PSI - Issue 51

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

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

Procedia Structural Integrity 51 (2023) 62–68

© 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 ICSID 2022 Organizers Abstract Most structural damage occurs in welds, and transient stress analysis corresponding to the welding procedure is performed to investigate the cause. To accurately reproduce the stress generated in the welds, it is necessary to accurately reproduce the transient heat input in the welding procedure. Thus, traditionally, inverse analysis on the transient heat input is conducted by focusing on the molten shape of the actual components; i.e., try and error work performing transient temperature distribution analysis assuming heat input until the molten shape is reproduced. Goldak’s double-ellipsoidal heat source model was used by most of the researchers. In this case, heat source parameters from experience are assumed, and transient temperature distribution analysis is repeated by changing the parameters until the obtained region above the melting point matches the target molten shape. Recently, machine learning methods have been become effective to improve inverse analysis in structural integrity issues to straight-forward analysis. In this work, a model using the deep learning has been developed that can directly determine the parameters of the heat source model from the welding records and the molten shape, which can omit the inverse analysis of the heat source parameters, which has been a bottleneck in the past. This deep learning model can reduce the time required determining parameters used in FEA for failure analysis of welded components. © 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 ICSID 2022 Organizers Keywords: Artificial neural network; failure analysis; inverse analysis; weld residual stress 1. Introduction Most structural damage occurs in welds, and transient stress analysis corresponding to the welding procedure is performed to investigate the cause. In order to accurately reproduce the stress generated in the welds, it is necessary Abstract Most structural damage occurs in welds, and transient stress analysis corresponding to the welding procedure is performed to investigate the cause. To accurately reproduce the stress generated in the welds, it is necessary to accurately reproduce the transient heat input in the welding procedure. Thus, traditionally, inverse analysis on the transient heat input is conducted by focusing on the molten shape of the actual components; i.e., try and error work performing transient temperature distribution analysis assuming heat input until the molten shape is reproduced. Goldak’s double-ellipsoidal heat source model was used by most of the researchers. In this case, heat source parameters from experience are assumed, and transient temperature distribution analysis is repeated by changing the parameters until the obtained region above the melting point matches the target molten shape. Recently, machine learning methods have been become effective to improve inverse analysis in structural integrity issues to straight-forward analysis. In this work, a model using the deep learning has been developed that can directly determine the parameters of the heat source model from the welding records and the molten shape, which can omit the inverse analysis of the heat source parameters, which has been a bottleneck in the past. This deep learning model can reduce the time required determining parameters used in FEA for failure analysis of welded components. © 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 ICSID 2022 Organizers Keywords: Artificial neural network; failure analysis; inverse analysis; weld residual stress 1. Introduction Most structural damage occurs in welds, and transient stress analysis corresponding to the welding procedure is performed to investigate the cause. In order to accurately reproduce the stress generated in the welds, it is necessary 6th International Conference on Structural Integrity and Durability (ICSID 2022) Inverse analysis method of molten shape by deep learning Kenichi Ishihara a, *, Toshiyuki Meshii b 6th International Conference on Structural Integrity and Durability (ICSID 2022) Inverse analysis method of molten shape by deep learning Kenichi Ishihara a, *, Toshiyuki Meshii b a Kobelco Research Institute Inc., 1-5-5 Takatsukadai, Nishi-ku, Kobe-shi, Hyogo, 651-2271, Japan b Faculty of Engineering, University of Fukui, 3-9-1 Bunkyo, Fukui-shi, Fukui, 910-8507, Japan a Kobelco Research Institute Inc., 1-5-5 Takatsukadai, Nishi-ku, Kobe-shi, Hyogo, 651-2271, Japan b Faculty of Engineering, University of Fukui, 3-9-1 Bunkyo, Fukui-shi, Fukui, 910-8507, Japan

* Corresponding author. Tel.: +81-78-992-6059; fax: +81-78-992-5830. E-mail address: ishihara.kenichi@kki.kobelco.com * Corresponding author. Tel.: +81-78-992-6059; fax: +81-78-992-5830. E-mail address: ishihara.kenichi@kki.kobelco.com

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 ICSID 2022 Organizers 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 ICSID 2022 Organizers

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 ICSID 2022 Organizers 10.1016/j.prostr.2023.10.068