Title: Identification of nonlinear dynamic systems described by Hammerstein state-space models with discontinuous nonlinearities
Authors: Houda Salhi; Samira Kamoun
Addresses: Laboratory of Sciences and Technique of Automatic Control and Computer Engineering (Lab-SAT), National Engineering School of Sfax (ENIS), University of Sfax, Tunisia ' Laboratory of Sciences and Technique of Automatic Control and Computer Engineering (Lab-SAT), National Engineering School of Sfax (ENIS), University of Sfax, Tunisia
Abstract: This paper deals with the parameter estimation problem of Hammerstein state-space models with different nonlinearities. The basic idea is to develop a recursive algorithm which estimate jointly the system model parameters and the state variables by combining the adjustable model method, the least squares technique and the Kalman filter. A numerical example is provided to test the flexibility and the effectiveness of the proposed algorithm.
Keywords: recursive algorithm; parameter estimation; state estimation; Hammerstein model; discontinuous nonlinearities; adjustable model; least squares technique; Kalman filter; preaload; dead zone nonlinearity.
International Journal of Engineering Systems Modelling and Simulation, 2017 Vol.9 No.3, pp.127 - 135
Received: 09 Apr 2016
Accepted: 22 Oct 2016
Published online: 08 Jun 2017 *