Caponio A., Neri F., Cascella G.L., Salvatore N.
 

This paper appears in: Evolutionary Computation, 2008. CEC 2008. (IEEE World Congress on Computational Intelligence). IEEE Congress on
Issue Date: 1-6 June 2008
On page(s): 2113 - 2120
Location: Hong Kong
Print ISBN: 978-1-4244-1822-0
INSPEC Accession Number: 10250790
Digital Object Identifier: 10.1109/CEC.2008.4631079
Date of Current Version: 23 September 2008

ABSTRACT

This paper proposes the application of Memetic Algorithms employing Differential Evolution as an evolutionary framework in order to achieve optimal design of the control system for a permanent-magnet synchronous motor. Two Memetic Differential Evolution frameworks have been considered in this paper and their performance has been compared to a standard Differential Evolution, a standard Genetic Algorithm and a Memetic Algorithm presented in literature for solving the same problem. All the algorithms have been tested on a simulation of the whole system (control system and plant) using a model obtained through identification tests. Numerical results show that the Memetic Differential Evolution frameworks seem to be very promising in terms of convergence speed and has fairly good performance in terms of final solution detected for the real-world problem under examination. In particular, it should be remarked that the employment of a meta-heuristic local search component during the early stages of the evolution seems to be very beneficial in terms of algorithmic efficiency.