A mating technique for various crossover in genetic algorithm for optimum system identification
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 G...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Praise Worthy Prize
2021
|
| Online Access: | http://eprints.utem.edu.my/id/eprint/26735/2/21102-47870-1-PB.PDF http://eprints.utem.edu.my/id/eprint/26735/ https://www.praiseworthyprize.org/jsm/index.php?journal=ireme&page=article&op=view&path%5B%5D=26010 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | 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. |
|---|