ABSTRACT This study proposes a novel physics‐informed neural network (PINN) model for predicting the high‐cycle fatigue (HCF) life of a nickel‐based single‐crystal (SX) superalloy DD6 at elevated temperatures, with the crystallographic orientation and other factors considered. The model employs quaternions as input features and incorporates the Schmid factor into the loss function to impose physical constraints on crystal orientation. The results show that the present model exhibits high accuracy and generalization, which significantly outperforms conventional ML methods. Furthermore, the comprehensive influences of temperature, orientation, and its deviation on the fatigue life can be revealed. Finally, SHAP (SHapley Additive exPlanations) analysis is conducted to explore the multiple factors influencing the HCF life, and the relative importance of these factors is evaluated.
Wang et al. (Wed,) studied this question.