Utilizing Hopfield neural networks and an improved simulated annealing procedure for design optimization of electromagnetic devices

Abstract

A new method for the design optimization of electromagnetic devices is presented. Improved Simulated Annealing (SA) is used along With the Hopfield neural network (€IN) to optimize a solution obtained from a trained multilayered perceptron (MLP). This results in an overall increase in the speed of optimization. Results are presented for two examples which show the effectiveness of the proposed method in obtaining a near optimal solution.In this paper, we present results obtained for a c-core magnetic circuit and a 2-pole dc motor using the proposed method. The simulated annealing algorithm has been modified by separating the search and state updating procedure, of the shortcomings of using with in design optimization problems. The results show the effectiveness of using the proposed method for design optimization.

Accelerating the computer-based simulation and design of electromagnetic devices by applying knowledge

“…Again, knowledge which has been learnt can be used to guide an optimizer or, in some cases, to actually perform optimization. An alternative form of network, that due to Hopfield [7] can provide direct optimization, [8].…”