基于NGA-LSSVM的白水浓度软测量  

Soft sensing of white water concentration based on NGA-LSSVM

作　　者：曲涛[1] 潘海天[1] 夏陆岳[1] 蔡亦军[1] 孙小方[1] 

机构地区：[1]浙江工业大学化学工程与材料学院,浙江杭州310032

出　　处：《浙江工业大学学报》2008年第6期612-615,共4页Journal of Zhejiang University of Technology

基　　金：浙江省重大科技计划资助项目(2005C11032)

摘　　要：提出了一种基于小生境遗传算法—最小二乘支持向量机(NGA-LSSVM)的软测量建模方法.充分利用遗传算法强大的全局搜索能力,引入小生境遗传算法对最小二乘支持向量机各个参数(损失函数参数、惩罚因子、核函数及其参数)进行优化选择,将支持向量机参数由人工选取变为自动确定,为解决支持向量机参数自动优化问题提供了一条有效的途径.将所提出的建模方法应用于制浆造纸生产过程白水浓度软测量研究中,研究结果表明:与普通最小二乘支持向量机相比,该建模方法具有更佳的预测精度,能满足造纸生产过程的实际需要.A soft sensing modeling method based on Niche Genetic Algorithm-Least Square Support Vector Machine （NGA-LSSVM） is proposed. The niche genetic algorithm is mainly used to select and optimize the parameters of LS-SVM （Loss function parameter, Punishment factor, Core function and it＇s parameters） by making full use of the overall searching ability of genetic algorithm, which offer an effective way for SVM parameters automatic selection. The proposed modeling method is applied to the soft sensing of white water concentration . The study result shows that the proposed method has better estimate accuracy compared to the generic LS-SVM, in which the parameters are selected artificially; and it can satisfy the needs of industrial production quite well.

关 键 词：支持向量机 小生境遗传算法 白水浓度 软测量 

分 类 号：O621.25[理学—有机化学]