目的研究复杂工业系统动态、非线性特点,提出分步动态核主元分析(Kernel Principal Component Analysis,KPCA)的故障诊断方法.方法该方法首先构造增广矩阵,然后将增广矩阵分成一系列子矩阵,将各子矩阵的构建一个新的数据增广矩阵,并对...目的研究复杂工业系统动态、非线性特点,提出分步动态核主元分析(Kernel Principal Component Analysis,KPCA)的故障诊断方法.方法该方法首先构造增广矩阵,然后将增广矩阵分成一系列子矩阵,将各子矩阵的构建一个新的数据增广矩阵,并对每个子矩阵使用KPCA提取变量数据的非线性空间相关特征,最后通过监测统计量监测出系统故障,用贡献度的方法识别发生故障变量.结果该方法改进了传统的动态方法,引入分步动态的定义,并且能充分考虑工业过程中的非线性和动态性,更精确的描述工业过程特性,更精确的监测复杂工业系统的故障,并准确的识别出故障变量.结论对热连轧过程中活套故障诊断的仿真结果表明:基于分步动态KPCA的故障诊断方法能准确有效地诊断出故障,并识别出产生故障的原因.展开更多
The purpose of this paper is to analyze the dynamic behavior of fractional-order four-order hyperchaotic Lii system, and use the Open-Plus-Closed-Looping （OPCL） coupling method to construct the system＇s correspondi...The purpose of this paper is to analyze the dynamic behavior of fractional-order four-order hyperchaotic Lii system, and use the Open-Plus-Closed-Looping （OPCL） coupling method to construct the system＇s corresponding response system, and then implement function projective synchronization （FPS） of fractional-order drive-response system with system parameters perturbation or not. Finally, the numerical simulations verify the effectiveness and robustness of this scheme.展开更多
文摘目的研究复杂工业系统动态、非线性特点,提出分步动态核主元分析(Kernel Principal Component Analysis,KPCA)的故障诊断方法.方法该方法首先构造增广矩阵,然后将增广矩阵分成一系列子矩阵,将各子矩阵的构建一个新的数据增广矩阵,并对每个子矩阵使用KPCA提取变量数据的非线性空间相关特征,最后通过监测统计量监测出系统故障,用贡献度的方法识别发生故障变量.结果该方法改进了传统的动态方法,引入分步动态的定义,并且能充分考虑工业过程中的非线性和动态性,更精确的描述工业过程特性,更精确的监测复杂工业系统的故障,并准确的识别出故障变量.结论对热连轧过程中活套故障诊断的仿真结果表明:基于分步动态KPCA的故障诊断方法能准确有效地诊断出故障,并识别出产生故障的原因.
基金Supported by National Natural Science Foundation of China under Grant Nos.60573172,60973152Doctoral Program Foundation of Institution of Higher Education of China under Grant No.20070141014the Natural Science Foundation of Liaoning Province of China under Grant No.20082165
文摘The purpose of this paper is to analyze the dynamic behavior of fractional-order four-order hyperchaotic Lii system, and use the Open-Plus-Closed-Looping （OPCL） coupling method to construct the system＇s corresponding response system, and then implement function projective synchronization （FPS） of fractional-order drive-response system with system parameters perturbation or not. Finally, the numerical simulations verify the effectiveness and robustness of this scheme.
