| 基于KPCA和最小二乘支持向量机的软测量建模 |
| |
| 引用本文： | 周林成,杨慧中. 基于KPCA和最小二乘支持向量机的软测量建模[J]. 计算机仿真, 2008, 25(10) |
| |
| 作者姓名： | 周林成 杨慧中 |
| |
| 作者单位： | 江南大学通信与控制工程学院,江苏,无锡,214122;江南大学通信与控制工程学院,江苏,无锡,214122 |
| |
| 基金项目： | 国家自然科学基金，江苏省高科技项目 |
| |
| 摘 要： | 为了解决化工领域数据建模小样本、不适定性、非线性等问题,提出了一种基于核主元分析(KPCA)和最小二乘支持向量机的软测量建模方法,用核主元分析对输入变量进行数据压缩,消除变量之间的相关性,运用PSO算法对核参数进行了寻优,通过交叉验证的方法对支持向量机进行参数选择.将其用于双酚A(BPA)软测量建模的研究结果表明:方法具有学习速度快、泛化能力强等优点,为BPA软测量建模的在线实施提供了方便.
|
| 关 键 词： | 最小二乘支持向量机 核主元分析 软测量 泛化能力 |
Soft Sensor Modeling Based on KPCA and Support Vector Machines |
| |
| ZHOU Lin-cheng,YANG Hui-zhong. Soft Sensor Modeling Based on KPCA and Support Vector Machines[J]. Computer Simulation, 2008, 25(10) |
| |
| Authors: | ZHOU Lin-cheng YANG Hui-zhong |
| |
| Affiliation: | ZHOU Lin-cheng,YANG Hui-zhong(School of Communication , Control Engineering,Jiangnan University,Wuxi Jiangsu 214122,China) |
| |
| Abstract: | In order to solve the problem of the small and ill-posed sample and nonlinearity in chemical industry processes,a soft measure method based on Kernel Principal Component Analysis (KPCA) and least square support vector machine is presented.The Kernel Principal Component Analysis method could not only solve the linear correlation of the input but also compress the data. Kernel parameters of KPCA are optimized by particle swarm optimization. Cross validation method is used to select parameters of least square ... |
| |
| Keywords: | Least square support vector machine Kernel principal component analysis Soft measure Generalization capability |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
