Decoupled ARX and RBF Neural Network Modeling Using PCA and GA Optimization for Nonlinear Distributed Parameter Systems

doi:10.1109/TNNLS.2016.2631481

	Decoupled ARX and RBF Neural Network Modeling Using PCA and GA Optimization for Nonlinear Distributed Parameter Systems
	Zhang, Ridong 3; Tao, Jili 2; Lu, Renquan 3; Jin, Qibing 1
刊名	IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
	2018-02-01
卷号	29 期号:2 页码:457-469
关键词	Decoupled Autoregressive Exogenous (Arx) Model Distributed Parameter Systems (Dpss) Genetic Algorithm (Ga) Principal Component Analysis (Pca) Radial Basis Function (Rbf) Neural Network
ISSN号	2162-237X
DOI	10.1109/TNNLS.2016.2631481
文献子类	Article
英文摘要	Modeling of distributed parameter systems is difficult because of their nonlinearity and infinite-dimensional characteristics. Based on principal component analysis (PCA), a hybrid modeling strategy that consists of a decoupled linear autoregressive exogenous (ARX) model and a nonlinear radial basis function (RBF) neural network model are proposed. The spatial-temporal output is first divided into a few dominant spatial basis functions and finite-dimensional temporal series by PCA. Then, a decoupled ARX model is designed to model the linear dynamics of the dominant modes of the time series. The nonlinear residual part is subsequently parameterized by RBFs, where genetic algorithm is utilized to optimize their hidden layer structure and the parameters. Finally, the nonlinear spatial-temporal dynamic system is obtained after the time/space reconstruction. Simulation results of a catalytic rod and a heat conduction equation demonstrate the effectiveness of the proposed strategy compared to several other methods.
WOS关键词	PREDICTIVE CONTROL ; CONTROL DESIGN
WOS研究方向	Computer Science ; Engineering
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000422952400018
资助机构	Zhejiang Provincial Natural Science Foundation of China(LQ13F030008 ; National Natural Science Foundation of China(61673147) ; China National Funds for Distinguished Young Scientists(61425009) ; R1100716)
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/28280]
专题	中国科学院自动化研究所
通讯作者	Zhang, Ridong
作者单位	1.Beijing Univ Chem Technol, Inst Automat, Beijing 100029, Peoples R China 2.Zhejiang Univ, Ningbo Inst Technol, Ningbo 315100, Zhejiang, Peoples R China 3.Hangzhou Dianzi Univ, Zhejiang Informat & Control Inst, Key Lab IOT & Informat Fus Technol, Hangzhou 310018, Zhejiang, Peoples R China
推荐引用方式 GB/T 7714	Zhang, Ridong,Tao, Jili,Lu, Renquan,et al. Decoupled ARX and RBF Neural Network Modeling Using PCA and GA Optimization for Nonlinear Distributed Parameter Systems[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2018,29(2):457-469.
APA	Zhang, Ridong,Tao, Jili,Lu, Renquan,&Jin, Qibing.(2018).Decoupled ARX and RBF Neural Network Modeling Using PCA and GA Optimization for Nonlinear Distributed Parameter Systems.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,29(2),457-469.
MLA	Zhang, Ridong,et al."Decoupled ARX and RBF Neural Network Modeling Using PCA and GA Optimization for Nonlinear Distributed Parameter Systems".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 29.2(2018):457-469.