摘要
离子液体受到结构上不对称性、静电作用等多种作用影响,系数特征容易发生形变,传统的测量方法在干扰状态下,很难准确测量。提出一种新的无限稀释活度系数测量模型(MCS-SVM)。通过实验测量与无限稀释活度系数相关的溶质参数,并将它们分成为训练集和测试集;然后将训练集输入到一种最小二乘支持向量机分类模型,并测量活度系数,完成最优的无限稀释活度系数测量,消除测量误差。仿真结果表明,相对于传统测量方法可以准确描述无限稀释活度系数与溶质参数的非线性关系,提高了无限稀释活度系数的测量精度。
In order to improve prediction accuracy of the infinite dilution activity coefficient in ion liquid, a prediction model for infinite dilution activity coefficient based on cuckoo search algorithm and least squares support vector machine （MCS-SVM） is proposed. Firstly, the solute parameters of coefficients at infinite dilution are meas- ured and divides into training set and test set; and then the training are input to the least squares support vector ma- chine to train, and the cuckoo search algorithm is used to optimize the parameters of least squares support vector machine. Finally the optimal prediction model of the infinite dilution activity coefficient is established, and the sim- ulation experiments were carried out to test the performance of model. The simulation results show that, compared with the multiple linear regression model and BP neural network, MCS-LSSVM can accurately describe the nonlin- ear relationship between the infinite dilution activity coefficient and solute parameters, and has improved the predic- tion accuracy of infinite dilution activity coefficient, provides a new research approach for infinite dilution activity coefficient which has the nonlinear characteristics.
出处
《科学技术与工程》
北大核心
2013年第24期7262-7266,共5页
Science Technology and Engineering
关键词
离子液体
无限稀释活度系数
最小二乘支持向量机
ionic liquids
infinite dilution activity coefficients
east squares support vector machine
