An Improved NSGA-II Algorithm for Multi-Objective Optimization of Irregular Polygon Patch Antennas

This paper presents an improved NSGA-II algorithm for the multi-objective optimization of irregular polygon patch antennas (IPPAs), improving convergence efficiency and Pareto front quality. The algorithm integrates adaptive mechanisms that dynamically adjust crossover and mutation rates based on generational progression, accelerating convergence while preserving solution diversity. Furthermore, a simulated annealing-inspired acceptance criterion is embedded during offspring generation to mitigate local optima trapping and enhance evolutionary robustness. A dual-objective formulation simultaneously minimizes antenna volume and maximizes operational bandwidth within the X-band. Optimization is executed via HFSS co-simulation, with detailed electromagnetic models ensuring physical realizability and design fidelity. The optimized antenna achieves a compact volume of 2807.6 mm³ and an operational bandwidth of 2.7 GHz. Experimental validation of fabricated prototypes demonstrates agreement with simulations, confirming the accuracy and reliability of the proposed method. These results demonstrate the effectiveness of the improved NSGA-II algorithm in addressing complex multi-objective design challenges and underscore its potential in advanced broadband antenna applications.