| 基于特征向量提取的核主元分析法 |
| |
| 引用本文： | 吴洪艳,黄道平. 基于特征向量提取的核主元分析法[J]. 计算机科学, 2009, 36(7): 185-187 |
| |
| 作者姓名： | 吴洪艳 黄道平 |
| |
| 作者单位： | 华南理工大学自动化科学与工程学院,广州,510640;湛江师范学院信息科学与技术学院,湛江,524048;华南理工大学自动化科学与工程学院,广州,510640 |
| |
| 基金项目： | 广东省科技计划资助项目 |
| |
| 摘 要： | 核主成分分析(KPCA)是非线性化工过程故障检测与诊断时常用的多变量统计控制方法之一.从两个方面改进了KPCA的故障检测性能.为了提高KPCA方法故障检测的准确率,提出了基于小波的KPCA故障检测方法.当样本数大时,采用基于几何考虑的特征向量提取(FVS)算法,降低了KPCA计算的复杂性,缩短了计算时间.Tennessee Eastman process仿真给出了所提出的方法的有效性.
|
| 关 键 词： | 故障诊断 核主成分分析 特征向量提取 小波变换 |
| 收稿时间： | 2008-08-25 |
| 修稿时间： | 2008-10-26 |
Kernel Principal Component Analysis Based on Feature Vector Selection |
| |
| WU Hong-yan,HUANG Dao-ping. Kernel Principal Component Analysis Based on Feature Vector Selection[J]. Computer Science, 2009, 36(7): 185-187 |
| |
| Authors: | WU Hong-yan HUANG Dao-ping |
| |
| Affiliation: | College of Automation Science and Technology;South China University of Technology;Guangzhou 510640;China;College of Information Science and Technology;Zhanjiang Normal University;Zhanjiang 524048;China |
| |
| Abstract: | Kernel principal component analysis(KPCA) is one of multivariate statistical control methods for solving nonlinear chemical process fault diagnosis.In this paper,it improves KPCA from two aspects.First,in order to improve the accuracy of KPCA for fault detection,a new method combined with wavelet was developed.Second,feature vector selection(FVS) scheme was adopted to reduce the computational complexity of KPCA whereas preserve the geometrical structure of the data.Tennessee Eastman process(TEP) simulations... |
| |
| Keywords: | Fault diagnosis Kernel principal component analysis Feature extraction Wavelet transform |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《计算机科学》浏览原始摘要信息 |
|
点击此处可从《计算机科学》下载全文 |
|
