Title :
Hybrid optimization in electromagnetics using sensitivity information from a neuro-fuzzy model
Author :
Rashid, Kashif ; Ramirez, Jaime A. ; Freeman, Ernest M.
Author_Institution :
Dept. of Electr. & Electron. Eng., Imperial Coll. of Sci., Technol. & Med., London, UK
fDate :
7/1/2000 12:00:00 AM
Abstract :
The use of sensitivity information from a neuro-fuzzy model for the purpose of optimization is investigated in this paper. This approach permits the application of classic deterministic or hybrid optimization methods in establishing the global minimum of any approximated objective function using neuro-fuzzy modeling. For nondifferentiable functions this approach is of great benefit. An analytical problem and the TEAM 22 benchmark problem are investigated. Results using the genetic algorithm method and the sequential quadratic programming method in sequence show the usefulness of the formulation
Keywords :
electrical engineering computing; electromagnetic field theory; fuzzy neural nets; genetic algorithms; optimisation; quadratic programming; sensitivity; TEAM 22 benchmark problem; analytical problem; approximated objective function; deterministic method; electromagnetics; genetic algorithm method; global minimum; hybrid optimization; neuro-fuzzy model; nondifferentiable functions; search process; sensitivity information; sequential quadratic programming method; Cost function; Design optimization; Electromagnetic modeling; Genetic algorithms; Optimization methods; Predictive models; Quadratic programming; Sampling methods; Signal generators; Stochastic processes;
Journal_Title :
Magnetics, IEEE Transactions on
