PSI - Issue 60

ScienceDirect StructuralIntegrity Procedia 00 (2023) 000 – 000 Available online at www.sciencedirect.com Available online at www.sciencedirect.com ScienceDirect StructuralIntegrity Procedia 00 (2023) 000 – 000 Available online at www.sciencedirect.com ScienceDirect

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

Procedia Structural Integrity 60 (2024) 418–432

© 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 ICONS 2023 Organizers © 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 ICONS 2023 Organizers Abstract For various piping components (D/T > 100) vulnerable to an in-plane or out-of-plane moment, finite element analyses are performed. Several bulletins published by The Welding Research Council, Inc. contain extensive data and instructions for calculating local stresses. Large numbers of finite element runs have been carried out in the STP-PT-074 following the suggested modelling techniques in WRC 497, BPVC VIII-Section 2 Annex 5. A, EPRI 110996, and different comparisons between the WRC, FEA, and EPRI conclusions are documented. In addition, the validation comparisons against other correlations, finite element results, and test data, rules for evaluating the local stresses following "ASME BPVC Section VIII - Division 2 - Rules for Construction of Pressure Vessels - Alternative Rules" are provided. The STP-PT-074 data is utilized and expanded upon in this paper using machine language approaches. The research on the dimensional constraints of the D m /T ratios between 7 and 2500, the d m /D m ratios between 0 and 0.7, and the t/T ratios between 0.1 and 10 has been conducted, and the predictions are presented. The predicted values and the outcomes of the finite element analysis are compared. The present study shows that it is possible to use machine learning models to forecast the local stresses in nozzles, shells, and formed heads from external loads, as described in this paper. © 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 ICONS 2023 Organizers Third International Conference on Structural Integrity 2023 (ICONS 2023) Implementation of Machine Learning Method to Quantitatively Evaluate the Local Stresses in Nozzles in Shells and Formed Heads from External Loads Balaji Srinivasan a,b, *, Srinivasan V b Third International Conference on Structural Integrity 2023 (ICONS 2023) Implementation of Machine Learning Method to Quantitatively Evaluate the Local Stresses in Nozzles in Shells and Formed Heads from External Loads Balaji Srinivasan a,b, *, Srinivasan V b a ETD Department, Engineers India Limited, EIL Office Complex, Gurugram – 122001, Haryana, India b Department of Design, Indian Institute of Technology Delhi, New Delhi- 110016, Delhi, India a ETD Department, Engineers India Limited, EIL Office Complex, Gurugram – 122001, Haryana, India b Department of Design, Indian Institute of Technology Delhi, New Delhi- 110016, Delhi, India Abstract For various piping components (D/T > 100) vulnerable to an in-plane or out-of-plane moment, finite element analyses are performed. Several bulletins published by The Welding Research Council, Inc. contain extensive data and instructions for calculating local stresses. Large numbers of finite element runs have been carried out in the STP-PT-074 following the suggested modelling techniques in WRC 497, BPVC VIII-Section 2 Annex 5. A, EPRI 110996, and different comparisons between the WRC, FEA, and EPRI conclusions are documented. In addition, the validation comparisons against other correlations, finite element results, and test data, rules for evaluating the local stresses following "ASME BPVC Section VIII - Division 2 - Rules for Construction of Pressure Vessels - Alternative Rules" are provided. The STP-PT-074 data is utilized and expanded upon in this paper using machine language approaches. The research on the dimensional constraints of the D m /T ratios between 7 and 2500, the d m /D m ratios between 0 and 0.7, and the t/T ratios between 0.1 and 10 has been conducted, and the predictions are presented. The predicted values and the outcomes of the finite element analysis are compared. The present study shows that it is possible to use machine learning models to forecast the local stresses in nozzles, shells, and formed heads from external loads, as described in this paper.

Keywords: Machine Learning; Local Stresses; WRC; Finite element analysis; Regression ; Keywords: Machine Learning; Local Stresses; WRC; Finite element analysis; Regression ;

* Corresponding author. Tel.: +91-124-2891786 E-mail address: balaji.s@eil.co.in * Corresponding author. Tel.: +91-124-2891786 E-mail address: balaji.s@eil.co.in

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 ICONS 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 ICONS 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 ICONS 2023 Organizers 10.1016/j.prostr.2024.05.063