Fatigue life prediction of a L-PBF component in Ti-6Al-4V using sample data, FE-based simulations and machine learning. (February 2023)

• Record Type: Journal Article
• Authors: Cutolo, Antonio; Lammens, Nicolas; Vanden Boer, Koen; Erdelyi, Hunor; Schulz, Matthias; Muralidharan, Gokula Krishna; Thijs, Lore; Elangeswaran, Chola; Van Hooreweder, Brecht
• Is Part Of: International journal of fatigue. Volume 167:Part A(2023)
• Publication Date: 2023-02
• Subjects: Laser powder bed fusion -- Ti-6Al-4V -- Fatigue life -- Machine-learning; Materials -- Fatigue -- Periodicals; Materials -- Fatigue; Periodicals; 620.1122
• DOI: 10.1016/j.ijfatigue.2022.107276
• Languages: English
• ISSNs: 0142-1123

Abstract

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. Highlights: The fatigue life of an L-PBF Ti-6Al-4V demonstrator is predicted and validated Predictions in line with fatigue test results performed on the demonstrator The prediction tool is built by combining FE-simulation and ML-algorithm The ML algorithm is trained using an extensive fatigue database The dataset accounts for several Ti-6Al-4V surface and microstructural conditions