| 基于改进差分进化和最小二乘支持向量机的铝酸钠溶液浓度软测量 |
| |
| 引用本文： | 钱晓山,阳春华,徐丽莎.基于改进差分进化和最小二乘支持向量机的铝酸钠溶液浓度软测量[J].化工学报,2013,0(5):1704-1709. |
| |
| 作者姓名： | 钱晓山 阳春华 徐丽莎 |
| |
| 作者单位： | 1. 中南大学信息科学与工程学院, 湖南 长沙 410083;
2. 宜春学院物理科学与工程技术学院, 江西 宜春 336000;
3. 中南林业科技大学涉外学院, 湖南 长沙 410004 |
| |
| 基金项目： | 国家高技术研究发展计划项目(2009AA04Z124, 2009AA04Z137);国家自然科学基金项目(60874069);国家杰出青年科学基金项目(61025015)。 |
| |
| 摘 要： | 针对氧化铝蒸发过程铝酸钠溶液浓度难以在线检测问题,提出了改进差分进化和最小二乘支持向量机的铝酸钠溶液浓度软测量建模方法。首先基于灰色关联分析和核主成分分析确定模型的输入变量,再用改进差分进化算法的最小二乘支持向量机构建软测量模型。并与DE-LSSVM软测量模型进行比较;最后应用蒸发过程生产数据进行验证,结果表明,新模型具有更好的学习能力和泛化性能且预测精度更高,可为蒸发过程操作优化提供必要的指导。
|
| 关 键 词： | 改进差分进化 最小二乘支持向量机 铝酸钠溶液浓度 软测量 |
| 收稿时间： | 2012-08-16 |
| 修稿时间： | 2013-01-02 |
Soft sensor of sodium aluminate solution concentration based on improved differential evolution algorithm and LSSVM |
| |
| QIAN Xiaoshan,YANG Chunhua,XU Lisha.Soft sensor of sodium aluminate solution concentration based on improved differential evolution algorithm and LSSVM[J].Journal of Chemical Industry and Engineering(China),2013,0(5):1704-1709. |
| |
| Authors: | QIAN Xiaoshan YANG Chunhua XU Lisha |
| |
| Affiliation: | 1. School of Information Science & Engineering, Central South University, Changsha 410083, Hunan, China;
2. School of Physical Science and Technology, Yichun University, Yichun 336000, Jiangxi, China;
3. She Wai School, Central South University of Forestry and Technology, Changsha 410004, Hunan, China |
| |
| Abstract: | Aiming at online testing of concentration of sodium aluminate solution in evaporation process of alumina production, a modeling method for concentration of sodium aluminate solution based on improved differential evolution algorithm and least squares support vector machine was proposed.The input variables of the soft sensor model were determined by analyzing process parameters based on grey relational analysis and kernel principal components analysis,and then the LSSVM model was established based on improved differential evolution algorithm and compared with DE-LSSVM soft sensor model.Finally, the experimental results of industrial production data of evaporation process showed that the new model had better learning ability and generalization performance and higher prediction accuracy, and could provide necessary guidance for the evaporation process operation optimization. |
| |
| Keywords: | improved differential evolution least squares support vector machine concentration of sodium aluminate solution soft sensor |
| 本文献已被 CNKI 等数据库收录！ |
| 点击此处可从《化工学报》浏览原始摘要信息 |
|
点击此处可从《化工学报》下载全文 |
|
