Machine learning-driven web-post buckling resistance prediction for high-strength steel beams with elliptically-based web openings

Aug 5, 2026

Periodical elliptically-based web (EBW) openings in high strength steel (HSS) beams are increasingly adopted to leverage high strength-to-weight ratios and reduced floor height by enabling utility services through web openings. These beams remain vulnerable to web-post buckling (WPB), requiring accurate prediction of WPB buckling capacity and verification of analytical design models. A validated finite element dataset of 10,764 web-post models is used to train and test ANN, SVR, and GEP, and to propose new ML-based design models compared against numerical and existing analytical methods.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages55

Reading Time2 h 19 min

AccessFree to download

Abstract

Keywords

Introduction

City Research Online City, University of London Institutional Repository Citation: Rabi, M. , Jweihan, Y. S. , Abarkan, I. , Ferreira, F. P. V. , Shamass, R. , Limbachiya, V. , Tsavdaridis, K. D. & Pinho Santos, L. F. (2024) . Machine learning-driven web-post buckling resistance prediction for high-strength steel beams with elliptically-based web openings. Results in Engineering, 101749. doi: 10. 1016/j. rineng.2024.101749 This is the accepted version of the paper. This version of the publication may differ from the final published version. Permanent repository link: [https://openaccess.city.ac.uk/id/eprint/31981/](https://openaccess.city.ac.uk/id/eprint/31981/) Link to published version: [https://doi.org/10.1016/j.rineng.2024.101749](https://doi.org/10.1016/j.rineng.2024.101749) [Copyright:](Copyright: City Research Online aims to make research outputs of City)[ City Research Online aims to make research outputs of City](Copyright: City Research Online aims to make research outputs of City), University of London available to a wider audience. Copyright and Moral Rights remain with the author(s) and/or copyright holders. URLs from City Research Online may be freely distributed and linked to. Reuse: Copies of full items can be used for personal research or study, educational, or not-for-profit purposes without prior permission or charge. Provided that the authors, title and full bibliographic details are credited, a hyperlink and/or URL is given for the original metadata page and the content isnot changed in any way. | City Research Online: | [http://openaccess.city.ac.uk/](http://openaccess.city.ac.uk/) | [publications@city.ac.uk](publications@city.ac.uk) | | --- | --- | --- | | | | | 1 Machine Learning-Driven Web-Post 2 Buckling Resistance Prediction for High- 3 Strength Steel Beams with elliptically-based 4 web openings 5 6 Musab Rabi a, Yazeed S. Jweihan b, Ikram Abarkan c, Felipe Piana Vendramell Ferreirad, 7 Rabee Shamass e, Vireen Limbachiya f, Konstantinos Daniel Tsavdaridis g, Luis 8 Fernando Pinho Santos f 9 a Dept of Civil Engineering, Jerash University, Jerash, Jordan, 26150. 10 b Civil and Environmental Engineering Department, College of Engineering, Mutah University, 11 Mutah, Karak, Jordan, 61710, P.O. BOX 7 12 c Department of Physics, Faculty of Sciences, Abdelmalek Essaâdi University, 93002 13 Tetouan, Morocco 14 d Faculty of Civil Engineering, Federal University of Uberlândia,–Campus Santa Mônica, 15 Uberlândia, Minas Gerais, Brazil 16 e Department of Civil and Environmental Engineering, Brunel University London, 17 London, UK 18 f Division of Civil and Building Services Engineering, School of Build Environment and 19 Architecture, London South Bank University, UK 20 g Department of Engineering, School of Science and Technology, City, University of 21 London, Northampton Square, EC1V 0HB, London, UK 22 23 24 Abstract 25 The use of periodical elliptically-based web (EBW) openings in high strength 26 steel (HSS) beams has been increasingly popular in recent years mainly because of 27 the high strength-to-weight ratio and the reduction in the floor height as a result of 28 allowing different utility services to pass through the web openings. However, these 29 sections are susceptible to web-post buckling (WPB) failure mode and therefore it is 30 imperative that an accurate design tool is made available for prediction of the web- 31 post buckling capacity. Therefore, the present paper aims to implement the power of 32 various machine learning (ML) methods for prediction of the WPB capacity in HSS 33 beams with (EBW) openings and to assess the performance of existing analytical 34 design model. For this purpose, a numerical model is developed and validated with 35 the aim of conducting a total of 10764 web-post finite element models, considering 36 S460, S690 and S960 steel grades. This data is employed to train and validate 37 diffe

FAQs

Why are periodical elliptically-based web openings used in high-strength steel beams?

They help achieve high strength-to-weight ratios and reduce floor height by allowing different utility services to pass through the openings.

What problem does the study focus on?

The paper addresses web-post buckling (WPB) failure mode and the need for accurate prediction of WPB capacity.

Which machine learning methods are used for WPB resistance prediction?

The study trains and validates ANN, support vector machine regression (SVR), and gene expression programming (GEP) using a large finite element dataset.

Aug 5, 2026

Upload by Ava Thompson