Multi-Algorithm Ensemble Learning Framework for Predicting the Solder Joint Reliability of Wafer-Level Packaging.

Abstract

To enhance design efficiency, this study employs an effective prediction approach that utilizes validated finite element analysis (FEA) to generate simulation data and subsequently applies machine learning (ML) techniques to predict packaging reliability. Validated FEA models are used to replace the costly design-on-experiment approach. However, the training time for some ML algorithms is costly; therefore, reducing the size of the training dataset to lower computational cost is a critical issue for ML. Nevertheless, this approach simultaneously introduces new challenges in maintaining prediction accuracy due to the inherent limitations of small data machine learning. To address these challenges, this work adopts Wafer-Level Packaging (WLP) as a case study. It proposes an ensemble learning framework that integrates multiple machine learning algorithms to enhance predictive robustness. By leveraging the complementary strengths of different algorithms and frameworks, the ensemble approach effectively improves generalization, enabling accurate predictions even with constrained training data.