Yield estimation of antenna systems is important to check their robustness with respect to the uncertain sources. Since direct Monte Carlo sampling of accurate physics‐based models can be computationally intensive, this work proposes the use of the polynomial chaos–Kriging (PC‐Kriging) metamodeling method for fast yield estimation of multiband patch antennas. PC‐Kriging integrates the polynomial chaos expansion (PCE) as the trend function of Kriging metamodel since the PCE is good at capturing the function tendency and Kriging is good at matching the observations at training points. The PC‐Kriging method is demonstrated on two analytical cases and two multiband patch antenna cases and is compared with the PCE and Kriging metamodeling methods. In the analytical cases, PC‐Kriging reduces the computational cost by over 40% compared with PCE and over 94% compared with Kriging. In the antenna cases, PC‐Kriging reduces the computational cost by over 60% compared with Kriging and over 90% compared with PCE. In all cases, the savings are obtained without compromising the accuracy.

中文翻译：

---

基于多项式混沌Kriging的多频带贴片天线有效产量估算

天线系统的成品率估计对于检查不确定源的鲁棒性很重要。由于精确的基于物理的模型的直接蒙特卡洛采样可能需要大量计算，因此这项工作建议使用多项式混沌-克里格（PC-Kriging）元建模方法来快速估计多频带贴片天线的良率。PC-Kriging将多项式混沌扩展（PCE）集成为Kriging元模型的趋势函数，因为PCE善于捕获函数趋势，而Kriging善于匹配训练点的观测值。在两个分析案例和两个多频带贴片天线案例中演示了PC-Kriging方法，并与PCE和Kriging元建模方法进行了比较。在分析情况下，与PCE相比，PC-Kriging降低了40％的计算成本，与Kriging相比，降低了94％以上的计算成本。在天线情况下，PC-Kriging与Kriging相比可将计算成本降低60％以上，与PCE相比可将计算成本降低90％以上。在所有情况下，都可以在不影响精度的情况下节省成本。