The system identification and control of Hammerstein system using non-uniform rational B-spline neural network and particle swarm optimization

Abstract

a b s t r a c tIn this paper a new system identification algorithm is introduced for Hammerstein systems based on observational input/output data. The nonlinear static function in the Hammerstein system is modelled using a non-uniform rational B-spline (NURB) neural network. The proposed system identification algorithm for this NURB network based Hammerstein system consists of two successive stages. First the shaping parameters in NURB network are estimated using a particle swarm optimization (PSO) procedure. Then the remaining parameters are estimated by the method of the singular value decomposition (SVD). Numerical examples including a model based controller are utilized to demonstrate the efficacy of the proposed approach. The controller consists of computing the inverse of the nonlinear static function approximated by NURB network, followed by a linear pole assignment controller.

Swarm and evolutionary computing algorithms for system identification and filter design: A comprehensive review

“…In (Hong and Chen, 2012), non-uniform rational B-spline (NURB) neural network was used to represent the nonlinear block in a Hammerstein model.…”

Dynamic multivariate B-spline neural network design using orthogonal least squares algorithm for non-linear system identification

“…The BSNN is a feed-forward neural network with two layers of neurons [5,10,12]. The hidden layer comprises neurons with the activation function in the form of multivariate B-spline function.…”

“…They should though be equipped with delay units in order to be used to model dynamic systems. Thus, the BSNN has to be fed with current and delayed values of the inputs and the outputs of the system [2,3,5,10,12,14]. A set comprising Q data pairs collected from the inputs and outputs of the process is considered.…”

“…There are several techniques proposed to select the knots of the B-spline functions [5,7,8,9,10,11,12].…”

Microcontroller-Based B-Spline Neural Position Control for Voice Coil Motors

“…Unlike other basis functions using an exponential function, the B-spline basis function is obtained by a recurrence operation with simple calculation [24], [25]. The low computational complexity is important.…”