A Deep Learning Surrogate Model for Topology Optimization

In this work, a topology optimization procedure is proposed and applied to the TEAM 25 problem, i.e., a model of a die press with an electromagnet for orientation of magnetic powder. The shape of the press is described as a free discretized profile, and its relation to the flux density in the cavity is simulated by finite element analysis (FEA) and learned by a deep neural network (DNN) model. The DNN is used as a surrogate model for optimization, aiming to obtain a desired flux density distribution in the cavity. Results are promising, as better accuracy is obtained with respect to the full FEA-based optimization approach with the reduced time cost. Once trained, the surrogate model can be used to efficiently solve a whole family of problems where a different target field distribution is defined.

Automated summary

A topology optimization procedure is proposed and applied to the TEAM 25 problem involving a die press model with an electromagnet for orientation of magnetic powder. The relationship between the press shape and flux density in the cavity is simulated using finite element analysis and learned by a deep neural network model. The DNN is used as a surrogate model for optimization, leading to promising results in terms of improved accuracy and reduced time cost compared to the full FEA-based optimization approach.