| 基于改进在线支持向量回归的离子浓度预测模型 |
| |
| 引用本文： | 王凌云,桂卫华,刘梅花,阳春华. 基于改进在线支持向量回归的离子浓度预测模型[J]. 控制与决策, 2009, 24(4) |
| |
| 作者姓名： | 王凌云 桂卫华 刘梅花 阳春华 |
| |
| 作者单位： | 中南大学,信息科学与工程学院,长沙,410083 |
| |
| 摘 要： | 针对湿法炼锌净化过程中杂质离子浓度检测的大滞后特性和模型失效问题.提出了基于在线支持向量回归的离子浓度预测模型.该模型对每个新样本进行增量学习,并能删除数据集中的一个旧样本.进而提出用分块矩阵的方法解决更新算法计算复杂的问题.将该建模方法应用于离子浓度的预测,结果表明预测模型具有较好的泛化性能,模型更新时间明显缩短,有效地提高了适应工况的实时性.
|
| 关 键 词： | 离子浓度 在线支持向量回归 预测模型 更新矩阵 |
Prediction model of ion concentration based on improved online support vector regression |
| |
| WANG Ling-yun,GUI Wei-hua,LIU Mei-hua,YANG Chun-hua. Prediction model of ion concentration based on improved online support vector regression[J]. Control and Decision, 2009, 24(4) |
| |
| Authors: | WANG Ling-yun GUI Wei-hua LIU Mei-hua YANG Chun-hua |
| |
| Affiliation: | School of Information Science and Engineering;Central South University;Changsha 410083;China. |
| |
| Abstract: | A prediction model of ion concentration based on online support vector regression is proposed for the characteristic of large delay in the process of detecting the metal ion concentration and the problem of model failure in the purification process of zinc hydrometallurgy. An old sample data is removed from the data set while adding a new sample for incremental learning in this model. A blocking matrix method is proposed to solve the complicated computational problem in updating algorithm. Then this method ... |
| |
| Keywords: | Ion concentration Online support vector regression Prediction model Update matrix |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
