Settings

Now showing1 - 2 of 2
  • Some of the metrics are blocked by your 
    consent settings
    Item type:Publication, Access status: with files ,
    Comparison of machine learning and stress concentration factors-based fatigue failure prediction in small-scale butt-welded joints
    (Wiley-Blackwell, 2022-07-31)
    Braun, Moritz
    ;
    Kellner, Leon
    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.
    Publicationtype: Journal Article
    Scopus© Citations 11  85  336
  • Some of the metrics are blocked by your 
    consent settings
    Item type:Publication, Access status: with files ,
    Study on the cohesive edge crack in a square plate with the cohesive element method
    (Springer, 2021-07-01)
    Kellner, Leon
    ;
    Lu, Wenjun
    ;
    Ehlers, Sören
    ;
    Høyland, Knut V.
    The size of the fully developed process zone (FDPZ) is needed for the arrangement of displacement sensors in fracture experiments and choosing element size in numerical models using the cohesive element method (CEM). However, the FDPZ size is generally not known beforehand. Analytical solutions for the exact FDPZ size only exist for highly idealised bodies, e.g. semi-infinite plates. With respect to fracture testing, the CEM is also a potential tool to extrapolate laboratory test results to full-scale while considering the size effect. A numerical CEM-based model is built to compute the FDPZ size for an edge crack in a finite square plate of different lengths spanning several magnitudes. It is validated against existing analytical solutions. After successful validation, the FDPZ size of finite plates is calculated with the same numerical scheme. The (FDPZ) size for finite plates is influenced by the cracked plate size and physical crack length. Maximum cohesive zone sizes are given for rectangular and linear softening. Further, for this setup, the CEM-based numerical model captures the size effect and can be used to extrapolate small-scale test results to full-scale.
    Publicationtype: Journal Article
    Scopus© Citations 8  158  225