Efficient boosting-based algorithms for shear strength prediction of squat RC walls

Farzinpour, Alireza; Dehcheshmeh, Esmaeil Mohammadi; Broujerdian, Vahid; Esfahani, Samira Nasr; Gandomi, Amir H.

doi:10.1016/j.cscm.2023.e01928

Cited by 8 publications

(7 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An information processing system called an artificial neural network (ANN) was built on an imitation of the brain’s neural network structure and function. It had many advantages compared with the traditional semi-empirical method [ 52 ]. It could be divided into the feedforward network and the feedback network [ 53 ].…”

Section: Resultsmentioning

confidence: 99%

Bond performance between hybrid fiber-reinforced concrete and BFRP bars under freeze-thaw cycle

2024

PLoS ONE

View full text Add to dashboard Cite

This study applied the pull-out test to examine the influence of freeze-thaw cycles and hybrid fiber incorporation on the bond performance between BFRP bars and hybrid fiber-reinforced concrete. The bond-slip curves were fitted by the existing bond-slip constitutive model, and then the bond strength was predicted by a BP neural network. The results indicated that the failure mode changed from pull-out to splitting for the BFRP bar ordinary concrete specimens when the freeze-thaw cycles exceeded 50, while only pull-out failure occurred for all BFRP bar hybrid fiber-reinforced concrete specimens. An increasing trend was shown on the peak slip, but a decreasing trend was shown on the bond stiffness and bond strength when freeze-thaw cycles increased. The bond strength could be increased significantly by the incorporation of basalt fiber (BF) and cellulose fiber (CF) under the same freezing and thawing conditions as compared to concrete specimens without fibers. The Malvar model and the Continuous Curve model performed best in fitting the ascending and descending sections of the bond-slip curves, respectively. The BP neural network also accurately predicted the bond strength, with relative errors of predicted bond strengths ranging from 3.75% to 13.7%, and 86% of them being less than 10%.

show abstract

Section: Resultsmentioning

confidence: 99%

Bond performance between hybrid fiber-reinforced concrete and BFRP bars under freeze-thaw cycle

2024

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…This incident is a result of conclusions made regarding several of the shear failure patterns of low aspect ratio walls. [25]. The coefficient of variation (COV) values for various predicted-totest ratios can be seen in Table 5 along with minimum, maximum, mean, and standard deviation.…”

Section: The Xgboost Model's Prediction Resultsmentioning

confidence: 99%

“…To prevent overfitting, a strategy called column sampling is employed. A research effort from the University of Washington, XGBoost was presented in 2016 at the International Conference on Knowledge Discovery and Data Mining (SIGKDD) Conference [25]. Listed below is a brief description of the essential mathematical concepts that XGBoost uses.…”

Section: The Model For Shear Strength Of Rc Walls Utilizing Xgboostmentioning

confidence: 99%

Study the Efficiency of the XGBoost Algorithm for Squat RC Wall Shear Strength Prediction and Parametric Analysis

H. Sulaiman,

M. Ibrahim,

J. Imran

2024

DJES

View full text Add to dashboard Cite

Squat-reinforced concrete (RC) shear walls with an aspect ratio of less than two are considered effective structural members, where shear is the dominant failure mechanism. Squat shear walls are widely used in nuclear power plants and building construction and feature optimal cost and outstanding performance, due to their lateral strength and high rigidity to resist lateral loads. However, since the accurate evaluation of the shear strength of squat shear walls must meet the design specifications, its calculation may be very complex, challenging, and inaccurate using experimental and theoretical equations due to many influential and overlapping design factors, so it takes more time and higher cost to determine it. This study uses machine learning (ML) methods to build a shear strength prediction efficient model for squat RC walls to address these issues. First, a huge dataset of 1424 RC squat wall test specimens gathered from the literature is utilized for developing an ML model, by employing XGBoost, to predict the shear strength. Results verified that the XGBoost model had the best accuracy and least error while assessing the squat walls' strength at shear. Moreover, an XGBoost optimum algorithm fared better than the empirical models based on mechanics, with a 99.2% accuracy. Finally, to prove that the model can identify the most important variables that significantly affect the shear strength, parameter and sensitivity analyses were performed and the results showed that the wall length is the factor that contributes most to the ultimate shear strength of the squat shear wall as a percentage (7.62%), followed by the yield strength. For the web as a ratio. (6.88%), concrete strength (6.75%), reinforcement ratio information (6.56%), and geometric properties (6.01%), while the axial load represents the smallest contribution, reaching (4.16%).

show abstract

“…𝑉 𝑗 = 𝑇 𝑏 − 𝑉 𝑐𝑜𝑙 (11) where, 𝑇 𝑏 is the tensile force in the beam longitudinal reinforcement (N), 𝑉 𝑐𝑜𝑙 is the force of the shear in the upper column (N), and 𝑉 𝑗 is the joint shear force (N).…”

Section: 1 Rc Beam-column Joint Modellingmentioning

confidence: 99%

“…In the design and seismic analysis of tall structures, lateral load-resisting systems like RC shear walls are commonly utilized. Accurately predicting the capacity of these systems is a critical aspect of the design process (11). Predicting the capacity becomes complex due to the reinforcement characteristics of concrete and the interactions between flexure and shear.…”

Section: Introductionmentioning

confidence: 99%

Optimal Prediction of Shear Properties in Beam-Column Joints Using Machine Learning Approach

Ramavath,

Suryawanshi

2024

IJE

View full text Add to dashboard Cite

Efficient boosting-based algorithms for shear strength prediction of squat RC walls

Cited by 8 publications

References 43 publications

Bond performance between hybrid fiber-reinforced concrete and BFRP bars under freeze-thaw cycle

Bond performance between hybrid fiber-reinforced concrete and BFRP bars under freeze-thaw cycle

Study the Efficiency of the XGBoost Algorithm for Squat RC Wall Shear Strength Prediction and Parametric Analysis

Optimal Prediction of Shear Properties in Beam-Column Joints Using Machine Learning Approach

Contact Info

Product

Resources

About