| 工业共沸精馏塔软测量建模方法的研究与应用 |
| |
| 引用本文： | 薄翠梅,张湜,李俊.工业共沸精馏塔软测量建模方法的研究与应用[J].南京工业大学学报(自然科学版),2006,28(3):44-48. |
| |
| 作者姓名： | 薄翠梅 张湜 李俊 |
| |
| 作者单位： | 南京工业大学,自动化学院,江苏,南京,210009 |
| |
| 基金项目： | 扬子石油化工股份有限公司资助项目 |
| |
| 摘 要： | 针对某一工业共沸精馏塔成分估计问题，利用基于支持向量机技术的软测量建模方法，建立了恰当的工业软测量模型。利用滑动时间窗技术实时更新建模数据集，并根据预估精度决策在线优化和模型更新，提高工业软测量模型的在线估计精度。研究结果表明，基于滑动时间窗的LS—SVM软测量建模方法，是一种有效的软测量建模方法。
|
| 关 键 词： | 工业共沸精馏塔 软测量技术 支持向量机 |
| 文章编号： | 1671-7643(2006)03-0044-05 |
| 收稿时间： | 2005-04-20 |
| 修稿时间： | 2005年4月20日 |
Study and application of soft sensor modeling methods aiming at an industrial azeotropic distillation |
| |
| BO Cui-mei,ZHANG Shi,LI Jun.Study and application of soft sensor modeling methods aiming at an industrial azeotropic distillation[J].Journal of Nanjing University of Technology,2006,28(3):44-48. |
| |
| Authors: | BO Cui-mei ZHANG Shi LI Jun |
| |
| Institution: | College of Automation, Nanjing University of Technology, Nanjing 210009, China |
| |
| Abstract: | The modeling method based on sliding time window was introduced, which dealed with these problems that the components of an azeotropic distillation were difficultly measured. An appropriate model was built by support vector machine technology based on least square. The data in sliding time window were used to optimize online or rebuild periodicity model to improve the estimate precision. The effective result indicates that the method is a useful method for the modeling. |
| |
| Keywords: | industry azeotropic distillation soft sensor modeling support vector machine proposed |
| 本文献已被 维普 万方数据 等数据库收录！ |
