Soft-sensor modeling for lysine fermentation processes based on PSO-SVM inversion

doi:10.3969/j.issn.0438-1157.2012.09.051

CIESC Journal ›› 2012, Vol. 63 ›› Issue (9): 3000-3007.DOI: 10.3969/j.issn.0438-1157.2012.09.051

Soft-sensor modeling for lysine fermentation processes based on PSO-SVM inversion

WANG Bo¹, SUN Yukun², JI Xiaofu¹, HUANG Yonghong¹, HUANG Li¹

1. School of Electrical and Information Engineering, Jiangsu University, Zhenjiang 212013, Jiangsu, China;
2. Nanjing Institute of Technology, Nanjing 211167, Jiangsu, China

Received:2012-01-08 Revised:2012-03-30 Online:2012-09-05 Published:2012-09-05
Supported by:
supported by the High-tech Research and Development Program of China(2011AA09070301,2007AA04Z179)and the Natural Science Foundation of Jiangsu Province(BK2011465).

基于PSO-SVM逆的赖氨酸发酵过程软测量

王博¹, 孙玉坤², 嵇小辅¹, 黄永红¹, 黄丽¹

1. 江苏大学电气学院, 江苏镇江 212013;
2. 南京工程学院, 江苏南京 211167

通讯作者: 王博
作者简介:王博(1982-),男,博士,讲师。
基金资助:
国家高技术研究发展计划项目(2011AA09070301,2007AA04Z179);江苏省自然科学基金项目(BK2011465)。

Abstract

Abstract: Lysine fermentation process,which is characterized by nonlinear,large time-delay,multivariable dynamic coupling,is very difficult to realize crucial biochemical parameters on-line measurement.A soft-sensing modeling method was proposed based on PSO-SVM inversion theory.Firstly,the reversibility of the system was analyzed and the inverse extension model was built by introducing the feature information and abandoning the secondary information,and the inverse extension model was built offline with SVM which had good fitting capability and was adjusted online by PSO based on the error information between actual fermentation process input and model output.Finally,the inverse extension model was applied to the fed-batch L-lysine fermentation process and prediction with on-line soft-sensor of the directly immeasurable crucial biochemical parameters was realized.The simulations showed that the crucial biochemical parameters could be predicted.The results also showed that the proposed method was more accurate compared with the alternative modeling methods.

Key words: PSO algorithm, SVM, inversion extention model, L-lysine fermentation process

摘要： 针对赖氨酸发酵过程非线性、大滞后、多变量动态耦合,关键生化参数难以实时在线测量等问题,提出一种改进的粒子群-支持向量机(PSO-SVM)逆发酵过程软测量建模方法。首先分析逆系统的存在性,并结合赖氨酸发酵过程,引入发酵特征信息和舍弃次要信息构造逆扩展模型;然后利用支持向量机离线辨识初始逆扩展模型,并根据系统输入与模型输出的偏差信号,采用粒子群算法对初始逆扩展模型进行在线校正;最后将校正后的逆扩展模型串联在原发酵过程之后构成复合伪线性系统,实现不直接可测关键生化参数的在线预测。以L-赖氨酸流加发酵过程为例,验证了所提算法能够对发酵过程关键生物量参数进行较准确的在线预测,较普通的SVM逆建模方法具有更高的预测精度。

关键词: 粒子群算法, 支持向量机, 逆扩展模型, L-赖氨酸发酵

CLC Number:

TP301.6

WANG Bo, SUN Yukun, JI Xiaofu, HUANG Yonghong, HUANG Li. Soft-sensor modeling for lysine fermentation processes based on PSO-SVM inversion[J]. CIESC Journal, 2012, 63(9): 3000-3007.

王博, 孙玉坤, 嵇小辅, 黄永红, 黄丽. 基于PSO-SVM逆的赖氨酸发酵过程软测量[J]. 化工学报, 2012, 63(9): 3000-3007.

References 20

[1]	Montaque G A,Morris A J,Bush J R.Consideration in control scheme development for fermentation process control[J].Control Process System IEEE,2002,8(2):44-48
[2]	Chen Jian(陈坚),Liu Liming(刘立明),Du Guocheng(堵国成).Fermentation Process Optimization Theory and Techniques(发酵过程优化原理与技术)[M].Beijing:Chemical Industry Press,2009:12-129
[3]	Renard F,Wouwe V A.Robust adaptive control of yeast fed-batch cultures[J].Computers and Chemical Engineering,2008,32(12):1238-1248
[4]	Alford J S.Bioprocess control:advances and challenges[J].Compute.Chem.Eng.,2006,30(10):1464-1475
[5]	Du Feng(杜锋),Lei Ming(雷鸣),Liu Quan(刘全).Advanced control in fermentation process[J].Information and Control(信息与控制),2004,33(3):314-317
[6]	Dai X Z,Wang W C,Ding Y H.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
[7]	Li Y F,Yuan J Q.Prediction of key state variables using support vector machines in bioprocesses[J].Chemical Engineering and Technology,2006,29(3):313-319
[8]	Wang Xiaodong(汪晓东),Zhang Changjiang(张长江).Sensor dynamic modeling using least square support vector machines[J].Chinese Journal of Scientific Instrument(仪器仪表学报),2006,27(7):730-733
[9]	Lin Bihua(林碧华),Gu Xingsheng(顾幸生).Soft sensor modeling based on DE-LSSVM[J]. Journal of Chemical Industry and Engineering(China)(化工学报),2008,59(7):1681-1685
[10]	Deng Naiyang(邓乃扬),Tian Yingjie(田英杰).The New Method of Data Mining Based on Support Vector Machine(数据挖掘的新方法-支持向理机)[M].Beijing:Science Press,2004:42-163
[11]	Suykens J A K,Vandewalle J.Least Squares Vector Machines[M].Singapore:World Scientific,2002:3-132
[12]	Desai K,Badhe Y,Kulkarni B D.Soft-sensor development for fed-batch bioreactors using support vector regression[J].Bio-Chemical Engineering Journal,2006,27(3):225-239
[13]	Liu G H,Zhou D W.Model optimization of SVM for a fermentation soft sensor[J].Expert Systems with Applications,2010,37(4):2708-2713
[14]	Dai Xianzhong(戴先中).Neural Network Inverse Control Method of Multivariable Nonlinear Systems(多变量非线性系统的神经网络逆控制)[M].Beijing:Science Press,2005:94-148
[15]	Suykens J A K.Support vector machines:a nonlinear modeling and control perspective[J].European Journal of Control,2001,7(2/3):311-327
[16]	Suykens J A K,Vandewalle J.Recurrent least squares support vector machines[J].IEEE Transactions on Circuits and Systems-I,2000,47(7):1109-1114
[17]	Shawe T R,Cristianini N.Kernel methods for pattern analysis[M].England:Cambridge University Press,2004:200-240
[18]	Zhang Xuegong(张学工).Introduction to statistical learning theory and support vector machines[J].Acta Automatica Sinica(自动化学报),2000,26(1):32-42
[19]	Li Wei(栗伟),Su Hongye(苏宏业).Parameter estimation of catalytic cracking model using PSO algorithm[J].CIESC Journal(化工学报),2010,61(8):1927-1932
[20]	Luo Jianxu(罗健旭),Chang Qing(常青).Data pre-processing in soft sensor technology[J].Control Engineering of China(控制工程),2006:13(4):298-301

Soft-sensor modeling for lysine fermentation processes based on PSO-SVM inversion

基于PSO-SVM逆的赖氨酸发酵过程软测量

PDF (PC)

Knowledge

Cited

Abstract

Cite this article

share this article

References 20

Related Articles 15

Recommended Articles

Metrics

Comments

[1]	Xianyi YU, Jianghong WU, Yunhui GAO. Research on refrigerant leakage identification for heat pump system based on PCA-SVM models [J]. CIESC Journal, 2020, 71(7): 3151-3164.
[2]	Rui MU, Gaoyang LE, Huizhong YANG. Estimation method of dissolved gas quantity in COD determination based on O₃/UV [J]. CIESC Journal, 2019, 70(2): 730-735.
[3]	Jianyong ZHU, Xuqian ZHANG, Hui YANG, Rongxiu LU. Soft-sensing of Pr/Nd component content under different single illumination conditions [J]. CIESC Journal, 2019, 70(2): 780-788.
[4]	ZHU Xianglin, LING Jing, WANG Bo, HAO Jianhua, DING Yuhan. Soft-sensing modeling of marine protease fermentation process based on improved PSO-RBFNN [J]. CIESC Journal, 2018, 69(3): 1221-1227.
[5]	HUA Li, YU Haichen, SHAO Cheng, GONG Shixin. Monitoring and diagnosis of abnormal condition in ethylene production process based on SVM-BOXPLOT [J]. CIESC Journal, 2018, 69(3): 1053-1063.
[6]	LIU Jia, SHAO Cheng, ZHU Li. Modeling of cracking furnace yields with PSO-LS-SVM based on operating condition classification by transfer learning [J]. CIESC Journal, 2016, 67(5): 1982-1988.
[7]	FENG Kai, LU Jiangang, CHEN Jinshui. Identification and model predictive control of LPV models based on LS-SVM for MIMO system [J]. CIESC Journal, 2015, 66(1): 197-205.
[8]	WANG Tong, GAO Xianwen, LIU Wenfang. Adaptive soft sensor method and application in determination of dynamic fluid levels [J]. CIESC Journal, 2014, 65(12): 4898-4904.
[9]	YANG Xiaomei, LIU Wenqi, YANG Jun. LSSVM modeling for fermentation process based on dividing stages [J]. CIESC Journal, 2013, 64(9): 3262-3269.
[10]	XU Zijun, ZHAO Liang, HE Wangli, LI Zhihao, QIAN Feng. Base oil supply chain modeling method based on revenue sharing contract [J]. CIESC Journal, 2013, 64(12): 4454-4460.
[11]	XU Long, LU Jiangang, YANG Qinmin, CHEN Jinshui, SHI Yingzi. A new near-infrared spectroscopy informative interval selection method [J]. CIESC Journal, 2013, 64(12): 4410-4415.
[12]	LIAO Xingzhi, WAN Zhou, XIONG Xin. Fault diagnosis method of rolling bearing based on ensemble local mean decomposition and least squares support vector machine [J]. CIESC Journal, 2013, 64(12): 4667-4673.
[13]	MA Junjie, WU Min, LI Yong. Minimal coke consumption calculating method [J]. CIESC Journal, 2012, 63(9): 2688-2696.
[14]	LI Lijuan, PAN Lei, ZHANG Shi. Soft sensor modeling for mobility of jig bed based on AP-clustering algorithm [J]. CIESC Journal, 2012, 63(9): 2675-2680.
[15]	JIANG Huaqin, ZHAO Chengye, LIU Xinggao. Melt index prediction of propylene polymerization based on LSSVM using swarm intelligence optimization [J]. CIESC Journal, 2012, 63(9): 2794-2798.