PSI - Issue 75

Available online at www.sciencedirect.com Structural Integrity Procedia (2025) 000–000 Available online at www.sciencedirect.com ScienceDirect Structural Integrity Procedia (2025) 000–000 Available online at www.sciencedirect.com ScienceDirect

www.elsevier.com/locate/procedia www.elsevier.com/locate/procedia

ScienceDirect

Procedia Structural Integrity 75 (2025) 519–529

© 2025 The Authors. Published by ELSEVIER B.V. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0) Peer-review under the responsibility of Dr Fabien Lefebvre with at least 2 reviewers per paper © 2025 The Authors. Published by ELSEVIER B.V. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0) Peer-review under responsibility of the scientific committee of the Fatigue Design 2025 organizers Keywords: Welded components, Fatigue, Master S-N curve, Machine learning. Given the large number of welds in the vehicle industry and the time-consuming process of weld fatigue assessment, automating the evaluation process is essential for improving efficiency and accuracy. In this study, the master S-N curve method is combined with machine learning techniques to create an automated weld evaluation process in commercial finite element software for use with low-density shell meshes in post-processing of welded components. The results were compared with those obtained using the effective notch stress method across several case studies. The methodology developed in the current study proves to be effective for the automatic post-processing of large finite element models and contributes to reducing manual effort in the FE pre-and post processing, which eventually results in an effective stress evaluation of welded details subjected to fatigue loading. © 2025 The Authors. Published by ELSEVIER B.V. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0) Peer-review under responsibility of the scientific committee of the Fatigue Design 2025 organizers Keywords: Welded components, Fatigue, Master S-N curve, Machine learning. Fatigue Design 2025 (FatDes 2025) Automated implementation of structural stress evaluation for weld fatigue assessment in industrial applications Carl-Fredrik Lind a,b , Mehdi Ghanadi a , Baktash Zargari Samani b , Joonas Köll b , Zuheir Barsoum a * a KTH Royal Institute of Technology, Department of Engineering Mechanics, Division of Material and Structural Mechanics, SE-100 44 Stockholm, Sweden b Strength and durability Analysis, KNRTA, 106 PAV-02, Scania CV AB, SE 151 48 Södertälje, Sweden Given the large number of welds in the vehicle industry and the time-consuming process of weld fatigue assessment, automating the evaluation process is essential for improving efficiency and accuracy. In this study, the master S-N curve method is combined with machine learning techniques to create an automated weld evaluation process in commercial finite element software for use with low-density shell meshes in post-processing of welded components. The results were compared with those obtained using the effective notch stress method across several case studies. The methodology developed in the current study proves to be effective for the automatic post-processing of large finite element models and contributes to reducing manual effort in the FE pre-and post processing, which eventually results in an effective stress evaluation of welded details subjected to fatigue loading. Fatigue Design 2025 (FatDes 2025) Automated implementation of structural stress evaluation for weld fatigue assessment in industrial applications Carl-Fredrik Lind a,b , Mehdi Ghanadi a , Baktash Zargari Samani b , Joonas Köll b , Zuheir Barsoum a * a KTH Royal Institute of Technology, Department of Engineering Mechanics, Division of Material and Structural Mechanics, SE-100 44 Stockholm, Sweden b Strength and durability Analysis, KNRTA, 106 PAV-02, Scania CV AB, SE 151 48 Södertälje, Sweden Abstract Abstract

* Corresponding author. Tel.: +46-70-2304342 E-mail address: zuheir@kth.se * Corresponding author. Tel.: +46-70-2304342 E-mail address: zuheir@kth.se

2452-3216 © 2025 The Authors. Published by ELSEVIER B.V. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0) Peer-review under responsibility of the scientific committee of the Fatigue Design 2025 organizers 2452-3216 © 2025 The Authors. Published by ELSEVIER B.V. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0) Peer-review under responsibility of the scientific committee of the Fatigue Design 2025 organizers

2452-3216 © 2025 The Authors. Published by ELSEVIER B.V. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0) Peer-review under the responsibility of Dr Fabien Lefebvre with at least 2 reviewers per paper 10.1016/j.prostr.2025.11.052