| 一种基于非线性回归和支持向量机的混合建模方法 |
| |
| 引用本文： | 邓卫卫,杨慧中. 一种基于非线性回归和支持向量机的混合建模方法[J]. 江南大学学报(自然科学版), 2011, 10(2) |
| |
| 作者姓名： | 邓卫卫 杨慧中 |
| |
| 作者单位： | 江南大学教育部轻工过程先进控制重点实验室,江苏无锡,214122 |
| |
| 基金项目： | 国家自然科学基金项目，江苏省高技术研究项目，江南大学创新团队发展计划资助项目 |
| |
| 摘 要： | 针对采用单一的建模方法存在的局限性,提出了一种基于非线性回归和支持向量机的混合建模方法.该方法将模型分为两部分,一部分由简单的非线性回归模型估计对象的总体变化趋势,另一部分由一个支持向量机组合模型来描述对象的局部变化特性,最后将该组合模型与非线性回归模型叠加,构成混合软测量模型.将该建模方法应用到双酚A反应的催化剂活性软测量建模中,仿真结果表明了该方法的有效性.
|
| 关 键 词： | 非线性回归 K-均值聚类 混合建模 支持向量机 催化剂活性 |
A Hybrid Modeling Method Based on Nonlinear Regression and Support Vector Machine |
| |
| DENG Wei-wei,YANG Hui-zhong. A Hybrid Modeling Method Based on Nonlinear Regression and Support Vector Machine[J]. Journal of Southern Yangtze University:Natural Science Edition, 2011, 10(2) |
| |
| Authors: | DENG Wei-wei YANG Hui-zhong |
| |
| Affiliation: | DENG Wei-wei,YANG Hui-zhong(Key Laboratory of Advanced Process Control for Light Industry,Ministry of Eduction,Jiangnan University,Wuxi 214122,China) |
| |
| Abstract: | Owing to the limitations of the single modeling method,a hybrid modeling method based on nonlinear regression and support vector machine(SVM) is presented.The model is divided into two parts by this method.The one part of the model is the simple nonlinear model to estimate the overall trend of the object,and the other part is a combined model of support vector machines to describe the local variation characteristics of the object.The combined model and the nonlinear regression model are incorporated to form... |
| |
| Keywords: | nonlinear regression K-means clustering hybrid modeling SVM catalytic activity |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
