Generative Pixelated Microstrip Millimeter-Wave Circuit Components Design

In this paper, we present a novel method for the generative design of pixelated microstrip Millimeter-Wave (mm-wave) circuit components. Our approach utilizes a primary meandering transmission line, which is connected to the input and output/terminated ports, with random small pixelated patches surrounding the primary transmission line as perturbations. A 2D Convolutional Neural Network (CNN) incorporating a Convolutional Block Attention Module (CBAM) is trained and employed as a forward solver to predict the input impedance of the circuit component. Additionally, a Variational Autoencoder (VAE) is trained to generate new pixelated microstrip mm-wave circuit component patterns by sampling from the latent space, thereby extending beyond the original training dataset. By leveraging the CNN-based forward solver for impedance prediction and the VAE for pattern generation, we can inversely generate the mm-wave circuit component design that meets specific input impedance requirements.