Predicting crack nucleation in commercially pure titanium using orientation imaging microscopy and machine learning

Abstract

Due to the prohibitively long experimental and simulation times, dwell fatigue (DF) failure prediction in titanium and its alloys is a challenging task. Since most of these failures have a microstructural level origin, this work focusses on utilizing minimal experiments and machine learning for predicting failure initiation points in a given microstructure. Failure initiation points in commercially pure titanium were identified using interrupted tensile and DF tests. Orientation imaging data was used to train a Random Forest model to calculate the relative importance of various grain orientation-based features to crack nucleation. Subsequently a predictive model for identifying locations that are likely to form a DF crack in a microstructure is developed.