Suitability of Mechanics-Based and Optimized Machine Learning-Based Models in the Shear Strength Prediction of Slender Beams Without Stirrups

Accurate shear capacity estimation for reinforced concrete (RC) beams without stirrups is essential for reliable structural design. Traditional code-based methods, primarily empirical, exhibit variability in predicting shear strength for these beams. This paper assesses the effectiveness of mechanic...

Full description

Saved in:
Bibliographic Details
Main Authors: Abayomi B. David, Oladimeji B. Olalusi, Paul O. Awoyera, Lenganji Simwanda
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Buildings
Subjects:
Online Access:https://www.mdpi.com/2075-5309/14/12/3946
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850241229786185728
author Abayomi B. David
Oladimeji B. Olalusi
Paul O. Awoyera
Lenganji Simwanda
author_facet Abayomi B. David
Oladimeji B. Olalusi
Paul O. Awoyera
Lenganji Simwanda
author_sort Abayomi B. David
collection DOAJ
description Accurate shear capacity estimation for reinforced concrete (RC) beams without stirrups is essential for reliable structural design. Traditional code-based methods, primarily empirical, exhibit variability in predicting shear strength for these beams. This paper assesses the effectiveness of mechanics-based and optimized machine learning (ML) models for predicting shear strength in stirrup-less, slender beams using a dataset of 784 tests. Seven ML models—artificial neural network (ANN), support vector machine (SVM), decision tree (DT), random forest (RF), AdaBoost, gradient boosting (GBR), and extreme gradient boosting (XGB)—were compared against three mechanics-based models: the Tran’s NLT Model (2020), the Multi-Action Shear Model (MASM), and the Compression Chord Capacity Model (CCC). Among the ML models, XGB and GBR demonstrated the highest predictive accuracy, with coefficients of determination (R<sup>2</sup>) of 0.974 and 0.966, respectively, indicating strong correlation with experimental data. Performance metrics such as mean absolute error (MAE) and root mean squared error (RMSE) showed that XGB and GBR consistently outperformed other models, yielding lower error margins. Statistical analysis revealed minimal bias and variability in the predictions of XGB and GBR, with a coefficient of variation (CoV) of 14%, ensuring high reliability. The NLT model, the most accurate of the mechanical-based models, achieved a mean of 1.02 and a CoV of 16% for its model error, demonstrating reasonable prediction reliability but falling behind XGB and GBR in accuracy. With Shapley additive explanations (SHAPs), the beam width and depth were identified as primary predictors of shear strength, providing critical insights for enhancing design and construction practises.
format Article
id doaj-art-fb2d3afa60fa4e0fa12c6312be8f6170
institution OA Journals
issn 2075-5309
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Buildings
spelling doaj-art-fb2d3afa60fa4e0fa12c6312be8f61702025-08-20T02:00:39ZengMDPI AGBuildings2075-53092024-12-011412394610.3390/buildings14123946Suitability of Mechanics-Based and Optimized Machine Learning-Based Models in the Shear Strength Prediction of Slender Beams Without StirrupsAbayomi B. David0Oladimeji B. Olalusi1Paul O. Awoyera2Lenganji Simwanda3Department of Civil Engineering, Stellenbosch University, Matieland 7602, South AfricaDepartment of Civil Engineering, Durban University of Technology, Pietermaritzburg 3209, South AfricaDepartment of Civil Engineering, Prince Mohammad Bin Fahd University, Al Khobar 31952, Saudi ArabiaDepartment of Structural Reliability, Klokner Institute, Czech Technical University in Prague, 160 00 Prague, Czech RepublicAccurate shear capacity estimation for reinforced concrete (RC) beams without stirrups is essential for reliable structural design. Traditional code-based methods, primarily empirical, exhibit variability in predicting shear strength for these beams. This paper assesses the effectiveness of mechanics-based and optimized machine learning (ML) models for predicting shear strength in stirrup-less, slender beams using a dataset of 784 tests. Seven ML models—artificial neural network (ANN), support vector machine (SVM), decision tree (DT), random forest (RF), AdaBoost, gradient boosting (GBR), and extreme gradient boosting (XGB)—were compared against three mechanics-based models: the Tran’s NLT Model (2020), the Multi-Action Shear Model (MASM), and the Compression Chord Capacity Model (CCC). Among the ML models, XGB and GBR demonstrated the highest predictive accuracy, with coefficients of determination (R<sup>2</sup>) of 0.974 and 0.966, respectively, indicating strong correlation with experimental data. Performance metrics such as mean absolute error (MAE) and root mean squared error (RMSE) showed that XGB and GBR consistently outperformed other models, yielding lower error margins. Statistical analysis revealed minimal bias and variability in the predictions of XGB and GBR, with a coefficient of variation (CoV) of 14%, ensuring high reliability. The NLT model, the most accurate of the mechanical-based models, achieved a mean of 1.02 and a CoV of 16% for its model error, demonstrating reasonable prediction reliability but falling behind XGB and GBR in accuracy. With Shapley additive explanations (SHAPs), the beam width and depth were identified as primary predictors of shear strength, providing critical insights for enhancing design and construction practises.https://www.mdpi.com/2075-5309/14/12/3946beamsshear strengthmachine learningmodel uncertaintyShapley additive explanation methodXGBoost algorithm
spellingShingle Abayomi B. David
Oladimeji B. Olalusi
Paul O. Awoyera
Lenganji Simwanda
Suitability of Mechanics-Based and Optimized Machine Learning-Based Models in the Shear Strength Prediction of Slender Beams Without Stirrups
Buildings
beams
shear strength
machine learning
model uncertainty
Shapley additive explanation method
XGBoost algorithm
title Suitability of Mechanics-Based and Optimized Machine Learning-Based Models in the Shear Strength Prediction of Slender Beams Without Stirrups
title_full Suitability of Mechanics-Based and Optimized Machine Learning-Based Models in the Shear Strength Prediction of Slender Beams Without Stirrups
title_fullStr Suitability of Mechanics-Based and Optimized Machine Learning-Based Models in the Shear Strength Prediction of Slender Beams Without Stirrups
title_full_unstemmed Suitability of Mechanics-Based and Optimized Machine Learning-Based Models in the Shear Strength Prediction of Slender Beams Without Stirrups
title_short Suitability of Mechanics-Based and Optimized Machine Learning-Based Models in the Shear Strength Prediction of Slender Beams Without Stirrups
title_sort suitability of mechanics based and optimized machine learning based models in the shear strength prediction of slender beams without stirrups
topic beams
shear strength
machine learning
model uncertainty
Shapley additive explanation method
XGBoost algorithm
url https://www.mdpi.com/2075-5309/14/12/3946
work_keys_str_mv AT abayomibdavid suitabilityofmechanicsbasedandoptimizedmachinelearningbasedmodelsintheshearstrengthpredictionofslenderbeamswithoutstirrups
AT oladimejibolalusi suitabilityofmechanicsbasedandoptimizedmachinelearningbasedmodelsintheshearstrengthpredictionofslenderbeamswithoutstirrups
AT pauloawoyera suitabilityofmechanicsbasedandoptimizedmachinelearningbasedmodelsintheshearstrengthpredictionofslenderbeamswithoutstirrups
AT lenganjisimwanda suitabilityofmechanicsbasedandoptimizedmachinelearningbasedmodelsintheshearstrengthpredictionofslenderbeamswithoutstirrups