Title :
Identification of nonlinear discrete time systems using trigonometric polynomial neural networks
Author :
Yamamoto, Yoshihiro
Author_Institution :
Dept. of Inf. & Knowledge Eng., Tottori Univ., Tottori
Abstract :
A trigonometric polynomial neural network (TPNN) has been proposed by the authors. TPNN can be considered as a new scheme of neural network based on a trigonometric polynomial which is familiar in Fourier Analysis. The proposed network is linear with respect to its coefficients and the well known recursive least squares method of linear parameter estimation can be used. Identification of nonlinear discrete time system is examined in this paper using the TPNN. Some considerations for the use of TPNN are also discussed. These results are confirmed by many simulation studies.
Keywords :
discrete time systems; least squares approximations; neural nets; nonlinear control systems; parameter estimation; identification; linear parameter estimation; nonlinear discrete time systems; recursive least squares method; trigonometric polynomial neural networks; Automatic control; Discrete time systems; Fourier series; Least squares approximation; Least squares methods; Multi-layer neural network; Neural networks; Parameter estimation; Polynomials; Vectors; Identification; Least squares; Neural network; Nonlinear discrete time system; Trigonometric polynomial;
Conference_Titel :
Control, Automation and Systems, 2008. ICCAS 2008. International Conference on
Conference_Location :
Seoul
Print_ISBN :
978-89-950038-9-3
Electronic_ISBN :
978-89-93215-01-4
DOI :
10.1109/ICCAS.2008.4694672
