Optimization of a batch reactor based on a process neural network

LIN ShuQian;WANG Jing;CAO LiuLin

Journal of Beijing University of Chemical Technology ›› 2010, Vol. 37 ›› Issue (2) : 126-131.

PDF(1131 KB)
Welcome to Journal of Beijing University of Chemical Technology, Today is July 12, 2025
Email Alert  RSS
PDF(1131 KB)
Journal of Beijing University of Chemical Technology ›› 2010, Vol. 37 ›› Issue (2) : 126-131.
机电工程与信息科学

Optimization of a batch reactor based on a process neural network

  • LIN ShuQian;WANG Jing;CAO LiuLin
Author information +
History +

Abstract

The optimal operation trajectory of a batch process is always determined by experienced workers, based on their rich experience. Obviously this method is time consuming and laborious. In order to overcome this problem, a simple and fast mathematical method is given based on a process neural network (PNN) model. A PNN is used to model batch processes in order to overcome the restrictions on instantaneous synchronization input for a traditional neural network. Based on the PNN, a quadratic form performance index function is presented which allows the optimal operating trajectory to be obtained. The proposed scheme is successfully applied to a simulated batch process.

Cite this article

Download Citations
LIN ShuQian;WANG Jing;CAO LiuLin. Optimization of a batch reactor based on a process neural network[J]. Journal of Beijing University of Chemical Technology, 2010, 37(2): 126-131

References

[1]陈治纲, 许超, 邵惠鹤. 间歇过程优化与先进控制综述[J]. 化工自动化及仪表, 2003, 30(3): 1-6.
Chen Z G, Xu C, Shao H H. Summary of batch process optimization and advanced control[J]. Control and Instruments in Chemical Industry, 2003, 30(3): 1-6. (in C
hinese)
[2]Tian Y, Zhang J, Morris J. Optimal control of a batch emulsion copolymerisation reactor based on recurrent neural network models[J]. Chemic
al Engineering and Processing, 2002, 41: 531-538.
[3]Zhang J. Batch-to-batch optimal control of a batch polymerisation process based on stacked neural network models[J]. Chemical Engineering Science, 2008, 63: 1273-1281.
[4]Xiong Z H, Zhang J. A batchtobatch iterative optimal control strategy based on recurrent neural network models[J]. Journal of Process Control,
2005, 15: 11-21.
[5]Xiong Z H, Zhang J. Modelling and optimal control of fedbatch processes using a novel control affine feedforward neural network[J]. Neurocomputing, 2004, 61: 317-337.
[6]何新贵, 许少华. 输入输出均为时变函数的过程神经网络及应用[J]. 软件学报, 2003, 14(4): 764-769.
He X G, Xu S H. Process neural network with timevaried input and output functi
ons and its applications[J]. Journal of Software, 2003, 14(4): 764-769. (in Chinese)
[7]何新贵, 梁久祯. 过程神经元网络的若干理论问题[J]. 中国工程科学, 2000, 2(12): 40-44.
He X G, Liang J Z. A number of theoretical issues of process neurl network[J].
China Engineering Science, 2000, 2(12): 40-44. (in Chinese)
[8]许少华, 蔡月芹, 谢树民. 基于傅立叶函数基变换的过程神经元网络学习算法[J]. 计算机工程与设计, 2006, 27(23): 4413-4415.
Xu S H, Cai Y Q, Xie S M. Learning algorithm of procedure neural networ based on
orthogonal base function[J]. 〖JP3〗Computer Engineering and Design, 2006, 27(23): 4413-4415. (in Chinese)
[9]苏金明. MATLAB6.1实用指南[M]. 北京: 电子工业出版社, 2002.
Su J M. MATLAB6.1 pratical guide[M]. Beijing: Electronic Industry Press, 2002. (in Chinese)
[10]吴重光. 过程系统仿真技术[M]. 北京: 中国石化出版社, 1997.
Wu C G. Process system simulation technology[M]. Beijing: China Petrochemical
Press, 1997. (in Chinese)
PDF(1131 KB)

3646

Accesses

0

Citation

Detail

Sections
Recommended

/