Title :
Application of artificial neural networks to parameter estimation of dynamical systems
Author :
Materka, Andrzej
Author_Institution :
Dept. of Electr. & Comput. Syst. Eng., Monash Univ., Clayton, Vic., Australia
Abstract :
Neural network (NN) based estimators of dynamical system parameters are introduced and compared to the least-squares-error estimators. Equations are derived to discuss the NN estimator existence and to express its covariance matrix. The results are illustrated using a numerical example of a 3-parameter system represented by multiexponential model
Keywords :
learning (artificial intelligence); least squares approximations; matrix algebra; multivariable systems; neural nets; parameter estimation; 3-parameter system; artificial neural networks; covariance matrix; dynamical systems; least-squares-error estimators; multiexponential model; parameter estimation; Application software; Artificial neural networks; Circuit testing; Electronic circuits; Electronic equipment testing; Fault diagnosis; Integral equations; Neural networks; Parameter estimation; Parametric statistics;
Conference_Titel :
Instrumentation and Measurement Technology Conference, 1994. IMTC/94. Conference Proceedings. 10th Anniversary. Advanced Technologies in I & M., 1994 IEEE
Conference_Location :
Hamamatsu
Print_ISBN :
0-7803-1880-3
DOI :
10.1109/IMTC.1994.352109
