MULTIVARIATE STATISTICAL PROCESS MONITORING USING MULTI-SCALE KERNEL PRINCIPAL COMPONENT ANALYSIS
MULTIVARIATE STATISTICAL PROCESS MONITORING USING MULTI-SCALE KERNEL PRINCIPAL COMPONENT ANALYSIS
复制标题
DOI：
10.3182/20060829-4-cn-2909.00017
复制
发表时间：
2006
期刊：
影响因子：
--
通讯作者：
Xiaogang Deng;Xuemin Tian
中科院分区：
文献类型：
--
作者：
Xiaogang Deng;Xuemin Tian
摘要将小波分析与核主元分析的非线性变换相结合，提出了一种基于多尺度核主元分析（MSKPCA）的非线性动态过程监测方法。小波分析用于分析过程数据的动态特性，核主成分分析是利用核函数来捕捉非线性主成分。该方法可以同时提取数据的互相关、自相关和非线性。在此基础上，提出了一种多尺度主元分析相似因子用于故障识别。对CSTR过程的仿真结果表明，该方法在故障检测和诊断方面优于传统的PCA方法。
Abstract A monitoring method based on multi-scale kernel principal component analysis (MSKPCA) is proposed for nonlinear dynamic processes, by combining wavelet analysis with nonlinear transformation using kernel principal component analysis. Wavelet analysis is used to analyze dynamic characteristic of process data, while the kernel principal component analysis is to capture nonlinear principal components by kernel functions. This method can simultaneously extract cross correlation, auto correlation, and nonlinearities from the data. Furthermore, a multi-scale principal component analysis similarity factor is proposed for fault identification. Simulation of CSTR process shows that the proposed method outperforms the traditional PCA method in fault detection and diagnosis.