A Global‐Local Cooperative Surrogate‐Assisted Multi‐Objective Differential Evolution Algorithm for Parameterized Antenna Topology Optimization

A cooperative optimization framework with enhanced parameterized topology and current‐driven dimensionality reduction approach is proposed. The expansion of the design space in both dimensionality and diversity is achieved by the enhanced parameterized topology through the introduction of Boolean and shape variables, which permit free adjustment of geometry, topology type, position, and dimension. Furthermore, rapid dimensionality reduction is achieved using a current‐driven strategy, whereby the current distribution is analyzed to identify critical parameters. The ensuing multi‐objective optimization challenge is addressed by a global‐local cooperative surrogate‐assisted multi‐objective differential evolution algorithm (GLCSA‐MODE). The approach is guided synergistically by global and local surrogate models to achieve rapid enhancement of antenna performance. To validate the effectiveness of the proposed method, a microstrip patch antenna is optimized, fabricated, and measured. The measured results are in good agreement with the simulations, demonstrating an impedance bandwidth of 43.21% (4.88–7.57 GHz) and a flat gain response in the passband. The results confirm the method's effectiveness in dual‐objective optimization and its capability to generate unconventional antenna topologies.