Extended and unscented kalman filters for artificial neural network modelling of a nonlinear dynamical system

Abstract

Recently, artificial neural networks, especially feedforward neural networks, have been widely used for the identification and control of nonlinear dynamical systems. However, the determination of a suitable set of structural and learning parameter value of the feed-forward neural networks still remains a difficult task. This paper is concerned with the use of extended Kalman filter and unscented Kalman filter based feedforward neural networks training algorithms. The comparisons of the performances of both algorithms are discussed and illustrated using a simulated example. The simulation results show that in terms of mean squared errors, unscented Kalman filter algorithm is superior to the extended Kalman filter and back-propagation algorithms since there are improvements between 2.45–21.48% (for training) and 8.35–29.15% (for testing). This indicates that unscented Kalman filter based feedforward neural networks learning could be a good alternative in artificial neural network models based applications for nonlinear dynamical systems.