[1]于 霜,刘国海,梅从立,等.生物发酵过程中VIP优化神经网络逆系统 的软测量方法[J].南京理工大学学报(自然科学版),2015,39(04):447.
 Yu Shuang,Liu Guohai,Mei Congli,et al.VIP optimal neural network inverse system soft sensing method in bio-fermentation process[J].Journal of Nanjing University of Science and Technology,2015,39(04):447.
点击复制

生物发酵过程中VIP优化神经网络逆系统 的软测量方法
分享到:

《南京理工大学学报》(自然科学版)[ISSN:1005-9830/CN:32-1397/N]

卷:
39卷
期数:
2015年04期
页码:
447
栏目:
出版日期:
2015-08-31

文章信息/Info

Title:
VIP optimal neural network inverse system soft sensing method in bio-fermentation process
作者:
于 霜1刘国海2梅从立2程锦翔2
1.苏州工业职业技术学院 机电工程系,江苏 苏州 215104; 2.江苏大学 电气信息工程学院,江苏 镇江 212013
Author(s):
Yu Shuang1Liu Guohai2Mei Congli2Cheng Jinxiang2
1.Department of Mechanical and Electrical Engineering,Suzhou Institute of Industrial Technology, Suzhou 215104,China; 2.School of Electrical and Information Engineering,Jiangsu University,Zhenjiang 212013,China
关键词:
变量投影重要性 神经网络逆系统 软测量 发酵过程 内含传感器 变量筛选 在线检测
Keywords:
variable importance in the project neural network inverse system soft sensing fermentation process inherent sensing variables selection online measuring
分类号:
TP273
摘要:
针对生物发酵过程中生化变量难以在线检测的问题,提出一种基于变量投影重要性(Variable importance in the project,VIP)方法优化的神经网络逆系统软测量模型。根据逆系统理论建立发酵过程生化变量的软测量模型,由于发酵系统的复杂性,逆系统软测量模型具有不惟一性,且难以得到精确的表达式。文中提出采用VIP方法对逆系统软测量模型的辅助变量进行优选,以对主变量贡献率较高的变量作为软测量模型的辅助变量,离线采集发酵过程各变量值,训练神经网络近似逆系统软测量模型,得到优化的神经网络逆系统软测量模型,实现发酵过程中菌体浓度和基质浓度的在线估计。利用Pensim平台采集数据,对所提方法做了仿真实验,结果表明:经过优化辅助变量的神经网络逆系统软测量方法具有更高的估计精度和泛化能力。
Abstract:
To solve the online measuring of biochemical variables in the fermentation process,a neural network inverse soft sensing method which is optimized using the variable importance in the project(VIP)is proposed.According to the inverse system theory,a soft sensing model of biochemical variables is constructed.Due to the complexity of the fermentation process,the soft sensing model is not unique and not exact.This paper proposes that secondary variables should be optimized using the VIP method.The variables which have greater contribution to key variables are selected as the secondary variables of the soft sensing model.This paper collectes the fermentation process data offline and trains neural network approximating complex soft sensing model.The optimal neural network inverse system soft sensing model is obtained.It can estimate the mycelium concentration and substrate concentration online.Numerical simulations based on the Pensim data platform show that the optimal soft sensing model has higher estimation accuracy and stronger generation ability.

参考文献/References:

[1] 潘丰,李海波,顾蕊.基于递归补偿模糊神经网络的发酵过程建模[J].南京理工大学学报,2005,10(29):108-111.
Pan Feng,Li Haibo,Gu Rui.Fermentation process modeling based on recurrent compensatory neuro-fuzzy network[J].Journal of Nanjing University of Science and Technology,2005,10(29),108-111.
[2]Tan Baohua,Quan Shuhai,Zhang Liyan,et al.Study on membrane water content soft sensing method based on internal resistance in PEMFC[J].International Journal of Digital Content Technology and Its Applications,2012,6(11):205-212.
[3]Sheng Biqi,Zhang Rongbiao,Pan Tianhong,et al.Dynamic canonical correlation analysis for onlinequality estimation in an industrial sputtering process[J].International Journal of Digital Content Technology and Its Applications,2012,6(7):93-101.
[4]Zhang Yonghong,Xia Zhining,Qin Litang,et al.Prediction of blood-brain partitioning:A model based on molecular electronegativity distance vector descriptors[J].Journal of Molecular Graphics and Modelling,2010,29(2):214-220.
[5]Wang Shengwei,Wang Jinbo.Law-based sensor fault diagnosis and validation for building air-conditioning systems[J].HVAC and R Research,1999,5(4):353-380.
[6]Yan Xuefeng.Modified nonlinear generalized ridge regression and its application to develop naphtha cut point soft sensor[J].Computers and Chemical Engineering,2008,32(3):608-621.
[7]Cheruy A.Software sensors in bioprocess engineering[J].Journal of Biotechnology,1997,52(3):193-199.
[8]孙玉坤,张瑶,黄永红,等.基于免疫遗传算法的动态递归模糊神经网络在发酵过程中的应用[J].信息与控制,2011,40(1):110-114.
Sun Yukun,Zhang Yao,Huang Yonghong,et al.Application of dynamic recursive fuzzy neural network based on immune genetic algorithm to fermentation process[J].Information and Control,2011,40(1):110-114.
[9]田学民,王强,邓晓刚.一种引入动量项的小波神经网络软测量建模方法[J].化工学报,2011,62(8):2238-2242.
Tian Xuemin,Wang Qiang,Deng Xiaogang.Soft sensing based on wavelet neural networks with momentum[J].Journal of Chemical Industry and Engineering,2011,62(8):2238-2242.
[10]Dai Xianzhong,Wang Wancheng,Ding Yuhan,et al.“Assumed Inherent Sensor” inversion based ANN dynamic soft-sensing method and its application in erythromycin fermentation process[J].Computers and Chemical Engineering,2006,30(8):1203-1225.
[11]Birol G,Undey C,Çinar A.A modular simulation package for fed-batch fermentation:Penicillin production[J].Computers and Chemical Engineering,2002,26(11):1553-1565.
[12]Chen Weiliang,Zhang Kaifeng,Lu Chao,et al.Soft-sensing of crucial biochemical variables in penicillin fermentation[A].Proceedings of the 29th Chinese Control Conference[C].Washington D C,USA:IEEE Computer Society,2010:1391-1397.

备注/Memo

备注/Memo:
收稿日期:2014-08-26 修回日期:2014-12-12
基金项目:国家中小型企业创新基金(6612C26213202207); 苏州市科技基础设施建设计划项目(SZP201303)
作者简介:于霜(1981-),女,博士,讲师,主要研究方向:复杂系统的智能控制,E-mail:myushuang@hotmail.com。
引文格式:于霜,刘国海,梅从立,等.生物发酵过程中VIP优化神经网络逆系统的软测量方法[J].南京理工大学学报,2015,39(4):447-451.
投稿网址:http://zrxuebao.njust.edu.cn
更新日期/Last Update: 2015-08-31