论文部分内容阅读
结合5种混凝土延性柱耗能器在低周期反复荷载作用下的试验数据研究,利用神经网络的工作原理,通过建立神经网络的输入层、隐含层、输出层,确定输入单元、输出单元和隐含层节点数,从而建立了BP神经网络的模型,并根据已有的部分试验数据数据.对网络进行训练,对各种混凝土延性柱耗能器骨架曲线进行了预测拟合,实现混凝土延性柱耗能器骨架曲线的数字化,使其成为具有分析和判断的拟合曲线功能,完整的描绘混凝土延性柱耗能器的骨架曲线,为后续混凝土延性柱耗能器性能研究的仿真模拟提供了可靠的数据模型.结果表明,这种方法是可行的.
Based on the experimental data of five types of concrete ductile column energy dissipators under low cyclic loading, using the working principle of neural network, the input unit, output unit and output unit are determined by establishing the input layer, hidden layer and output layer of the neural network The number of nodes in hidden layer is established to build the model of BP neural network and the data of some existing experimental data are used to train the network.Furthermore, the skeleton curves of various types of concrete ductile column energy dissipators are predicted and fitted to realize the ductility of concrete The digitalization of the column energy consumption skeleton curve makes it a fitting curve function with analysis and judgment. The complete skeleton curve of the concrete ductile column energy dissipation device is provided for the simulation simulation of the performance study of the concrete ductile column energy dissipation device Reliable data model.The results show that this method is feasible.