Title :
Utilizing feedforward neural networks for acceleration of global optimization procedures [SMES problems]
Author :
Ebner, Th. ; Magele, Ch ; Brandstatter, B.R. ; Richter, E.R.
Author_Institution :
Graz Univ. of Technol., Austria
fDate :
9/1/1998 12:00:00 AM
Abstract :
Global optimization in electrical engineering usually requires an enormous amount of CPU time to evaluate the objective function when stochastic methods are used. Approximating the objective function can drastically reduce the computational demands. The use of feedforward neural networks is proposed in this paper and its application is investigated using an unconstrained and a constrained version of the TEAM Workshop problem 22
Keywords :
feedforward neural nets; inverse problems; optimisation; stochastic processes; superconducting magnet energy storage; SMES problems; TEAM Workshop problem 22; computational demands; feedforward neural networks; global optimization procedures; objective function; stochastic methods; Acceleration; Artificial neural networks; Feedforward neural networks; Feeds; Neural networks; Optimization methods; Response surface methodology; Simulated annealing; Stochastic processes; Training data;
Journal_Title :
Magnetics, IEEE Transactions on
