Applying a dual extended Kalman filter for the nonlinear state and parameter estimations of a continuous stirred tank reactor

The extended Kalman filter (EKF) provides an efficient method for generating approximate maximum-likelihood estimates of the states or parameters of discrete-time nonlinear dynamical systems. In this paper, we consider the dual-estimation problem, the so-called dual EKF, in which both the states of a dynamical system and its parameters are estimated simultaneously, given only noisy observations. The main contribution of this paper is to show the efficacy of a proposed simplified dual-EKF technique (which in this work will be referred to as the dual EKF-2) in comparison with the conventional joint EKF. This has been demonstrated by conducting simulation studies on a CSTR which has been dynamically simulated using the HYSYS simulation package. Extensive analysis revealed that, not only the dual-EKF approach can achieve optimal state- and parameter-estimation performances comparable to the joint EKF, but also it has the main advantage of carrying out separate estimations of the states and parameters.