基于SVM的微生物发酵过程软测量建模研究  

Soft sensor modeling using SVM in fermentation process

作　　者：刘国海[1] 周大为[1] 徐海霞[1] 梅从立[1] 

机构地区：[1]江苏大学电气信息工程学院,镇江212013

出　　处：《仪器仪表学报》2009年第6期1228-1232,共5页Chinese Journal of Scientific Instrument

基　　金：国家高新技术发展计划(863)(2007AA04Z179)资助项目

摘　　要：微生物发酵过程中支持向量机(SVM)软测量模型的预测精度主要取决于SVM参数和输入变量优化选择。提出了一种新的SVM参数选择与输入变量选取方法,将SVM参数的选择和输入变量的选取看作组合优化问题,构造了基于赤池信息准则(AIC)的组合优化目标函数。为提高优化效率,采用遗传模拟退火算法(GSAA)来搜索最优的目标函数值。通过与网格算法、遗传算法等方法对比仿真研究表明,所提SVM微生物发酵过程软测量建模方法在微生物发酵过程的软测量建模中具有优良的性能。The accuracy of SVM in fermentation process is mainly impacted by two factors： input variable selection and parameter setting in SVM training procedures. In this paper, a novel method is proposed to solve the problem. The selection problem of SVM parameters and input variables is considered as a compound optimazation problem. A new compound optimal objective function based on Akaike information criterion is constructed. In order to increase the efficiency of the optimazition, genetic simulation annealing algorithm （GSAA） is used to search the optimal value of the objective function. Compared with grid algorithm and genetic algorithm, the reasults show that the noval method based on the combination of GSAA and AIC is an effective approach for parameter selection and input variable selection and has good performance for soft sensor modeling in microorganism fermentation process.

关 键 词：软测量 支持向量机 遗传模拟退火算法 赤池信息准则 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]