Machine learning-driven capacity design and embodied carbon reduction optimization in composite reduced web section (RWS) connections

Rabie, Mohamed; Almutairi, Fahad Falah; Tsavdaridis, Konstantinos Daniel; Shaaban, Ibrahim

Machine learning-driven capacity design and embodied carbon reduction optimization in composite reduced web section (RWS) connections

Lists

Rabie, Mohamed, Almutairi, Fahad Falah, Tsavdaridis, Konstantinos Daniel and Shaaban, Ibrahim ORCID: https://orcid.org/0000-0003-4051-341X (2026) Machine learning-driven capacity design and embodied carbon reduction optimization in composite reduced web section (RWS) connections. Advances in Engineering Software, 217. ISSN 0965-9978

[thumbnail of RabieM ShaabanI _ Machine learning-driven capacity design and embodied carbon reduction optimization in composite_VoR.pdf]

Preview

PDF
RabieM ShaabanI _ Machine learning-driven capacity design and embodied carbon reduction optimization in composite_VoR.pdf - Published Version
Available under License Creative Commons Attribution.
Download (8MB) | Preview

Official URL: https://www.sciencedirect.com/science/article/pii/...

Abstract

A gap in current predictive modelling approaches limits the ability to accurately assess the mechanical, durability performance and sustainability metrics of Reduced Web Section (RWS) connections. This paper addresses this gap by developing an ensemble machine learning (ML) framework combined with multi-objective optimisation, enabling the efficient prediction of seven key mechanical and ductility properties alongside total embodied carbon (EC) reduction. Three ensemble ML models—Extra Trees Regressor (ETR), Gradient Tree Boosting (GTBR), and Extreme Gradient Boosting (XGBoost)—were evaluated, with XGBoost demonstrating superior generalization across most outputs. Additionally, Shapley Additive Explanations (SHAP) analysis was conducted to identify the most influential design parameters, improving model interpretability. The multi-objective optimisation performed using NSGA-II, generated Pareto-optimal solutions, highlighting trade-offs between structural performance and sustainability considerations. The findings reveal that cross-sectional properties, material stiffness, and connection type significantly impact RWS performance, and optimising these parameters can lead to improved ductility, moment capacity, and reduced environmental impact. To enhance practical applicability, a user-friendly interface was developed and deployed via Hugging Face, allowing users to test the results, make predictions and retrieve optimal design parameters based on the nearest Pareto-optimal solutions. The results of this paper demonstrate that ensemble ML methods, coupled with optimisation and explainability tools, provide a robust framework for advancing RWS connection design, ensuring both seismic resilience and sustainability in structural engineering.

Item Type:	Article
Identifier:	10.1016/j.advengsoft.2026.104145
Keywords:	Reduced Web Section (RWS) Connections ; Ensemble machine learning ; Multi-objective optimisation ; Sustainable structural design ; Embodied carbon ;
Subjects:	Construction and engineering
Date Deposited:	05 Nov 2026
Dates:	Date Publication status 2 March 2026 Accepted 7 March 2026 Published Online
School, department or research centre:	School of Computing and Engineering
Keywords:	Reduced Web Section (RWS) Connections ; Ensemble machine learning ; Multi-objective optimisation ; Sustainable structural design ; Embodied carbon ;
URI:	https://repository.uwl.ac.uk/id/eprint/15784