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.
Similar content being viewed by others
References
Quantrille, T.E. and Liu, Y.A., Artificial Intelligence in Chemical Engineering, Orlando: Academic, 1992.
Hussain, M.A., Review of the Applications of Neural Networks in Chemical Process Control-Simulation and Online Implementation, Artif. Intell. Eng., 1999, vol. 13, p. 55.
Willis, M.J., Montague, G.A., Di Massimo, C., et al., Artificial Neural Networks in Process Estimation and Control, Automatica, 1992, vol. 28, no. 6, p. 1181.
Trebaticky, P., Recurrent Neural Network Training with the Extended Kalman Filter, Proc. Student Research Conf. in Informatics and Information Technologies, Bratislava, 2005, p. 57.
Haykin, S., Kalman Filtering and Neural Networks, New York: Wiley, 2001.
Wan, E.A., van der Merwe, R., and Nelson, A.T., Dual Estimation and the Unscented Transformation, Advances in Neural Information Processing Systems, Solla S.A., Leen T.K., and Muller K.R., Eds., Cambridge: MIT, 2000, vol. 12, p. 666.
Wan, E.A. and van der Merwe, R., The Unscented Kalman Filter for Nonlinear Estimation, Proc. IEEE Symp. 2000 on Adaptive Systems for Signal Processing, Communication and Control, Lake Louise, Alberta, Canada, 2000, p. 153.
Author information
Authors and Affiliations
Corresponding author
Additional information
The article is published in the original.
Rights and permissions
About this article
Cite this article
Saptoro, A. Extended and unscented kalman filters for artificial neural network modelling of a nonlinear dynamical system. Theor Found Chem Eng 46, 274–278 (2012). https://doi.org/10.1134/S0040579512030074
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S0040579512030074