Discrete-Time System Identification Based On Novel Information Criterion Using Genetic Algorithm

• Main Authors: Abd Samad, Md Fahmi, Mohd Nasir, Abdul Rahman
• Format: Article
• Language: English
• Published: University of El Oued 2017
• Subjects: Q Science (General); QA Mathematics
• Online Access: http://eprints.utem.edu.my/id/eprint/22715/2/3353-7186-1-PB_MMETIC_JFAS.pdf; http://eprints.utem.edu.my/id/eprint/22715/; http://jfas.info/psjfas/index.php/jfas/article/view/3353/1892; http://dx.doi.org/10.4314/jfas.v9i7s.54
• Institution: Universiti Teknikal Malaysia Melaka

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.