Research on accelerated coding absorber design with deep learning

Abstract

The traditional design of metamaterials requires a large amount of prior knowledge in electromagnetism and is time-consuming and labour-intensive, but these challenges can be addressed by using trained neural networks to accelerate the forward design process. However, when it comes to coded absorbers, there is no clear ‘guidance manual’ on which neural network is most effective for this task. In this paper, three basic neural networks (full connection, one-dimensional convolution and two-dimensional convolution) are designed considering the apparent pattern and structural parameters of the coded absorber, trained under the same conditions, and evaluated for performance.The two-dimensional convolutional neural network achieved the highest accuracy on the test set, with an average accuracy of 92.37% and 70.3% of groups with accuracy greater than 95%. These results indicate that trained neural networks have great potential to approximate the functionality of traditional electromagnetic simulation software, and the two-dimensional convolutional neural network is the best choice for accelerating the forward design of coded absorbers.