Effect of microstructural heterogeneity on fatigue strength predicted by reinforcement machine learning

The posterior statistical distributions of fatigue strength are determined using Bayesian inferential statistics and the Metropolis Monte Carlo method. This study explores how structural heterogeneity affects ultrahigh cycle in additive manufacturing. methods procedures may assist estimate posteriors scatter. acceptable probability relies on Markov chain's random microstructure state. In addition to commonly studied variables, proportion chemical composition was demonstrated substantially impact if lifetime crack propagation did not prevail due high threshold internal notches. utilizes an algorithm typically used for quantum mechanics solve complicated multifactorial problem. inputs outputs modified by fitting microstructural heterogeneities into algorithm. main advantage here is applying a general-purpose nonphenomenological model that can be applied multiple influencing factors without numerical penalty.