利用中国160站逐月降水资料,运用一种基于前馈型人工神经网络的非线性主成分分析方法(nonlinear principal component analysis,NLPCA)研究了中国近50 a四季降水异常分布的非线性特征。结果表明,NLPCA有能力表示出更一般的低维结构特征...利用中国160站逐月降水资料,运用一种基于前馈型人工神经网络的非线性主成分分析方法(nonlinear principal component analysis,NLPCA)研究了中国近50 a四季降水异常分布的非线性特征。结果表明,NLPCA有能力表示出更一般的低维结构特征。四季降水的异常分布都具有一定的非线性相关空间结构,其中春夏季节非线性较强,秋冬季节稍弱;四季降水距平的一维NLPCA近似在非线性主成分取极端相反位相时,对应的空间分布型表现出明显的不对称性。四季降水异常的一维NLPCA近似都比传统一维PCA的近似逼真,且存在季节变化。展开更多
文中以天津永和大桥为例,主要研究了温度和湿度效应对于模态频率影响,并选择非线性主成分分析(Nonlinear Principal Component Analysis,NLPCA)作为模态频率预处理的方法,以将温湿度对模态参数的影响和其他因素的影响区别开来,经过NLPC...文中以天津永和大桥为例,主要研究了温度和湿度效应对于模态频率影响,并选择非线性主成分分析(Nonlinear Principal Component Analysis,NLPCA)作为模态频率预处理的方法,以将温湿度对模态参数的影响和其他因素的影响区别开来,经过NLPCA处理的数据隐含了模态频率与温湿度的关系,而后应用神经网络(Artificial Neural Network,ANN)来构造温湿度与环境因素之间的关系模型。展开更多
利用NCEP/NCAR再分析500 hPa高度场资料,采用EOF和非线性主成分分析(NLPCA,Nonlinear Principal Component Analysis),研究了北半球冬季大气环流遥相关型的非线性特征,并将两种分析的结果与实际观测相比较,结果表明:NLPCA在提取资料场...利用NCEP/NCAR再分析500 hPa高度场资料,采用EOF和非线性主成分分析(NLPCA,Nonlinear Principal Component Analysis),研究了北半球冬季大气环流遥相关型的非线性特征,并将两种分析的结果与实际观测相比较,结果表明:NLPCA在提取资料场序列的低维非线性相关结构方面比传统EOF有明显的优越性。北半球冬季大气环流的遥相关型有明显的非线性结构特征,特别是EU型和PNA型,当非线性主成分NLPC取正负极值时,EU和PNA型并不是呈现完全的反位相结构。NLPC取负极值时,EU型的活动中心位置比NLPC取正极值时位置偏西,特别是欧亚大陆中部的距平中心,负中心比正中心偏西,强度更强;PNA型的4个距平中心在NLPC取正极值时比负极值时更集中,副热带太平洋的正中心、北太平洋的负中心比NLPC取负极值时的反符号中心偏东,强度更强。展开更多
State reconstruction approach is very useful for sensor fault isolation, reconstruction of faulty measurement and the determination of the number of components retained in the principal components analysis (PCA) mod...State reconstruction approach is very useful for sensor fault isolation, reconstruction of faulty measurement and the determination of the number of components retained in the principal components analysis (PCA) model. An extension of this approach based on a Nonlinear PCA (NLPCA) model is described in this paper. The NLPCA model is obtained using five layer neural network. A simulation example is given to show the performances of the proposed approach.展开更多
运用一种基于神经网络的非线性主成分分析法(nonlinear principal component analysis,NLP-CA)对中国1951—2003年53 a四季气温距平场(surface air temperature anomaly,SATA)进行分析,NLPCA第一模态结果显示中国四季气温异常具有一定...运用一种基于神经网络的非线性主成分分析法(nonlinear principal component analysis,NLP-CA)对中国1951—2003年53 a四季气温距平场(surface air temperature anomaly,SATA)进行分析,NLPCA第一模态结果显示中国四季气温异常具有一定的非线性特征,并且具有显著的季节性差异,即春、夏两季的非线性较强,秋、冬两季较弱。一维NLPCA对原始气温距平场的近似比一维PCA(principal component analysis)更好地反映了气温场的实际分布情况。展开更多
Traditional PCA is a linear method, but most engineering problems are nonlinear. Using the linear PCA in nonlinear problems may bring distorted and misleading results. Therefore, an approach of nonlinear principal com...Traditional PCA is a linear method, but most engineering problems are nonlinear. Using the linear PCA in nonlinear problems may bring distorted and misleading results. Therefore, an approach of nonlinear principal component analysis (NLPCA) using radial basis function (RBF) neural network is developed in this paper. The orthogonal least squares (OLS) algorithm is used to train the RBF neural network. This method improves the training speed and prevents it from being trapped in local optimization. Results of two experiments show that this NLPCA method can effectively capture nonlinear correlation of nonlinear complex data, and improve the precision of the classification and the prediction.展开更多
文摘利用中国160站逐月降水资料,运用一种基于前馈型人工神经网络的非线性主成分分析方法(nonlinear principal component analysis,NLPCA)研究了中国近50 a四季降水异常分布的非线性特征。结果表明,NLPCA有能力表示出更一般的低维结构特征。四季降水的异常分布都具有一定的非线性相关空间结构,其中春夏季节非线性较强,秋冬季节稍弱;四季降水距平的一维NLPCA近似在非线性主成分取极端相反位相时,对应的空间分布型表现出明显的不对称性。四季降水异常的一维NLPCA近似都比传统一维PCA的近似逼真,且存在季节变化。
文摘利用NCEP/NCAR再分析500 hPa高度场资料,采用EOF和非线性主成分分析(NLPCA,Nonlinear Principal Component Analysis),研究了北半球冬季大气环流遥相关型的非线性特征,并将两种分析的结果与实际观测相比较,结果表明:NLPCA在提取资料场序列的低维非线性相关结构方面比传统EOF有明显的优越性。北半球冬季大气环流的遥相关型有明显的非线性结构特征,特别是EU型和PNA型,当非线性主成分NLPC取正负极值时,EU和PNA型并不是呈现完全的反位相结构。NLPC取负极值时,EU型的活动中心位置比NLPC取正极值时位置偏西,特别是欧亚大陆中部的距平中心,负中心比正中心偏西,强度更强;PNA型的4个距平中心在NLPC取正极值时比负极值时更集中,副热带太平洋的正中心、北太平洋的负中心比NLPC取负极值时的反符号中心偏东,强度更强。
文摘State reconstruction approach is very useful for sensor fault isolation, reconstruction of faulty measurement and the determination of the number of components retained in the principal components analysis (PCA) model. An extension of this approach based on a Nonlinear PCA (NLPCA) model is described in this paper. The NLPCA model is obtained using five layer neural network. A simulation example is given to show the performances of the proposed approach.
文摘运用一种基于神经网络的非线性主成分分析法(nonlinear principal component analysis,NLP-CA)对中国1951—2003年53 a四季气温距平场(surface air temperature anomaly,SATA)进行分析,NLPCA第一模态结果显示中国四季气温异常具有一定的非线性特征,并且具有显著的季节性差异,即春、夏两季的非线性较强,秋、冬两季较弱。一维NLPCA对原始气温距平场的近似比一维PCA(principal component analysis)更好地反映了气温场的实际分布情况。
文摘Traditional PCA is a linear method, but most engineering problems are nonlinear. Using the linear PCA in nonlinear problems may bring distorted and misleading results. Therefore, an approach of nonlinear principal component analysis (NLPCA) using radial basis function (RBF) neural network is developed in this paper. The orthogonal least squares (OLS) algorithm is used to train the RBF neural network. This method improves the training speed and prevents it from being trapped in local optimization. Results of two experiments show that this NLPCA method can effectively capture nonlinear correlation of nonlinear complex data, and improve the precision of the classification and the prediction.