基于神经网络的钢筋混凝土剪力墙抗剪承载力研究

神经网络(ANN)模型作为土木工程领域中一种有效的方法能够用于解决复杂的问题.基于试验数据采用神经网络对钢筋混凝土剪力墙的抗剪承载力进行预测,收集160个钢筋混凝土剪力墙在低周往复荷载下的试验数据,建立数据库,选取140个试验样本对ANN模型进行训练,20个试验样本进行测试验证.ANN1和ANN2有14个输入参数:混凝...

Study on the shear bearing capacity of RC shear walls using artificial neural networks

In various areas of civil engineering, the artificial neural network (ANN) model is used to solve complex problems. In this study, ANN models were used to predict the shear bearing capacity of RC shear walls. Based on the results of 160 experiments, a database was constructed that included the performance of RC shear walls under cyclic loading. One hundred and forty samples were chosen to train the ANN models, and 20 were used for validation. There were fourteen inputs parameters: concrete compressive strength, aspect ratio, axial compression ratio, vertical bar yield strength, horizontal bar yield strength, web vertical reinforcement ratio, web horizontal reinforcement ratio, boundary region vertical reinforcement ratio, boundary region horizontal reinforcement ratio, sectional area ratio, sectional height thickness ratio, total section area, wall height, and section shape. ANN1 and ANN2 were normalized in intervals of [0, 1] and [0.1, 0.9], respectively. The shear force of the RC shear walls was the output data for both models. The predictions by the ANN models and the code methods from GB 50011 and ACI 318 were compared. The results reveal that the developed models exhibit better prediction and generalization capacity for RC shear walls than the code methods.