Title: System identification using the neural-extended Kalman filter for state-estimation and controller modification

Authors: Stephen C. Stubberud, Kathleen A. Kramer

Addresses: Oakridge Technology, 2481 Oakridge Cove, Del Mar, CA 92014, USA. ' Electrical Engineering Program, University of San Diego, 5998 Alcala Park, San Diego, California, USA

Abstract: The neural extended Kalman filter (NEKF) is an adaptive state estimation technique that can be used in target tracking and directly in a feedback loop. It improves state estimates by learning the difference between the a priori model and the actual system dynamics. The neural network training occurs while the system is in operation. Often, however, due to stability concerns, such an adaptive component in the feedback loop is not considered desirable by the designer of a control system. Instead, the tuning of parameters is considered to be more acceptable. The ability of the NEKF to learn dynamics in an open-loop implementation, such as with target tracking and intercept prediction, can be used to identify mismodelled dynamics external to the closed-loop system. The improved non-linear system model can then be used at given intervals to adapt the state estimator and the state feedback gains in the control law, providing better performance based on the actual system dynamics. This variation to NEKF control operations is introduced using applications to the non-linear version of the standard cart-pendulum system.

Keywords: adaptive control; Kalman filtering; neural networks; system identification; controller modification; state estimation; target tracking; intercept prediction; nonlinear systems; cart-pendulum system.

DOI: 10.1504/IJMIC.2010.035279

International Journal of Modelling, Identification and Control, 2010 Vol.11 No.1/2, pp.52 - 58

Published online: 20 Sep 2010 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article