Superior terahertz radiation detection through novel micro circular log-periodic antenna engineered with an advanced evolutionary neural network algorithm

In this work, we introduce a novel Micro Circular Log-Periodic Antenna (MCLPA) optimized with an advanced Evolutionary Neural Network (ENN) algorithm, specifically designed to enhance terahertz (THz) radiation detection. By leveraging the adaptive capabilities of the ENN framework, the antenna design efficiency is significantly improved, enabling rapid prototyping and yielding highly optimized structures tailored for practical THz applications. Extensive characterization confirms that the proposed MCLPA achieves outstanding performance, including an ultra-broad operational bandwidth of 372 GHz (0.135-0.507 THz), a peak gain of 5.51 dBi, an optimal S-parameter (S₁₁) of -13.68 dB, and a maximum radiation efficiency of 82.39%. In addition, the MCLPA exhibits superior sensitivity, low noise susceptibility, and fast response, which are key attributes for reliable and precise THz detection. When configured in array form, the design further enhances gain and directional responsiveness, demonstrating the scalability and deployment potential of the MCLPA. This ENN-driven MCLPA represents a significant breakthrough in THz antenna engineering, introducing a transformative design paradigm that synergistically integrates algorithmic intelligence with structural innovation. By substantially reducing design time and cost while achieving exceptional performance, the proposed ENN framework sets a new benchmark for the development of next-generation THz detection and communication systems, offering broad implications for future high-frequency technologies.