Real-Time Pattern Synthesis for Large-Scale Phased Arrays Based on Autoencoder Network and Knowledge Distillation

In this paper, a deep learning (DL) method based on autoencoder network is proposed to achieve the inverse design of phase retrieval for large-scale antenna arrays. The inverse problem between the beam pattern and antenna phases is established firstly in the context of planar phased array. Inception-Resnet-V2 with prior knowledge (IR-PK) is proposed as an efficient model, which involves the prior knowledge of array factor to guide neural network learning for stronger fitting ability. To obtain the real-time phase retrieval in small terminals, a MobileNet-distilled Inception-ResNet-V2 with prior knowledge (MD-IR-PK) model combining lightweight architecture and knowledge distillation is then designed under the condition of limited resources. The method is validated for array beamforming and hologram. Compared with popular solutions, IR-PK shows the advantages of good accuracy, fast convergence, and computational efficiency. Experiments have been carried out for metasurface-based holography, with the measured results agreeing well with the simulated ones. The proposed method is competitive for complex electromagnetic (EM) inverse problems involving high nonlinearity.