Search results

To present a neural network‐based approach to the design of electromagnetic devices.

A neural model is created which reproduces the relationship between the design parameters of the device and the performance parameters, typically field values.

The neural model is a single hidden layer MLP network, trained by using a set of cases calculated, for example, by means of a finite element analysis. The design problem can be solved by fixing the performance values at the output of the network and by calculating the corresponding input values. The relationship between the input and the output of the neural network is represented by three equations systems. By means of these three systems, we can forward the domain of the input, and we can back propagate the desired output throughout the network layers. In such a way, both the domain of the design parameters and the domain of the desired performances values can be projected in the same space. Whatever point inside the intersection between the two projected domains corresponds to a solution of the design problem.

Presents a procedure which is able to find a point belonging to such an intersection.

The purpose of this paper is to present a constructive algorithm to design multilayer perceptron neural networks used as approximation models of electromagnetic devices.

The proposed procedure allows automatic determination of both the number of neurons and the synaptic weights of networks with a single hidden layer. The approximation model is used in design optimization problems. The inputs of the neural network correspond to the design parameters whereas the output corresponds to the objective function of the optimization problem. The neural model is then inverted in order to determine which input is associated to a prefixed output.

The performance of the algorithm has been tested on analytical function and on the TEAM workshop problem 25.

As the reliability of the optimum solution is strongly affected by the accuracy of the neural approximation model, the approximation error is kept as low as possible, especially in the maximum/minimum points.