An Approach to Predicting Fatigue Crack Growth Under Mixed-Mode Loading Based on Improved Gaussian Process

This paper proposes an approach to predicting fatigue crack growth under mixed-mode loading based on improved Gaussian process. In terms of analyzing the theoretical background for growth, a corresponding finite element model is built generate sufficient simulation data, which utilized obtain key parameters (e.g., stress intensity factor) And then, process achieved meet condition that factor nonlinear continuous change in especially loading. Following, idea local sample densification method implemented improve generation according simplified path. Based above investigation, prediction using finished, subsequently verified through test data lower bainite steel (SCM435) material. The results show proposed has better computational accuracy and efficiency than traditional