Three different faults, namely, element fault, feed point fault, and feed network fault of antenna array are addressed. The ensemble ML detects the type of fault and location to diagnose a failure in an antenna array and also provides visualization. The machine learning (ML) algorithms, viz, Decision tree, Random forest, K-nearest neighbors, and Naïve Bayes, proven to be efficient in many other applications, are tried for fault detection of 4 × 4 planar antenna array. The 4 × 4 planar antenna array with fault scenarios is simulated using Ansys HFSS tool. The design center frequency of the array is 3.5 GHz. Ensemble of optimized ML algorithms enhances the performance in terms of accuracy and generalization. The proposed tuned stacking ensemble learning (TSEL) model outperforms the individual ML models, including the Support vector machine and tuned majority voting ensemble learning (TMVEL). The TSEL model provides 2% more accuracy than the TMVEL model. The accuracy attained for a single type of fault as well as three types of fault is 97% using 199 and 574 test samples, respectively. The visualisation of the detected fault(s) also is presented.

解决了三种不同的故障，即天线阵列的元件故障、馈电点故障和馈电网络故障。整体机器学习可检测故障类型和位置，以诊断天线阵列中的故障，并提供可视化功能。机器学习 (ML) 算法，即决策树、随机森林、K 最近邻和朴素贝叶斯，在许多其他应用中被证明是有效的，已尝试用于 4 × 4 平面天线阵列的故障检测。使用 Ansys HFSS 工具对具有故障场景的 4 × 4 平面天线阵列进行仿真。阵列的设计中心频率为3.5 GHz。优化的机器学习算法的集合增强了准确性和泛化性方面的性能。所提出的调整堆叠集成学习 (TSEL) 模型优于单个 ML 模型，包括支持向量机和调整多数投票集成学习 (TMVEL)。 TSEL 模型的准确度比 TMVEL 模型高 2%。使用 199 个和 574 个测试样本，对单一类型故障和三种类型故障分别获得的准确率达到 97%。还呈现了检测到的故障的可视化。