The study published in International Journal of Fatigue deals with the modelling of fatigue life prediction of additively manufactured Ti-6Al-4V samples using machine learning models. Representatives of the Czech Aerospace Research Centre, the Austrian CEST (Center of Electrochemical Surface Technology), the Hungarian Premet Kft., and the Austrian University of Applied Sciences Upper Austria cooperated on the study.
The study introduces a framework based on the machine learning approach and Spearman’s rank correlation analysis as an effective instrument to solve an influence of inner structure defects and stress amplitude on the fatigue life performance of 3D printed Ti-6Al-4V samples. The results present comparison between predicted and experimental results and validate the proposed framework.
