Genetic programming-based algorithms application in modeling the compressive strength of steel fiber-reinforced concrete exposed to elevated temperatures

Abstract

Steel-fiber-reinforced concrete (SFRC) has replaced traditional concrete in the construction sector, improving fracture resistance and post-cracking performance. However, extreme temperatures degrade concrete's material characteristics including stiffness and strength. The construction industry increasingly embraces machine learning (ML) to estimate concrete properties and optimize cost and time accurately. This study employs independent ML methods, gene expression programming (GEP), multi-expression programming (MEP), XGBoost, and Bayesian estimation model (BES) to predict SFRC compressive strength (CS) at high temperatures. 307 experimental data points from published studies were utilized to develop the models. The models were trained using 70 % of the dataset, with 15 % for validation and 15 % for testing. Iterative hyperparameter adjustment and trial-and-error refining achieved optimum predictions. All the models were evaluated using correlation (R) values for training, validation, and testing datasets. MEP showed slightly lower R-values of 0.923, 0.904, and 0.949 than GEP, which performed consistently with 0.963, 0.967, and 0.961. XGBoost had the greatest training R-value of 0.997 but dropped in validation (0.918) and testing (0.896). BES model exhibited commendable performance with scores of 0.986, 0.944, and 0.897. GEP and XGBoost exhibited great accuracy, with GEP sustaining constant accuracy across all datasets, highlighting its potency in predicting CS. Interpreting model predictions using SHapley Additive exPlanation (SHAP) highlighted temperature over heating rate. CS improved significantly as the steel fiber volume fraction (Vf) reached 1.5 %, plateauing thereafter. The proposed models are valid and accurate, providing designers and builders with a practical and adaptable method for estimating strength in SFRC structural applications, particularly under high-temperature conditions.

Keywords

• SFRC
• Elevated temperature
• Machine learning
• Compressive strength
• Predictive model