Fatigue life prediction of a L-PBF component in Ti-6Al-4V using sample data, FE-based simulations and machine learning

Abstract

Laser Powder Bed Fusion (L-PBF) is a widely-used additive manufacturing (AM) technique for producing complex metal parts used for a variety of dynamically loaded applications. Fatigue performance of standardized L-PBF samples is at present fairly well understood, while the knowledge on the fatigue behaviour of real-life complex shaped components is often lacking. This work presents insight, methods and results on predicting L-PBF component fatigue life using FE-based simulations, stress-based sample fatigue data and machine learning respectively. A realistic end-use part with representative geometry for many industrial applications was selected and produced in Ti-6Al-4V by L-PBF along with many standardized samples under different building orientations and with different types of heat treatments and surface finishing steps. The results indicate that the developed tool for component fatigue life prediction can accurately predict both the failure location and the number of cycles to failure.