首页 | 本学科首页   官方微博 | 高级检索  
     检索      

离子液体的无限稀释活度系数测量过程分析
引用本文:孟玲菊,玄兆坤,焦连升.离子液体的无限稀释活度系数测量过程分析[J].科学技术与工程,2013,13(24).
作者姓名:孟玲菊  玄兆坤  焦连升
作者单位:河北民族师范学院,河北民族师范学院化学系,,河北民族师范学院
摘    要: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,并进行的活度系数,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,该模型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。

关 键 词:关键词:离子液体  无限稀释活度系数  最小二乘支持向量机  
收稿时间:2013/4/26 0:00:00
修稿时间:2013/4/26 0:00:00

Ionic liquid of infinite dilution activity coefficient nonlinear modeling measurement process analysis
MENG Lingju,and.Ionic liquid of infinite dilution activity coefficient nonlinear modeling measurement process analysis[J].Science Technology and Engineering,2013,13(24).
Authors:MENG Lingju  and
Abstract:Abstract: In order to improve prediction accuracy of the infinite dilution activity coefficient in ion liquid, this paper proposes a prediction model for infinite dilution activity coefficient based on cuckoo search algorithm and least squares support vector machine(MCS-SVM). Firstly, the solute parameters of coefficients at infinite dilution are measured and divides into training set and test set; and then the training are input to the least squares support vector machine 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 simulation 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 nonlinear relationship between the infinite dilution activity coefficient and solute parameters, and has improved the prediction accuracy of infinite dilution activity coefficient, provides a new research approach for infinite dilution activity coefficient which has the nonlinear characteristics.
Keywords:
点击此处可从《科学技术与工程》浏览原始摘要信息
点击此处可从《科学技术与工程》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号