In this study, Machine Learning (ML) methods combined with Optuna hyperparameter optimization were investigated to predict creep strain in solder joints of multilayer chip capacitors. Material properties, geometry and thermal loading conditions were varied in simulations using Finite Element Modeling. Evaluated ML models included Random Forest, Gradient Boosting, Support Vector Regression (SVR) and Artificial Neural Network (ANN). The results demonstrated a prediction accuracy of 96%, particularly for SVR and ANN. The model performance significantly improved with increasing data size up to around 600 simulations. In the feature and hyperparameter importance analysis, solder stand-off height and component length most influenced ANN predictions, with learning rate being the key hyperparameter, while for SVR, the regularization parameter or kernel function was most critical.

The introduction of silicon carbide(SiC) has reduced the superiority of traditional silicon-based power module pack-aging strategies. As packaging strategies become increasingly complex, classical thermal modelling tools often prove inadequate in balancing efficiency with accuracy. Integrating these tools with machine learning (ML) can significantly enhance their application potential. This discussion commences by addressing the pressing issues in thermal modelling of SiC modules, specifically the challenges associated with multiple heat sources and heat spreading. During the design stage, ML models can swiftly simulate the thermal response of various packaging strategies, aiding engineers in eliminating ineffective options. In the monitoring phase, the employment of a digital twin enables a deeper investigation into degradation phenomena. This article reviews the current status and explores the potential applications of ML in thermal modelling of SiC power modules.