Ensemble models predict heat-exposed concrete strength at R² 0.903
Original title: Explainable Machine Learning Analysis of Temperature Effects on Mechanical Strength of Fiber-Reinforced High-Performance Concrete
On 1,204 records, gradient boosting had the lowest error at 6.67 MPa RMSE and was packaged in a Python GUI.
A study predicts compressive strength of fiber-reinforced high-performance concrete after temperature exposure using 1,204 experimental records. Eight machine-learning models were compared; gradient boosting and extreme gradient boosting each reached an R² of 0.903 on unseen data. SHAP and partial dependence analysis rank temperature as the strongest factor, and the best models were placed in a Python interface.
- Gradient boosting RMSE is 6.67 MPa; extreme gradient boosting MAE is 3.97 MPa.
- Extreme gradient boosting mean absolute percentage error is 10.60%.
- Strength falls as temperature rises, depending on the mixture design.
- Authors rank fine aggregate, superplasticizer, cement, water-to-binder ratio, and water after temperature.
From the original article
1 min read at arxiv.orgPredicting the compressive strength of fiber-reinforced high-performance concrete subjected to temperature exposure is challenging because to the intricate interdependencies of mixture composition, fiber properties, curing conditions, and temperature. A data-driven framework to predict compressive strength utilizing 1,204 experimental records containing a diverse array of material designs and exposure situations.
By Jagaran Chakma · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.