A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Shear Strength of Reinforced Concrete Tapered Beams by Using Systematic Multiscale Models and Artificial Neural Network
https://orcid.org/http://orcid.org/0000-0002-2421-3604
Tapered members are considered important members in structural applications. A thorough understanding of the shear behavior of these complicated geometrical elements is required for accurate design estimation. In this study, four proposed models were incorporated, including linear regression, nonlinear regression, and multi-logistic model, which are three different statistical models. Artificial neural networks have also been developed for predicting the concrete shear strength of reinforced concrete haunched beams. In this regard, all experimental shear strength data about 71 beams for one of the typical modes of tapered beams, characterized by those elements that decreased applied moments along with decreased section depth, were gathered and studied over 100 years. In the modeling process, eight important variables were used as input key parameters, including span length, average effective depth, beam width, the horizontal length of the tapered part, shear span length, concrete compressive strength, area of longitudinal steel reinforcement, and compression chord inclination angle. Then, six major statistical features such as the ratio of estimated value to tested value μ, coefficient of determination R2, mean absolute error MAE, root mean squared error RMSE, scatter index SI, and Mean absolute percentage error MAPE were employed to evaluate the proposed models. The results showed that the multi-logistic model and artificial neural network ANN model perform well in forecasting the shear strength of tapered beams. Furthermore, the shear span length is a vital and sensitive parameter in statistical models, whereas the average effective depth of the beams is a sensitive parameter in ANN models after performing sensitivity analysis.
Shear Strength of Reinforced Concrete Tapered Beams by Using Systematic Multiscale Models and Artificial Neural Network
https://orcid.org/http://orcid.org/0000-0002-2421-3604
Tapered members are considered important members in structural applications. A thorough understanding of the shear behavior of these complicated geometrical elements is required for accurate design estimation. In this study, four proposed models were incorporated, including linear regression, nonlinear regression, and multi-logistic model, which are three different statistical models. Artificial neural networks have also been developed for predicting the concrete shear strength of reinforced concrete haunched beams. In this regard, all experimental shear strength data about 71 beams for one of the typical modes of tapered beams, characterized by those elements that decreased applied moments along with decreased section depth, were gathered and studied over 100 years. In the modeling process, eight important variables were used as input key parameters, including span length, average effective depth, beam width, the horizontal length of the tapered part, shear span length, concrete compressive strength, area of longitudinal steel reinforcement, and compression chord inclination angle. Then, six major statistical features such as the ratio of estimated value to tested value μ, coefficient of determination R2, mean absolute error MAE, root mean squared error RMSE, scatter index SI, and Mean absolute percentage error MAPE were employed to evaluate the proposed models. The results showed that the multi-logistic model and artificial neural network ANN model perform well in forecasting the shear strength of tapered beams. Furthermore, the shear span length is a vital and sensitive parameter in statistical models, whereas the average effective depth of the beams is a sensitive parameter in ANN models after performing sensitivity analysis.
Shear Strength of Reinforced Concrete Tapered Beams by Using Systematic Multiscale Models and Artificial Neural Network
https://orcid.org/http://orcid.org/0000-0002-2421-3604
Tapered members are considered important members in structural applications. A thorough understanding of the shear behavior of these complicated geometrical elements is required for accurate design estimation. In this study, four proposed models were incorporated, including linear regression, nonlinear regression, and multi-logistic model, which are three different statistical models. Artificial neural networks have also been developed for predicting the concrete shear strength of reinforced concrete haunched beams. In this regard, all experimental shear strength data about 71 beams for one of the typical modes of tapered beams, characterized by those elements that decreased applied moments along with decreased section depth, were gathered and studied over 100 years. In the modeling process, eight important variables were used as input key parameters, including span length, average effective depth, beam width, the horizontal length of the tapered part, shear span length, concrete compressive strength, area of longitudinal steel reinforcement, and compression chord inclination angle. Then, six major statistical features such as the ratio of estimated value to tested value μ, coefficient of determination R2, mean absolute error MAE, root mean squared error RMSE, scatter index SI, and Mean absolute percentage error MAPE were employed to evaluate the proposed models. The results showed that the multi-logistic model and artificial neural network ANN model perform well in forecasting the shear strength of tapered beams. Furthermore, the shear span length is a vital and sensitive parameter in statistical models, whereas the average effective depth of the beams is a sensitive parameter in ANN models after performing sensitivity analysis.
Shear Strength of Reinforced Concrete Tapered Beams by Using Systematic Multiscale Models and Artificial Neural Network
Iran J Sci Technol Trans Civ Eng
Hassan, Bedar Rauf (author) / Yousif, Ali Ramadhan (author)
2023-12-01
21 pages
Article (Journal)
Electronic Resource
English
Predicting the shear strength of reinforced concrete beams using artificial neural networks
| Online Contents | 2004
Shear Resistance Prediction of Post-fire Reinforced Concrete Beams Using Artificial Neural Network
| Springer Verlag | 2019
Shear Resistance Prediction of Post-fire Reinforced Concrete Beams Using Artificial Neural Network
| DOAJ | 2019
Reliability of artificial neural networks in predicting shear strength of reinforced concrete beams
| Springer Verlag | 2024
Reliability of artificial neural networks in predicting shear strength of reinforced concrete beams
| Springer Verlag | 2024