PSI - Issue 57

Available online at www.sciencedirect.com Structural Integrity Procedia 00 (2022) 000 – 000 Available online at www.sciencedirect.com ScienceDirect

www.elsevier.com/locate/procedia

ScienceDirect

Procedia Structural Integrity 57 (2024) 112–120

© 2024 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 2023 organizers Abstract The surface geometry and the stress concentration of welded joints show a large variation and are individual for each joint at each position. This is one reason for the conservative fatigue assessment of welded joints. In the past the determination of stress concentration factors (SCF) by Finite Element (FE) simulations was based on the approximated surface geometry of the weld, defined by weld toe radius and flank angle or other geometrical parameters. In this work a new approach is presented to directly determine SCFs of welded joints based on the 2D-profile (coordinates) of the weld surfaces. For this, two convolutional neural networks (CNN) PointNet++ and 2DLaserNet for point cloud classification are modified to perform regression on 2D-profiles. As input parameter artificial 2D-profiles were generated. The artificial neural networks (ANN) were trained by using the SCFs determined by Finite Element (FE)-simulations based on the virtual 2D-profiles. Both ANN show a high performance (R2 score) for the determination of SCFs. Comparison of the proposed method with three analytical solutions shows in two cases a higher agreement and in one case a similar agreement. © 2023 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 2023 organizers Keywords: Welded joints, Surface geometry, Stress concentration factor, Artifical neural network, Regression 1. Introduction The weld toe is usually the fatigue critical location of each welded joint (Hobbacher, 2016). Numerous experimental and theoretical studies have shown, that the local weld geometry at the weld toe is directly related to the fatigue life and fatigue strength of the welded joint (Ning Nguyen and Wahab, 1995; Lieurade, Huther and Lefebvre, 2008; Barsoum and Jonsson, 2011; Schork et al. , 2017, 2020; Hultgren and Barsoum, 2020). The reason for this relation is the stress concentration at the weld toe (notch effect). The stress concentration factor (SCF) quantifies the Fatigue Design 2023 (FatDes 2023) Determination of stress concentration factors of welded joints from 3D-surface scans by artificial neural networks Jan Schubnell a *, Oener Aydogan a , Matthias Jung a a Fraunhofer Institut for Mechanics of Materials, Woehlerstr. 11, 79198 Freiburg, Germany

2452-3216 © 2023 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 2023 organizers

2452-3216 © 2024 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 2023 organizers 10.1016/j.prostr.2024.03.014