Predicting the Mechanical Properties of Concrete Containing Basalt Fiber Utilizing Optimized Hybrid Machine Learning Modeling

Basalt-fiber-reinforced concrete (BFRC) has attracted increasing attention owing to its potential to enhance concrete performance under different loading conditions. Because of the complex interactions among mixture constituents and fiber characteristics, predicting its mechanical properties can be challenging. Therefore, this study develops six individual machine learning (ML) models and a hybrid ML model based on weighted voting techniques using the six developed learners to predict both the compressive strength (CS) and tensile strength (TS) of BFRC. The individual ML models include K-nearest neighbors (KNN), random forest (RF), extra trees regressor (ETR), extreme gradient boosting (XGBoost), Light GBM (LightGBM), and gradient boosting machine (GBM). The hyperparameter optimization is performed using both particle swarm optimization (PSO) and grey wolf optimizer (GWO). Additionally, a superior hybrid ML model based on the six learners is constructed to improve the prediction accuracy of CS and TS of BFRC. Two datasets with the same mixtures containing 227 samples each were compiled from literature using eight input features: cement (C), coarse aggregate-to-fine aggregate ratio (CAG/FAG), silica fume/cement (SF/C), fly ash/cement (FA/C), water/cement ratio (W/C), superplasticizer/cement (SP/C), basalt fiber length-to-diameter ratio (F_LD), and fiber content (F_%). Analysis reveals that SF/C has the greatest influence on CS predictions, followed by W/C, CAG/FAG, F_%, and C, while TS predictions are mostly influenced by CAG/FAG, W/C, F_LD, and F_%. Finally, a graphical user interface (GUI) is developed for predicting BFRC strengths using the base learners and the hybrid model.

Authors

Institutions

Publication Details

Journal
Buildings
Published
2026-11-16
DOI
https://doi.org/10.3390/buildings16224564
Primary Topic
Innovative concrete reinforcement materials
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Predicting the Mechanical Properties of Concrete Containing Basalt Fiber Utilizing Optimized Hybrid Machine Learning Modeling

Ahmad Mfarreh Alenezi, Hany A. Dahish
7 links
Buildings
Innovative concrete reinforcement materials
article

Predicting the Mechanical Properties of Concrete Containing Basalt Fiber Utilizing Optimized Hybrid Machine Learning Modeling

Ahmad Mfarreh Alenezi, Hany A. Dahish
article en

Abstract

Basalt-fiber-reinforced concrete (BFRC) has attracted increasing attention owing to its potential to enhance concrete performance under different loading conditions. Because of the complex interactions among mixture constituents and fiber characteristics, predicting its mechanical properties can be challenging. Therefore, this study develops six individual machine learning (ML) models and a hybrid ML model based on weighted voting techniques using the six developed learners to predict both the compressive strength (CS) and tensile strength (TS) of BFRC. The individual ML models include K-nearest neighbors (KNN), random forest (RF), extra trees regressor (ETR), extreme gradient boosting (XGBoost), Light GBM (LightGBM), and gradient boosting machine (GBM). The hyperparameter optimization is performed using both particle swarm optimization (PSO) and grey wolf optimizer (GWO). Additionally, a superior hybrid ML model based on the six learners is constructed to improve the prediction accuracy of CS and TS of BFRC. Two datasets with the same mixtures containing 227 samples each were compiled from literature using eight input features: cement (C), coarse aggregate-to-fine aggregate ratio (CAG/FAG), silica fume/cement (SF/C), fly ash/cement (FA/C), water/cement ratio (W/C), superplasticizer/cement (SP/C), basalt fiber length-to-diameter ratio (F_LD), and fiber content (F_%). Analysis reveals that SF/C has the greatest influence on CS predictions, followed by W/C, CAG/FAG, F_%, and C, while TS predictions are mostly influenced by CAG/FAG, W/C, F_LD, and F_%. Finally, a graphical user interface (GUI) is developed for predicting BFRC strengths using the base learners and the hybrid model.

BuildingsVol. 16(22)
Qassim University (SA)
Industry, innovation and infrastructure
Innovative concrete reinforcement materials
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon