Discrete-time system identification based on novel information criterion using genetic algorithm

Abstract

Model structure selection is a problem in system identification which addresses selecting an adequate model i.e. a model that has a good balance between parsimony and accuracy in approximating a dynamic system. Parameter magnitude-based information criterion 2 (PMIC2), as a novel information criterion, is used alongside Akaike information criterion (AIC). Genetic algorithm (GA) as a popular search method, is used for selecting a model structure. The advantage of using GA is in reduction of computational burden. This paper investigates the identification of dynamic system in the form of NARX (Non-linear AutoRegressive with eXogenous input) model based on PMIC2 and AIC using GA. This shall be tested using computational software on a number of simulated systems. As a conclusion, PMIC2 is able to select optimum model structure better than AIC.

Keywords: Akaike information criterion; genetic algorithm; model structure selection; parameter-magnitude information criterion; search method