Application of genetic algorithm with a novel adaptive scheme for the identification of induction machine parameters

This work presents a powerful application of genetic algorithm (GA) for the identification of Park's model electric parameters of an induction machine. Such a model is used in control techniques for variable speed drives. GA is considered as the most recent product of the artificial intelligenc...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on energy conversion 2005-06, Vol.20 (2), p.284-291
Main Authors: Abdelhadi, B., Benoudjit, A., Nait-Said, N.
Format: Article
Language:English
Subjects:
Adaptive algorithms
Adaptive genetic algorithm (GA)
Artificial intelligence
Computational efficiency
Electric variables control
Electrical engineering
Expert systems
Genetic algorithms
identification method
induction machine
Induction machines
Mathematical models
Optimization
Optimization methods
optimization technique
Performance evaluation
Power engineering computing
Testing
Variable speed drives
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This work presents a powerful application of genetic algorithm (GA) for the identification of Park's model electric parameters of an induction machine. Such a model is used in control techniques for variable speed drives. GA is considered as the most recent product of the artificial intelligence techniques. By its evolutionary character, it solves efficient electrical engineering problems despite its relative slowness in its standard form. Such shortcoming has been dealt with by incorporating a novel adaptive scheme. The suggested adaptive GA aims at accurately solving a nonlinear fitting optimization problem within a reduced computing time. The yielded solution of parameters produces, according to the machine model, the closest possible curves to those of the references. Finally, for the purpose of validation, the obtained machine performances of the adaptive GA method are compared with both those of references and those of a near-least-square-error estimator using experimental variable load measurements.
ISSN:0885-8969
1558-0059
DOI:10.1109/TEC.2004.841508