFSO algorithms is illustrated through the Tennessee Eastman benchmark problem.

关键词: Artificial immune system, Genetic algorithm, Feature selection

Abstract: With the Industry 4.0 era coming, modern chemical plants will be gradually transformed into smart factories, which sets higher requirements for fault detection and diagnosis (FDD) to enhance operation safety intelligence. In a typical chemical process, there are hundreds of process variables. Feature selection is a key to the efficiency and effectiveness of FDD. Even though artificial immune system has advantages in adaptation and independency on a large number of fault samples, antibody library construction used to be based on experience. It is not only time consuming, but also lack of scientific foundation in fault feature selection, which may deteriorate the FDD performance of the AIS. In this paper, a fault antibody feature selection optimization (FAFSO) algorithm is proposed based on genetic algorithm to optimize the fault antibody features and the antibody libraries' thresholds simultaneously. The performance of the proposed FAFSO algorithms is illustrated through the Tennessee Eastman benchmark problem.

Key words: Artificial immune system, Genetic algorithm, Feature selection