Discrete-Time System Identification Based On Novel Information Criterion Using Genetic Algorithm
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 criteri...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
University of El Oued
2017
|
| Subjects: | |
| 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 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | 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. |
|---|