SCI和EI收录∣中国化工学会会刊

›› 2016, Vol. 24 ›› Issue (10): 1399-1405.DOI: 10.1016/j.cjche.2016.06.012

• Process Systems Engineering and Process Safety • 上一篇    下一篇

Learning control of fermentation process with an improved DHP algorithm

Dazi Li, Ningjia Meng, Tianheng Song   

  1. Institute of Automation, Beijing University of Chemical Technology, Beijing 100029, China
  • 收稿日期:2015-10-23 修回日期:2016-03-03 出版日期:2016-10-28 发布日期:2016-11-19
  • 通讯作者: Dazi Li,E-mail address:lidz@mail.buct.edu.cn.
  • 基金资助:
    Supported by the National Natural Science Foundation of China (61573052).

Learning control of fermentation process with an improved DHP algorithm

Dazi Li, Ningjia Meng, Tianheng Song   

  1. Institute of Automation, Beijing University of Chemical Technology, Beijing 100029, China
  • Received:2015-10-23 Revised:2016-03-03 Online:2016-10-28 Published:2016-11-19
  • Supported by:
    Supported by the National Natural Science Foundation of China (61573052).

摘要: Control of the fed-batch ethanol fermentation processes to produce maximum product ethanol is one of the key issues in the bioreactor system. However, ethanol fermentation processes exhibit complex behavior and nonlinear dynamics with respect to the cell mass, substrate, feed-rate, etc. An improved dual heuristic programming algorithm based on the least squares temporal difference with gradient correction (LSTDC) algorithm (LSTDC-DHP) is proposed to solve the learning control problem of a fed-batch ethanol fermentation process. As a new algorithm of adaptive critic designs, LSTDC-DHP is used to realize online learning control of chemical dynamical plants, where LSTDC is commonly employed to approximate the value functions. Application of the LSTDC-DHP algorithmto ethanol fermentation process can realize efficient online learning control in continuous spaces. Simulation results demonstrate the effectiveness of LSTDC-DHP, and showthat LSTDC-DHP can obtain the near-optimal feed rate trajectory faster than other-based algorithms.

关键词: Dual heuristic programming, Batch process, Ethanol fermentation process, Learning control

Abstract: Control of the fed-batch ethanol fermentation processes to produce maximum product ethanol is one of the key issues in the bioreactor system. However, ethanol fermentation processes exhibit complex behavior and nonlinear dynamics with respect to the cell mass, substrate, feed-rate, etc. An improved dual heuristic programming algorithm based on the least squares temporal difference with gradient correction (LSTDC) algorithm (LSTDC-DHP) is proposed to solve the learning control problem of a fed-batch ethanol fermentation process. As a new algorithm of adaptive critic designs, LSTDC-DHP is used to realize online learning control of chemical dynamical plants, where LSTDC is commonly employed to approximate the value functions. Application of the LSTDC-DHP algorithmto ethanol fermentation process can realize efficient online learning control in continuous spaces. Simulation results demonstrate the effectiveness of LSTDC-DHP, and showthat LSTDC-DHP can obtain the near-optimal feed rate trajectory faster than other-based algorithms.

Key words: Dual heuristic programming, Batch process, Ethanol fermentation process, Learning control