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

Abstract

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

Approach for the probabilistic fatigue assessment of welded joints based on the local geometry of the weld seam

“…A method is proposed and tested in this study for the probabilistic fatigue assessment of welded joints based on their individual geometrical parameters using a combination of methods from previous studies. 17,20,27,28 The geometrical parameters were evaluated from 3D surface scans of 26 test series from previous studies [30][31][32][33][34][35][36] of welded joints.…”

“…The geometrical parameters and fatigue test results taken from previous studies [30][31][32][33][34][35][36] and other unpublished investigations are summarized in Table 1. These data contain 390 single fatigue tests with four different types of welded joints: single V-butt joints, double V-butt joints, cruciform joints, and T-joints.…”

Fatigue crack growth simulation by extended finite element method: A review of case studies

“…Since all of them are based on experimental or analytical data, they are not presented here, but some of them are referenced here for the benefit of readers. [136][137][138][139][140][141][142] In addition, many other recent papers presented also this important topic, some of them described briefly in the following text.…”

Very high‐cycle fatigue life prediction of high‐strength steel based on machine learning

“…A reinforcement ML method was developed to evaluate the effect of microstructural heterogeneity on the VHCF fatigue strength 13 . The comparison between the traditional stress concentration factor methods and ML prediction methods indicated that ML exhibits superior predictive performance 14 . The previous findings indicate that the application of ML method in the VHCF life prediction of high‐strength steel is feasible.…”