基于QGA-LSSVM的醋酸乙烯聚合率软测量建模  

Research on Soft Sensor Modeling of Vinyl Acetate Polymerization Rate Based on Hybrid QGA-LSSVM

作　　者：夏梁志[1] 李华[1] 饶克克[1] 李瑞瑞[1] 

机构地区：[1]兰州交通大学自动化与电气工程学院,甘肃兰州730070

出　　处：《计算机测量与控制》2012年第4期907-909,913,共4页Computer Measurement &Control

摘　　要：针对最小二乘支持向量机(LS-SVM)在建立醋酸乙烯(VAC)聚合率软测量模型过程中最优模型参数的选择问题,提出了利用一种量子遗传算法来自动选取LS-SVM模型正则化参数和核函数参数的方法;把LS-SVM模型参数的选择问题转化为优化问题,利用全局搜索能力强的量子遗传算法优化LS-SVM建模过程的重要参数,建立了基于QGA-LSSVM方法的VAC聚合率软测量模型;仿真结果表明:与已有的神经网络和支持向量机软测量方法相比,该模型泛化能力强,精度高,更有利于醋酸乙烯聚合率测量工程实际运用。An quantum genetic algorithm （QGA） was proposed to ow：rcome the disadvantage that it＇ s difficult to get better parameter values of least squares support vector machine （LS--SVM） and the mixed kernel function in the processing of establish the soft sensing of vinyl acetate （VAC） polymerization rate. The method can convert the LS--SVM model parameters of selection into optimization problem, the best parameters of LS--SVM would be selected by QGA which has the ability of better search, and the QGA--LSSVM mode about soft sensing of VAC polymerization rate was constructed. The simulation result indicated that compared with the methods based on neural network and support vector machine, the QGA--LSSVM model has more effective generation performance and high precision, and it is more conducive to the practical application of engineering measurements.

关 键 词：软测量 醋酸乙烯聚合率 最小二乘支持向量机 量子遗传算法 

分 类 号：TP274[自动化与计算机技术—检测技术与自动化装置]