Performance Optimization of Wide-Angle Frequency Scanning Antenna Based on Artificial Surface Plasmon

This paper focuses on the performance optimization of wide-angle frequency scanning antenna based on artificial surface plasmon (SSPP). The article begins with a detailed description of the stringent requirements of communication technology on antenna performance and the potential application value of SSPP in the field of antennas. It deeply analyzes the working principle and existing limitations of traditional scanning antennas, and innovatively proposes a new antenna design concept integrating SSPP. In order to achieve the performance optimization goal, an innovative algorithm based on adaptive particle swarm optimization (APSO) and deep learning is carefully designed. The particle swarm search strategy is optimized through a dynamic weight adjustment mechanism, and a convolutional neural network (CNN) is used to accurately construct an antenna performance prediction model. The antenna model was simulated with the electromagnetic simulation software HFSS. Under the conditions of scanning angle range of -80° to 80° and frequency range of 2-6GHz, the maximum scanning angle of the antenna before optimization was 60° at 4GHz, and the gain was 8dB; after optimization, the maximum scanning angle jumped to 80°, the gain increased to 10dB, and the sidelobe level decreased by 3dB. The experimental verification results are basically consistent with the simulation results, which effectively verifies the effectiveness of the algorithm and design.