Deep Neural Networks Based Surrogate Model for Topology Optimization of Electromagnetic Devices

In this work a novel approach is presented for topology optimization of low frequency electromagnetic devices. In particular a surrogate model based on deep neural networks with encoder-decoder architecture is introduced. A first autoencoder deep neural network learns to represent the input images that describe the topology, i.e. geometry and materials. The novel idea is to use the low dimensional output space of the encoder as the search space of the optimization algorithm, instead of using the higher dimensional space represented by the input images. A second deep neural network learns the relationship between the encoder outputs and the objective function (i.e., torque), which is calculated by means of a finite element analysis. The calculation time for the optimization is greatly improved by reducing the dimensionality of the search space, and by introducing the surrogate model, whereas the quality of the result is slightly affected.