Title :
Identification of a class of hyperbolic distributed parameter systems via deterministic learning
Author :
Dong, Xunde ; Wang, Cong
Author_Institution :
Center for Control & Optimization, South China Univ. of Technol., Guangzhou, China
Abstract :
In this paper, we investigate a class of hyperbolic distributed parameter systems(DPS), the Sine-Gordon (SG) equation with damp and driven. The plant is a hyperbolic type partial differential equation(PDE) and has been broadly applied for physics and other relevant realms. Instead of identifying the parameters of DPS, the purpose of the paper is to identify the infinite-dimensional dynamics of DPS. By using the method of lines we translate the DPS described by PDE into a set of ODEs, then the dynamics of the DPS are obtained by using the deterministic learning theory and represented by constant radius basis function(RBF) neural network. Furthermore the knowledge also can be used for control or identification.
Keywords :
distributed parameter systems; hyperbolic equations; learning (artificial intelligence); mathematics computing; parameter estimation; partial differential equations; radial basis function networks; sine-Gordon equation; ODE; PDE; RBF neural networks; SG equation; Sine-Gordon equation; class identification; constant radial basis function neural networks; deterministic learning theory; hyperbolic DPS; hyperbolic distributed parameter systems; hyperbolic type partial differential equation; infinite-dimensional dynamics identification; parameter identification; Approximation methods; Equations; Mathematical model; Orbits; Radial basis function networks; Trajectory;
Conference_Titel :
Intelligent Control and Information Processing (ICICIP), 2012 Third International Conference on
Conference_Location :
Dalian
Print_ISBN :
978-1-4577-2144-1
DOI :
10.1109/ICICIP.2012.6391543
