Glass fibre concrete - Experimental investigation and predictive modeling using advanced machine learning with an interactive online interface

Aug 5, 2026

Upload by Miles

This study investigates the mechanical properties of glass fibre concrete (GFC) through experimental and predictive analysis using advanced machine learning (ML) techniques. Experimental tests quantify GFC mechanical and durability characteristics, and the resulting data are merged with literature data to train ML models. The dataset includes 108 compressive strength and 87 split tensile strength samples spanning fly ash, cement, aggregates, water, fibre content, additives, and fibre dimensions. Optuna hyperparameter optimization and 5-fold cross-validation guide model selection, with GTBR achieving the best predictive accuracy. SHAP analysis clarifies feature contributions, and a user-friendly online interface enables property prediction via the trained model within the dataset range.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages22

Reading Time55 min

AccessFree to download

Introduction

Background and Motivation

Experimental Investigation

Data Integration and Feature Set

Advanced Machine Learning Modeling

Hyperparameter Optimization

Model Selection and Cross-Validation

Explainability with SHAP

Predictive Online Interface

UWL REPOSITORY [repository.uwl.ac.uk](repository.uwl.ac.uk) Glass fibre concrete: experimental investigation and predictive modeling using advanced machine learning with an interactive online interface Mohamed, Rabie and Shaaban, Ibrahim ORCID: [https://orcid.org/0000-0003-4051-341X](https://orcid.org/0000-0003-4051-341X) (2025) Glass fibre concrete: experimental investigation and predictive modeling using advanced machine learning with an interactive online interface. Construction and Building Materials, 472. pp. 1-21. ISSN 0950-0618 [https://doi.org/10.1016/j.conbuildmat.2025.140951](https://doi.org/10.1016/j.conbuildmat.2025.140951)[ ](https://doi.org/10.1016/j.conbuildmat.2025.140951)[This is the Published Version of the final output.](This is the Published Version of the final output.) UWL repository link: [https://repository.uwl.ac.uk/id/eprint/13492/](https://repository.uwl.ac.uk/id/eprint/13492/) Alternative formats: If you require this document in an alternative format, please contact: [open.research@uwl.ac.uk](open.research@uwl.ac.uk) Copyright: Creative Commons: Attribution 4.0 Copyright and moral rights for the publications made accessible in the public portal are retained by the authors and/or other copyright owners and it is a condition of accessing publications that users recognise and abide by the legal requirements associated with these rights. Take down policy: If you believe that this document breaches copyright, please contact us at [open.research@uwl.ac.uk](open.research@uwl.ac.uk) providing details, and we will remove access to the work immediately and investigate your claim. Construction and Building Materials 472 (2025) 140951 Contents lists available at ScienceDirect Construction and Building Materials journal [homepage:](homepage: www.elsevier.com/locate/conbuildmat)[ www.elsevier.com/locate/conbuildmat](homepage: www.elsevier.com/locate/conbuildmat) | Glass fibre concrete: Experimental investigation and predictive modeling using advanced machine learning with an interactive online interface
Mohamed Rabie * , Ibrahim G. Shaaban
School of Computing and Engineering, University of West London, St Mary’s Road, Ealing, London W5 5RF, UK | | | | | --- | --- | --- | --- | | A R T I C L E I N F O | | A B S T R A C T | | | Keywords:
Glass fibre concrete Machine learning Hyperparameter optimization Compressive strength
Split tensile strength Durability
Online user-friendly interface | | This study investigates the mechanical properties of glass fibre concrete (GFC) through experimental and predictive analysis using advanced machine learning (ML) techniques. The experimental work focuses on the mechanical and durability characteristics of GFC. The data obtained in the experimental testing were added to the dataset collected from the literature for the application of machine learning algorithms. The dataset contains 108 compressive strength and 87 split tensile strength data points that evaluated vital factors, including fly ash, cement, aggregates, water, fibre content, superplasticizer, fibre length, fibre diameter, and micro-silica. Optuna, a state-of-the-art hyperparameter optimization library utilizing deep learning, was employed to determine the optimal hyperparameters for each model. The best hyperparameters were selected based on the highest average performance from 5-fold cross-validation. Experimental results showed significant influences of fibre content on GFC mechanical and durability characteristics. The Gradient Tree Boosting Regression (GTBR) model was identified as the optimal model for predicting the compressive and split tensile strength of GFC. The model demonstrated high predictive accuracy for both compressive and split tensile strengths, with R2 values of 0.968 and 0.954, respectively. Shapley Additive exPlanations (SHAP) analysis emphasized the significant impact of fine aggregate, cement, and the amount of glass fibre on both compressive

FAQs

What mechanical properties of glass fibre concrete does the study focus on predicting?

The study predicts compressive strength and split tensile strength of glass fibre concrete using machine learning models.

How is hyperparameter optimization performed in the proposed workflow?

Optuna is used to find the optimal hyperparameters for each model, and the best settings are selected based on the highest average performance from 5-fold cross-validation.

Which machine learning model provides the best prediction results and what supports this choice?

Gradient Tree Boosting Regression (GTBR) is identified as optimal, showing high predictive accuracy with R² values of 0.968 for compressive strength and 0.954 for split tensile strength.

Aug 5, 2026

Upload by Miles