Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Predicting ultimate strength of FRP and lateral steel confined circular concrete columns using Artificial Neural Networks
https://orcid.org/http://orcid.org/0000-0001-6442-5401
In this paper, a new model is proposed to predict the ultimate strength of FRP and conventional reinforced concrete confined by lateral steel bars. Accordingly, circular specimens models are developed and investigated using an Artificial Neural Network (ANN) technique. To study the effect of the various parameters, e.g., the strength of unconfined concrete, the diameter of concrete samples, the height of the samples, tensile strength of FRP and conventional lateral steel, the thickness of FRP layers, the diameter of lateral steel stirrups, the strength of lateral steel stirrups, and modulus of elasticity of FRP and lateral steel stirrups, were selected. The proposed model is trained, validated, and tested based on 49 samples collected from the literature. Moreover, based on the developed ANN model, a set of design-based equations and charts is recommended. In addition to the samples utilized in developing the proposed model, further new samples are selected to evaluate the accuracy of the proposed model. The results from both ANN and user-friendly equations and charts show a good agreement with the test results. Moreover, parametric study is conducted to compare the performance of the proposed model against the experiments and numerical models in the literature. The parametric study shows that the ANN models possess better accuracy and performance to predict the ultimate strength of FRP and conventional steel-reinforced concrete confined specimens, for which the influence of important parameters is considered.
Predicting ultimate strength of FRP and lateral steel confined circular concrete columns using Artificial Neural Networks
https://orcid.org/http://orcid.org/0000-0001-6442-5401
In this paper, a new model is proposed to predict the ultimate strength of FRP and conventional reinforced concrete confined by lateral steel bars. Accordingly, circular specimens models are developed and investigated using an Artificial Neural Network (ANN) technique. To study the effect of the various parameters, e.g., the strength of unconfined concrete, the diameter of concrete samples, the height of the samples, tensile strength of FRP and conventional lateral steel, the thickness of FRP layers, the diameter of lateral steel stirrups, the strength of lateral steel stirrups, and modulus of elasticity of FRP and lateral steel stirrups, were selected. The proposed model is trained, validated, and tested based on 49 samples collected from the literature. Moreover, based on the developed ANN model, a set of design-based equations and charts is recommended. In addition to the samples utilized in developing the proposed model, further new samples are selected to evaluate the accuracy of the proposed model. The results from both ANN and user-friendly equations and charts show a good agreement with the test results. Moreover, parametric study is conducted to compare the performance of the proposed model against the experiments and numerical models in the literature. The parametric study shows that the ANN models possess better accuracy and performance to predict the ultimate strength of FRP and conventional steel-reinforced concrete confined specimens, for which the influence of important parameters is considered.
Predicting ultimate strength of FRP and lateral steel confined circular concrete columns using Artificial Neural Networks
https://orcid.org/http://orcid.org/0000-0001-6442-5401
In this paper, a new model is proposed to predict the ultimate strength of FRP and conventional reinforced concrete confined by lateral steel bars. Accordingly, circular specimens models are developed and investigated using an Artificial Neural Network (ANN) technique. To study the effect of the various parameters, e.g., the strength of unconfined concrete, the diameter of concrete samples, the height of the samples, tensile strength of FRP and conventional lateral steel, the thickness of FRP layers, the diameter of lateral steel stirrups, the strength of lateral steel stirrups, and modulus of elasticity of FRP and lateral steel stirrups, were selected. The proposed model is trained, validated, and tested based on 49 samples collected from the literature. Moreover, based on the developed ANN model, a set of design-based equations and charts is recommended. In addition to the samples utilized in developing the proposed model, further new samples are selected to evaluate the accuracy of the proposed model. The results from both ANN and user-friendly equations and charts show a good agreement with the test results. Moreover, parametric study is conducted to compare the performance of the proposed model against the experiments and numerical models in the literature. The parametric study shows that the ANN models possess better accuracy and performance to predict the ultimate strength of FRP and conventional steel-reinforced concrete confined specimens, for which the influence of important parameters is considered.
Predicting ultimate strength of FRP and lateral steel confined circular concrete columns using Artificial Neural Networks
Asian J Civ Eng
Hamid, Fkrat L. (Autor:in) / Jumaa, Ghazi Bahroz (Autor:in) / Weli, Sardasht S. (Autor:in)
Asian Journal of Civil Engineering ; 22 ; 493-503
01.04.2021
11 pages
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
Behaviour and ultimate strength of steel-tube-confined high strength concrete columns
| British Library Conference Proceedings | 1996
Cyclic lateral response of FRP-confined circular concrete-filled steel tubular columns
| Online Contents | 2016
Cyclic lateral response of FRP-confined circular concrete-filled steel tubular columns
| British Library Online Contents | 2016
Ultimate strength of reinforced concrete circular and rectangular columns
| British Library Conference Proceedings | 2001