Comparison of machine learning and stress concentration factors?based fatigue failure prediction in small?scale butt?welded joints

Fatigue behavior of welded joints is significantly influenced by numerous factors, for example, local weld geometry. A representative quantity the influence notch effect created geometry stress concentration factor (SCF). Thus, SCFs are often used to estimate fatigue failure locations and strength; however, this simplifies mutual other influencing factors. Consequently, strength estimates may deviate from experimental results. Machine learning techniques offer an alternative traditional assessment approaches based on SCFs. This study presents a comparison location predictions number cycles 621 tests small-scale butt-welded joints. In addition, understanding importance factors desired. We gradient boosted trees in combination with SHapley Additive exPlanation framework identify influential features their interactions.