Enhancing accuracy in flexural strength prediction of glass fibre-reinforced concrete via TPE-XGB algorithm and explainable machine learning

This study aims to accurately predict the flexural strength (FS) of glass fiber reinforced concrete (GFRC) using advanced machine learning (ML) techniques. A novel algorithm, tree structured parzen estimator based extreme gradient boosting (TPE-XGB), is proposed by integrating Bayesian optimization...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Innovative infrastructure solutions : the official journal of the Soil-Structure Interaction Group in Egypt (SSIGE) Jg. 10; H. 9; S. 416
Hauptverfasser: Khan, Muhammad Abdullah, Ullah, Anas Rahat, Mukhtiar, Danish, Siddique, Muhammad Shahid, Iqbal, Muhammad Hammad, Inqiad, Waleed Bin
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Cham Springer International Publishing 01.09.2025
Springer Nature B.V
Schlagworte:
Accuracy
Algorithms
Concrete technology
Earth and Environmental Science
Earth Sciences
Empirical equations
Environmental Science and Engineering
Flexural strength
Foundations
Gene expression
Geoengineering
Geotechnical Engineering & Applied Earth Sciences
Glass fiber reinforced concretes
Glass fiber reinforced plastics
Glass fibers
Hydraulics
Machine learning
Mathematical models
Reinforced concrete
Technical Paper
Water-cement ratio
Glass fibre reinforced concrete
Multi expression programming
Explainable machine learning
Flexural strength prediction
SHAP analysis
TPE-XGB
Gene expression programming
ISSN:2364-4176, 2364-4184
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:This study aims to accurately predict the flexural strength (FS) of glass fiber reinforced concrete (GFRC) using advanced machine learning (ML) techniques. A novel algorithm, tree structured parzen estimator based extreme gradient boosting (TPE-XGB), is proposed by integrating Bayesian optimization (TPE) for automated hyperparameter tuning with the predictive strength of XGB. In addition to TPE-XGB, other ML algorithms including bagging regressor (BR), gene expression programming (GEP), and multi expression programming (MEP) are also employed for comparison. A comprehensive dataset consisting of 227 experimental instances of GFRC flexural strength was compiled from 33 internationally published studies. The models were trained and evaluated using statistical error metrics, k fold cross validation, scatter plots, and residual analysis. Results showed that all models performed reliably, with TPE-XGB achieving the highest prediction accuracy (testing R 2 value of 0.972). In contrast, GEP and MEP, described as grey box models that produce interpretable mathematical expressions, offered empirical equations for FS prediction which enhanced transparency. To further address the non-transparent nature of black box models like TPE-XGB, explainable machine learning (XML) techniques were applied. These included SHAP (Shapley Additive Explanations), Individual Conditional Expectation (ICE), and Partial Dependence Plots (PDP). The analysis revealed that water to cement ratio, quantities of fine and coarse aggregates, and glass fiber content were the most influential variables affecting the flexural performance of GFRC. Finally, a graphical interface is proposed to demonstrate the practical usability of the developed models. This study contributes both accurate prediction tools and interpretable insights, supporting improved and informed design practices in concrete technology.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2364-4176
2364-4184
DOI:10.1007/s41062-025-02212-6