Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Artificial Neural Networks (ANN) Based Compressive Strength Prediction of AFRP Strengthened Steel Tube
The use of FRP composites as external confinement has recently become a very important system to consider when reinforcing concrete and steel structures. Many constitutive models have been proposed to design such structures. However, the emergence of artificial neural network offers a better alternative with a strong prediction capability. In this research, an artificial neural network (ANN) based model is used to estimate the compressive strength, maximum stresses and strains of AFRP strengthened circular hollow section steel tubes under axial compression. A database of 129 cases of finite element model (FEM) was analyzed using ANSYS Workbench 19.0 and ACP Tool. The FEM was validated with a previously done experimental test. Different geometric criteria have been taken into account to better address the complexity of the problem. Using this FEM database, ANNs have been trained using two approaches. The first approach was using the neural network toolbox in MATLAB. The second approach was using a built-in neural network tool in ANSYS Workbench. The successfully trained ANN is further used to predict the new cases, as an alternative to FE Analysis. Following, a parametric study and a sensitivity analysis were also carried out to investigate the effect of different parameters on the load capacity. The predicted results of the ANN models show a good correlation with the experimental and FEM results. Moreover, comparative analysis of performance result reveals that the ANSYS-ANN had better accuracy in terms of mean squared error and regression value (R2) compared to MATLAB-ANN. The ANN is quite an efficient tool in determining the strength of the AFRP strengthening steel tubes. Such a technique can be used to reduce computation time and labor.
Artificial Neural Networks (ANN) Based Compressive Strength Prediction of AFRP Strengthened Steel Tube
The use of FRP composites as external confinement has recently become a very important system to consider when reinforcing concrete and steel structures. Many constitutive models have been proposed to design such structures. However, the emergence of artificial neural network offers a better alternative with a strong prediction capability. In this research, an artificial neural network (ANN) based model is used to estimate the compressive strength, maximum stresses and strains of AFRP strengthened circular hollow section steel tubes under axial compression. A database of 129 cases of finite element model (FEM) was analyzed using ANSYS Workbench 19.0 and ACP Tool. The FEM was validated with a previously done experimental test. Different geometric criteria have been taken into account to better address the complexity of the problem. Using this FEM database, ANNs have been trained using two approaches. The first approach was using the neural network toolbox in MATLAB. The second approach was using a built-in neural network tool in ANSYS Workbench. The successfully trained ANN is further used to predict the new cases, as an alternative to FE Analysis. Following, a parametric study and a sensitivity analysis were also carried out to investigate the effect of different parameters on the load capacity. The predicted results of the ANN models show a good correlation with the experimental and FEM results. Moreover, comparative analysis of performance result reveals that the ANSYS-ANN had better accuracy in terms of mean squared error and regression value (R2) compared to MATLAB-ANN. The ANN is quite an efficient tool in determining the strength of the AFRP strengthening steel tubes. Such a technique can be used to reduce computation time and labor.
Artificial Neural Networks (ANN) Based Compressive Strength Prediction of AFRP Strengthened Steel Tube
Int J Steel Struct
Djerrad, Abderrahim (Autor:in) / Fan, Feng (Autor:in) / Zhi, Xu-dong (Autor:in) / Wu, Qi-jian (Autor:in)
International Journal of Steel Structures ; 20 ; 156-174
01.02.2020
19 pages
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
Failure behavior of flexural strengthened RC beams with AFRP sheet
| British Library Conference Proceedings | 2001
Compressive performance of AFRP reinforced laminated bamboo stub columns
| Springer Verlag | 2021
Axial Compressive Behavior of High- and Ultra High-Strength Concrete-Filled AFRP Tubes
| British Library Conference Proceedings | 2013
Masonry compressive strength prediction using artificial neural networks
| BASE | 2019