DocumentCode :
322922
Title :
The Chebyshev polynomials based unified model (CPBUM) neural network for the identification and control of nonlinear H problems
Author :
Jeng, Jin-Tsong ; Lee, Tsu Tian
Author_Institution :
Dept. of Electr. Eng., Nat. Taiwan Inst. of Technol., Taipei, Taiwan
Volume :
1
fYear :
1997
fDate :
9-14 Nov 1997
Firstpage :
285
Abstract :
In this paper, the authors propose a neural network model with a fast learning speed as well as a good function approximation capability, and a new objective function, which satisfies the H induced norm to solve the identification and control of nonlinear H problems. Based on this approximate transformable technique, the relationship between the single-layered neural network and multi-layered perceptrons neural network is derived. It is shown that the Chebyshev polynomials-based unified model neural network can be represented as a functional link network that is based on Chebyshev polynomials. They also derive a new learning algorithm such that the infinity norm of the transfer function from the input to the output is under a prescribed level. It turns out that the Chebyshev polynomials-based unified model neural network can be extended to the worst-case problem, in the identification and control of nonlinear H problems.
Keywords :
Chebyshev approximation; H control; control system analysis computing; identification; learning (artificial intelligence); neurocontrollers; nonlinear control systems; polynomials; transfer functions; Chebyshev polynomials-based unified model; computer simulation; control simulation; function approximation capability; functional link network; identification; infinity norm; learning algorithm; learning speed; multi-layered perceptrons; neural network; nonlinear H problems; objective function; single-layered neural net; transfer function; transformable technique; worst-case problem; Chebyshev approximation; Control systems; Function approximation; Multi-layer neural network; Multilayer perceptrons; Neural networks; Nonlinear control systems; Nonlinear systems; Polynomials; Recurrent neural networks;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Industrial Electronics, Control and Instrumentation, 1997. IECON 97. 23rd International Conference on
Print_ISBN :
0-7803-3932-0
Type :
conf
DOI :
10.1109/IECON.1997.671063
Filename :
671063
Link To Document :
بازگشت