Discovering Pareto-Optimal Magnetic-Design Solutions via a Generative Adversarial Network

Abstract

In the framework of induction hardening, the coil design task is particularly suitable to be formulated as a multi-objective optimization problem. In fact, the Pareto front estimation raises the issue of guaranteeing a satisfactory diversity and number of non-dominated solutions to be provided to the decision maker (DM). In this article, a generative adversarial network (GAN) and a forward neural network (FNN), which is cascade connected to the GAN generator, produce additional Pareto optimal solutions starting from the results of a genetic algorithm [non-dominated sorting genetic algorithm (NSGA II)] used as a training set. The FNN ensures an accurate prediction of the objectives of the added solutions, removing the need for further field analyses. This method is first tested against two analytical problems and subsequently validated on a three-objective coil design task to illustrate its utility for a real-world case.