A mating technique for various crossover in genetic algorithm for optimum system identification

Abd Samad @ Mahmood, Md Fahmi and Zainuddin, Farah Ayiesya (2021) A mating technique for various crossover in genetic algorithm for optimum system identification. International Review of Mechanical Engineering, 15 (11). pp. 574-581. ISSN 1970 - 8734

Text 21102-47870-1-PB.PDF Restricted to Registered users only Download (1MB)

Abstract

System identification is the study involving the derivation of a mathematical model from input and output data to explain dynamical behavior of a system. Such derivation is made using a mathematical model based on certain specified assumptions. To researchers who are involved in the application of Genetic Algorithm (GA) in optimization, the process of choosing the best parents in the population for mating has become of great interest. Here, the application is on selecting a model structure for system identification. This step addresses selecting an adequate model, i.e. a model that has a good balance between parsimony and accuracy in approximating a dynamic system. This paper demonstrates the integration of a novel mating technique with various types of crossover to enhance the performance of GA application. Four discrete-time systems of linear and nonlinear types are simulated and identified. The results show that GA with single parent mating can speed up the search for optimal models and avoid premature convergence even with different types of crossover.

Item Type:	Article
Uncontrolled Keywords:	System identification, Genetic algorithm, Crossover, Mating, Optimization
Divisions:	Faculty of Mechanical Engineering
Depositing User:	Sabariah Ismail
Date Deposited:	26 Apr 2024 08:36
Last Modified:	26 Apr 2024 08:36
URI:	http://eprints.utem.edu.my/id/eprint/26735
Statistic Details:	View Download Statistic

Actions (login required)

View Item