Neural networks and evolutionary algorithm application to complex EM structures modeling

The increasing interest among the scientific community on soft computing and optimization techniques in recent years leads to develop effective ad-hoc procedures for electromagnetic structures modelling, often based on evolutionary iterative algorithms. In fact, in most of engineering problems, numerical simulations could be very computationally expensive. An example of this is for instance the design of a complex EM structures with a lot of degrees of freedom. To enhance the speed of the optimization task, in this work the use of Artificial Neural Network is presented as a technique to suitably modelling and optimize complex EM structures.