With the increasing demand for electronic products, the electronic package gradually developed toward miniaturization and high density. The most significant advantage of the Wafer-Level Package (WLP) is that it can effectively reduce the volume and footprint area of the package. An important issue in the design of WLP is how to quickly and accurately predict the reliability life under the accelerated thermal cycling test (ATCT). If the simulation approach is not adopted, it usually takes several ACTCs to design a WLP, and each ACTC will take several months to get the reliability life results, which increases development time considerably. However, simulation results may differ depending on the designer’s domain knowledge, ability, and experience. This shortcoming can be overcome with artificial intelligence (AI). In this study, finite element analysis (FEA) is combined with machine learning algorithms, e.g., Kernel Ridge Regression (KRR), to create an AI model for predicting the reliability life of electronic packaging. Kernel Ridge Regression (KRR) combined with the K-means cluster algorithm provides a highly accurate and efficient way to obtain AI models for large-scale data sets.

Equation-Informed Neural Networks (EINNs) are developed as an efficient method for extracting the coefficients of constitutive equations. Subsequently, numerical Bayesian Inference (BI) iterations were applied to estimate the distribution of these coefficients, thereby further refining them. We could generate coefficients optimally aligned with the targeted application scenario by carefully adjusting pre-processing mapping parameters and identifying dataset preferences. Leveraging graphical representation techniques, the EINNs formulation is implemented in temperature- and strain-rate-dependent hyperbolic Garofalo, Anand, and Chaboche constitutive models to extract the corresponding coefficients for lead-free SAC305 solder material. The performance of the EINNs-based extracted coefficients, obtained from experimental results of SAC305 solder material, is comparable to existing studies. The methodology offers the dual advantage of providing the coefficients’ value and distribution against the training dataset.

There has always been high interest in predicting the solder joint fatigue life in advanced packaging with high accuracy and efficiency. Artificial Intelligence Plus (AI+) is becoming increasingly popular as computational facilities continue to develop. This study will introduce machine learning (a core component of AI). With machine learning, metamodels that approximate the attributes of systems or functions are created to predict the fatigue life of advanced packaging. However, the prediction ability is highly dependent on the size and distribution of the training data. Increasing the amount of training data is the most intuitive approach to improve prediction performance, but this implies a higher computational cost. In this research, the adaptive sampling methods are applied to build the machine learning model with a small dataset sampled from an existing database. The performance of the model will be visualized using predefined criteria. Moreover, ensemble learning can be used to improve the performance of AI models after they have been fully trained.

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.