AI 中文总结
该研究针对聚合物材料复介电常数提取难题，提出梯度增强NSGA-II算法。它融合全局探索与局部细化，纳入多维约束。实验表明其结果与文献和测量高度一致，相比其他算法收敛代数减少约50%，能快速评估室内无线性能，助力优化布局和提升网络性能。
AI 中文摘要
本文首次提出梯度增强的非支配排序遗传算法II（G-NSGA-II），以应对聚合物材料复介电常数提取问题中局部最优和解决方案非唯一性的挑战。该自适应混合算法将NSGA-II的全局探索能力与基于梯度的局部细化相结合，由种群停滞检测机制触发。此外，通过联合优化多个样品厚度的传输和反射系数纳入多维约束。在20-40GHz频段对六种典型聚合物进行的实验验证表明，检索到的相对介电常数和厚度与文献值和物理测量高度一致。与标准启发式和基于梯度的算法相比，所提出的G-NSGA-II将收敛所需的代数减少了约50%。这种速度上的显著提高，结合增强的鲁棒性，为建筑和电磁工程中的宽带介电特性提供了高度可靠和高效的解决方案。简单的测量方法和所提出的高效算法允许在室内环境中快速评估无线性能。这种方法是优化现有无线布局和提高网络性能的宝贵工具。
英文摘要
This paper presents gradient-enhanced non-dominated sorting genetic algorithm II (G-NSGA-II) to address the challenges of local optima and solution non-uniqueness in the complex permittivity extraction problem for the first time. This adaptive hybrid algorithm integrates the global exploration capability of NSGA-II with gradient-based local refinement, triggered by a population-stagnation detection mechanism. Furthermore, multi-dimensional constraints are incorporated by jointly optimizing transmission and reflection coefficients across multiple sample thicknesses. Experimental validation conducted on six typical polymers in the 20--40 GHz band demonstrates that the retrieved relative permittivity and thicknesses are in high agreement with literature values and physical measurements. Compared to standard heuristic and gradient-based algorithms, the proposed G-NSGA-II reduces the number of generations required for convergence by approximately 50\%. This significant improvement in speed, combined with enhanced robustness, provides a highly reliable and efficient solution for broadband dielectric characterization in architectural and electromagnetic engineering. The simple measurement method and the proposed efficient algorithm allow for a rapid evalutaion of wireless performance within indoor environments. This approach serves as a valuable tool for optimizing existing wireless layouts and improving network performance.
