As operating frequencies and clock speeds in processors have increased over the years, interconnects affect both the reliability and performance of entire electronic systems. Fault detection and diagnosis of the interconnects are crucial for prognostics and health management (PHM) of electronics. However, existing research works utilizing electrical signals as prognostic factors have limitations, such as the inability to distinguish the root cause of defects, which eventually requires additional destructive evaluation, and vulnerability to noise that results in a false alarm. Herein, we realize the non-destructive detection and diagnosis of defects in Cu interconnects, achieving early detection, high diagnostic accuracy, and noise robustness. To the best of our knowledge, this study first simultaneously analyzes the root cause and severity using electrical signal patterns. In this paper, we experimentally show that S-parameter patterns have the ability for fault diagnosis and they are effective input data for learning algorithms. Furthermore, we propose a novel severity rating ensemble learning (SREL) approach to enhance diagnostic accuracy and noise-robustness. Our method, with a maximum accuracy of 99.3%, outperforms conventional machine learning and multi-class convolutional neural networks (CNN) as additional noise levels increase.

翻译：摘要：随着处理器工作频率和时钟速度逐年提升，互连结构对电子系统的可靠性和性能均产生影响。互连的故障检测与诊断对于电子设备的故障预测与健康管理（PHM）至关重要。然而，现有利用电信号作为预测因子的研究存在局限性，例如无法区分缺陷的根本原因（最终需额外破坏性评估），且易受噪声干扰导致虚警。本文实现了铜互连缺陷的非破坏性检测与诊断，在早期检测、高诊断准确率和噪声鲁棒性方面取得突破。据我们所知，本研究首次利用电信号模式同时分析缺陷的根本原因和严重程度。通过实验，我们证明了S参数模式具备故障诊断能力，且是学习算法的有效输入数据。此外，我们提出了一种新型严重度评分集成学习（SREL）方法，以提升诊断准确率和噪声鲁棒性。该方法在最大准确率达99.3%的情况下，随着附加噪声水平增加，性能优于传统机器学习与多类卷积神经网络（CNN）。