SCI和EI收录∣中国化工学会会刊

Chinese Journal of Chemical Engineering ›› 2016, Vol. 24 ›› Issue (11): 1631-1639.DOI: 10.1016/j.cjche.2016.08.013

• 第25届中国过程控制会议专栏 • 上一篇    下一篇

Simultaneous hybrid modeling of a nosiheptide fermentation process using particle swarm optimization

Qiangda Yang1, Hongbo Gao2, Weijun Zhang1, Huimin Li1   

  1. 1 School of Metallurgy, Northeastern University, Shenyang 110819, China;
    2 Department of Electromechanical Engineering, Liaoning Provincial College of Communications, Shenyang 110122, China
  • 收稿日期:2016-05-06 修回日期:2016-08-18 出版日期:2016-11-28 发布日期:2016-12-06
  • 通讯作者: Qiangda Yang
  • 基金资助:

    Supported by the Specialized Research Fund for the Doctoral Program of Higher Education (No. 20120042120014).

Simultaneous hybrid modeling of a nosiheptide fermentation process using particle swarm optimization

Qiangda Yang1, Hongbo Gao2, Weijun Zhang1, Huimin Li1   

  1. 1 School of Metallurgy, Northeastern University, Shenyang 110819, China;
    2 Department of Electromechanical Engineering, Liaoning Provincial College of Communications, Shenyang 110122, China
  • Received:2016-05-06 Revised:2016-08-18 Online:2016-11-28 Published:2016-12-06
  • Contact: Qiangda Yang
  • Supported by:

    Supported by the Specialized Research Fund for the Doctoral Program of Higher Education (No. 20120042120014).

摘要: Hybrid modeling approaches have recently been investigated as an attractive alternative to model fermentation processes. Normally, these approaches require estimation data to train the empirical model part of a hybrid model. This may result in decreasing the generalization ability of the derived hybridmodel. Therefore, a simultaneous hybridmodeling approach is presented in this paper. It transforms the training of the empiricalmodel part into a dynamic system parameter identification problem, and thus allows training the empiricalmodel partwith only measured data. An adaptive escaping particle swarm optimization (AEPSO) algorithm with escaping and adaptive inertia weight adjustment strategies is constructed to solve the resulting parameter identification problem, and thereby accomplish the training of the empirical model part. The uniform design method is used to determine the empirical model structure. The proposed simultaneous hybrid modeling approach has been used in a lab-scale nosiheptide batch fermentation process. The results show that it is effective and leads to a more consistent model with better generalization ability when compared to existing ones. The performance of AEPSO is also demonstrated.

关键词: Bioprocess, Dynamic modeling, Neural networks, Optimization

Abstract: Hybrid modeling approaches have recently been investigated as an attractive alternative to model fermentation processes. Normally, these approaches require estimation data to train the empirical model part of a hybrid model. This may result in decreasing the generalization ability of the derived hybridmodel. Therefore, a simultaneous hybridmodeling approach is presented in this paper. It transforms the training of the empiricalmodel part into a dynamic system parameter identification problem, and thus allows training the empiricalmodel partwith only measured data. An adaptive escaping particle swarm optimization (AEPSO) algorithm with escaping and adaptive inertia weight adjustment strategies is constructed to solve the resulting parameter identification problem, and thereby accomplish the training of the empirical model part. The uniform design method is used to determine the empirical model structure. The proposed simultaneous hybrid modeling approach has been used in a lab-scale nosiheptide batch fermentation process. The results show that it is effective and leads to a more consistent model with better generalization ability when compared to existing ones. The performance of AEPSO is also demonstrated.

Key words: Bioprocess, Dynamic modeling, Neural networks, Optimization