DocumentCode :
2249283
Title :
Adaptive neural boundary control design for a class of nonlinear spatially distributed systems
Author :
Li, Yan-Chao ; Wu, Huai-Ning ; Wang, Jun-Wei
Author_Institution :
Sci. & Technol. on Aircraft Control Lab., Beihang Univ., Beijing, China
fYear :
2011
fDate :
17-19 Sept. 2011
Firstpage :
386
Lastpage :
391
Abstract :
In this paper, an adaptive neural network (NN) control design is proposed for a class of parabolic partial differential equation (PDE) systems with boundary control actuation and unknown nonlinearities. Initially, applying the Galerkin´s method, the PDE system is represented by a finite-dimensional slow subsystem and a coupled infinite-dimensional fast residual subsystem. Subsequently, a modal-feedback controller is designed according to dissipative theory and small gain theorem, such that the closed-loop PDE system is practically stable. In the proposed boundary control scheme, a radial basis function (RBF) NN is employed to approximate the unknown nonlinearities of the slow subsystem. The outcome of the control problem is formulated as a linear matrix inequality (LMI) problem. Finally, the proposed design method is applied to the control of the temperature profile of a catalytic rod to illustrate its effectiveness.
Keywords :
adaptive control; closed loop systems; feedback; linear matrix inequalities; neurocontrollers; nonlinear control systems; parabolic equations; partial differential equations; radial basis function networks; Galerkin method; adaptive neural boundary control design; adaptive neural network control design; boundary control actuation; boundary control scheme; closed-loop PDE system; coupled infinite-dimensional fast residual subsystem; dissipative theory; finite-dimensional slow subsystem; linear matrix inequality; modal-feedback controller; nonlinear spatially distributed systems; parabolic partial differential equation systems; radial basis function NN; small gain theorem; unknown nonlinearities; Adaptive systems; Artificial neural networks; Boundary conditions; Control design; Eigenvalues and eigenfunctions; Intelligent systems; Vectors; adaptive neural network (NN) control; boundary control; distributed parameter systems; linear matrix inequality (LMI); practical stability;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Cybernetics and Intelligent Systems (CIS), 2011 IEEE 5th International Conference on
Conference_Location :
Qingdao
Print_ISBN :
978-1-61284-199-1
Type :
conf
DOI :
10.1109/ICCIS.2011.6070360
Filename :
6070360
Link To Document :
بازگشت