Predicting the contribution of recycled aggregate concrete to the shear capacity of beams without transverse reinforcement using artificial neural networks
“…Likewise, the civil engineering construction industry has also adopted such techniques to overcome cumbersome experimental procedures. For instance, some of these approaches include multivariate adaptive regression spline (MARS) [15,16], genetic engineering programming (GEP) [17][18][19][20], support vector machine (SVM) [21,22], artificial neural networks (ANN) [23][24][25], decision tree (DT) [26][27][28], adaptive boost algorithm (ABA), and adaptive neuro-fuzzy interference (ANFIS) [29][30][31][32]. Javed et al [18] predict the axial behavior of a concrete-filled steel tube (CFST) with 227 data points by using gene expression programming.…”
Supervised machine learning and its algorithm is an emerging trend for the prediction of mechanical properties of concrete. This study uses an ensemble random forest (RF) and gene expression programming (GEP) algorithm for the compressive strength prediction of high strength concrete. The parameters include cement content, coarse aggregate to fine aggregate ratio, water, and superplasticizer. Moreover, statistical analyses like MAE, RSE, and RRMSE are used to evaluate the performance of models. The RF ensemble model outbursts in performance as it uses a weak base learner decision tree and gives an adamant determination of coefficient R2 = 0.96 with fewer errors. The GEP algorithm depicts a good response in between actual values and prediction values with an empirical relation. An external statistical check is also applied on RF and GEP models to validate the variables with data points. Artificial neural networks (ANNs) and decision tree (DT) are also used on a given data sample and comparison is made with the aforementioned models. Permutation features using python are done on the variables to give an influential parameter. The machine learning algorithm reveals a strong correlation between targets and predicts with less statistical measures showing the accuracy of the entire model.
“…Likewise, the civil engineering construction industry has also adopted such techniques to overcome cumbersome experimental procedures. For instance, some of these approaches include multivariate adaptive regression spline (MARS) [15,16], genetic engineering programming (GEP) [17][18][19][20], support vector machine (SVM) [21,22], artificial neural networks (ANN) [23][24][25], decision tree (DT) [26][27][28], adaptive boost algorithm (ABA), and adaptive neuro-fuzzy interference (ANFIS) [29][30][31][32]. Javed et al [18] predict the axial behavior of a concrete-filled steel tube (CFST) with 227 data points by using gene expression programming.…”
Supervised machine learning and its algorithm is an emerging trend for the prediction of mechanical properties of concrete. This study uses an ensemble random forest (RF) and gene expression programming (GEP) algorithm for the compressive strength prediction of high strength concrete. The parameters include cement content, coarse aggregate to fine aggregate ratio, water, and superplasticizer. Moreover, statistical analyses like MAE, RSE, and RRMSE are used to evaluate the performance of models. The RF ensemble model outbursts in performance as it uses a weak base learner decision tree and gives an adamant determination of coefficient R2 = 0.96 with fewer errors. The GEP algorithm depicts a good response in between actual values and prediction values with an empirical relation. An external statistical check is also applied on RF and GEP models to validate the variables with data points. Artificial neural networks (ANNs) and decision tree (DT) are also used on a given data sample and comparison is made with the aforementioned models. Permutation features using python are done on the variables to give an influential parameter. The machine learning algorithm reveals a strong correlation between targets and predicts with less statistical measures showing the accuracy of the entire model.
“…The maximum negative and positive errors reported in their study were −6.54% and 51.17%, respectively. Ababneh et al (2020) utilized ANN to predict the shear capacity of the beam without transverse bars, and compared their experimental results with the values predicted by ANN. They employed compressive strength, shear span-depth ratio, replacement ratio, longitudinal reinforcement ratio, effective beam depth, and beam width as input parameters in their model.…”
In the present study, the performance of reinforced concrete tunnel (RCT) under internal water pressure is evaluated by using nonlinear finite element analysis and surrogate models. Several parameters, including the compressive and tensile strength of concrete, the size of the longitudinal reinforcement bar, the transverse bar diameter, and the internal water pressure, are considered as the input variables. Based on the levels of variables, 36 mix designs are selected by the Taguchi method, and 12 mix designs are proposed in this study. Carbon fiber reinforced concrete (CFRC) or glass fiber reinforced concrete (GFRC) is considered for simulating these 12 samples. Principal component regression (PCR), Multi Ln equation regression (MLnER), and gene expression programming (GEP) are employed for predicting the percentage of damaged surfaces (PDS) of the RCT, the effective tensile plastic strain (ETPS), the maximum deflection of the RCT, and the deflection of crown of RCT. The error terms and statistical parameters, including the maximum positive and negative errors, mean absolute percentage error (MAPE), root mean square error (RMSE), coefficient of determination, and normalized square error (NMSE), are utilized to evaluate the accuracy of the models. Based on the results, GEP performs better than other models in predicting the outputs. The results show that the internal water pressure and the mechanical properties of concrete have the most effect on the damage and deflection of the RCT.
“…(3) critical shear crack theory (CSCT). In addition, shear studies in terms of types of concrete include, but are not limited to, lightweight concrete (LC), ultra-high-performance concrete (UHPC), and fiber-reinforced concrete (FRC) have been documented (Deifalla et al, 2020b;Tong et al, 2020;Ababneh et al, 2020;Shaban et al, 2020;Ridha et al, 2018).…”
Section: Introductionmentioning
confidence: 99%
“…Several theories are being used for the analysis of specimens under shear (ASCE-ACI, 1999; Cavagnis et al, 2020; Bentz et al, 2006; Muttoni et al, 1997), namely, (1) modified compression field theory (MCFT); (2) simplified modified compression field theory (SMCFT); and (3) critical shear crack theory (CSCT). In addition, shear studies in terms of types of concrete include, but are not limited to, lightweight concrete (LC), ultra-high-performance concrete (UHPC), and fiber-reinforced concrete (FRC) have been documented (Deifalla et al, 2020b; Tong et al, 2020; Ababneh et al, 2020; Shaban et al, 2020; Ridha et al, 2018). Figure 1.Reinforced concrete under shear loading a) failure cracking pattern and b) resistance mechanism (ASCE, 1999).…”
Lightweight concrete (LC) is a viable alternative for conventional normal weight concrete (NC). It has a reduced weight and similar properties. However, shear provisions design codes are way behind for the case of the LC compared to the NC. This study evaluates the shear design of NC and LC specimens. First, an extensive experimental database of these specimens under shear was compiled. Then, selected shear provisions of design codes were outlined and applied for strength calculations. The calculated strengths were evaluated considering the experimentally measured ones to assess these design codes' overall accuracy and consistency. In addition, the effect of selected parameters (depth, concrete strength, flexure reinforcement ratio, shear span to depth ratio, and nominal maximum aggregate size) on the safety of the design was assessed. The third draft of the Eurocode was the most accurate and consistent for the shear design of LC and NC specimens. Finally, the Eurocode shear provisions draft was adapted, refined, verified, and proposed for the shear design of LC beams and slabs.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
