Intelligent Data Driven Ensemble Approaches for Bending Strength Prediction of Ultra-High Performance Concrete Beams

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21610%2F25%3A00384999" target="_blank" >RIV/68407700:21610/25:00384999 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.53941/bci.2025.100003" target="_blank" >https://doi.org/10.53941/bci.2025.100003</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.53941/bci.2025.100003" target="_blank" >10.53941/bci.2025.100003</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Intelligent Data Driven Ensemble Approaches for Bending Strength Prediction of Ultra-High Performance Concrete Beams

Popis výsledku v původním jazyce

Existing code equations for predicting the bending capacity of ultra high performance fiber reinforced concrete (UHPFRC) beams often show large scatter, with coefficients of variation (CoV) exceeding 30 to 60 %, leading to both overly conservative and unconservative estimates. This study develops a novel and explainable machine learning (ML) framework for accurate bending capacity prediction, representing the first systematic benchmarking of advanced ensemble ML methods against international and national design codes. An updated database of 264 experimental UHPFRC beam tests was compiled from the literature and partitioned into training (70%), validation (15%), and testing (15%) subsets. Six ensemble algorithms were optimized using Bayesian hyperparameter tuning with 10 fold cross validation, namely Random Forest (RF), Gradient Boosting Machine (GBM), Light Gradient Boosting Machine (LightGBM), Adaptive Boosting (AdaBoost), Categorical Boosting (CatBoost), and Extreme Gradient Boosting (XGBoost). The best performing models, CatBoost and XGBoost, achieved excellent predictive accuracy on unseen test data (R2 ~ 0.96 to 0.97, RMSE ~ 15 to 18 kN.m, CoV ~ 10%) with essentially no systematic bias. These results clearly outperform code equations (R2 ~ 0.60–0.70, CoV ~ 28–64%, and biases up to 40 %). Interpretability analysis using Shapley Additive Explanations (SHAP) confirmed that effective depth and reinforcement ratio are the dominant predictors of bending strength, followed by steel yield strength and section properties, while UHPC compressive strength and fiber parameters had relatively minor influence within the dataset range. The novelty of this study lies in presenting an integrated and interpretable ML framework that not only achieves superior predictive performance but also provides mechanistic insight into UHPFRC beam behavior. The proposed approach offers a reliable data driven complement to current design codes and has potential for practical adoption in structural engineering design and code development.

Název v anglickém jazyce

Intelligent Data Driven Ensemble Approaches for Bending Strength Prediction of Ultra-High Performance Concrete Beams

Popis výsledku anglicky

Existing code equations for predicting the bending capacity of ultra high performance fiber reinforced concrete (UHPFRC) beams often show large scatter, with coefficients of variation (CoV) exceeding 30 to 60 %, leading to both overly conservative and unconservative estimates. This study develops a novel and explainable machine learning (ML) framework for accurate bending capacity prediction, representing the first systematic benchmarking of advanced ensemble ML methods against international and national design codes. An updated database of 264 experimental UHPFRC beam tests was compiled from the literature and partitioned into training (70%), validation (15%), and testing (15%) subsets. Six ensemble algorithms were optimized using Bayesian hyperparameter tuning with 10 fold cross validation, namely Random Forest (RF), Gradient Boosting Machine (GBM), Light Gradient Boosting Machine (LightGBM), Adaptive Boosting (AdaBoost), Categorical Boosting (CatBoost), and Extreme Gradient Boosting (XGBoost). The best performing models, CatBoost and XGBoost, achieved excellent predictive accuracy on unseen test data (R2 ~ 0.96 to 0.97, RMSE ~ 15 to 18 kN.m, CoV ~ 10%) with essentially no systematic bias. These results clearly outperform code equations (R2 ~ 0.60–0.70, CoV ~ 28–64%, and biases up to 40 %). Interpretability analysis using Shapley Additive Explanations (SHAP) confirmed that effective depth and reinforcement ratio are the dominant predictors of bending strength, followed by steel yield strength and section properties, while UHPC compressive strength and fiber parameters had relatively minor influence within the dataset range. The novelty of this study lies in presenting an integrated and interpretable ML framework that not only achieves superior predictive performance but also provides mechanistic insight into UHPFRC beam behavior. The proposed approach offers a reliable data driven complement to current design codes and has potential for practical adoption in structural engineering design and code development.

Druh

J_ost - Ostatní články v recenzovaných periodicích

CEP obor

—

OECD FORD obor

20102 - Construction engineering, Municipal and structural engineering

Projekt

<a href="/cs/project/GA24-10892S" target="_blank" >GA24-10892S: Strojové učení pro víceúrovňové modelování prostorové variability a trhlin pro zajištění udržitelnosti betonových konstrukcí</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Bulletin of Computational Intelligence

ISSN

3083-4643

e-ISSN

3083-4643

Svazek periodika

1

Číslo periodika v rámci svazku

1

Stát vydavatele periodika

AU - Austrálie

Počet stran výsledku

22

Strana od-do

31-52

Kód UT WoS článku

—

EID výsledku v databázi Scopus

—