BP神经网络在消能结构中的仿真应用研究

采用BP神经网络对支撑变形影响下的非线性粘滞消能器两端的位移幅值与层间位移幅值之比与消能器的阻尼系数、支撑的总水平刚度、结构的振动周期、层间位移幅值、消能器的非线性指数之间的关系进行预测仿真.仿真结果表明采用BP神经网络预测非线性粘滞消能器两端的位移幅值与层间位移幅值之比是有效且可行的.此外,还讨论隐含层结点数的合理确定.

Application Research on Simulation of BP Neural Network in Energy Dissipation Structure

In this paper,the forcasting simulation of the relation between the ratio of the maximal relative displacement of the nonlinear viscous damper to the maximal interstory displacement and the damp coefficient of the damper, the stiffness of the bases, the vibration period of structure, the maximal interstory displacement, the nonlinear exponent of the damper is performed by using BP neural network. The simulation results show it is an effective and feasible method to forecast the ratio of the maximal relative displacement of the nonlinear viscous damper to the maximal interstory displacement using BP neural network. In addition,this paper discusses bow to choose the proper count of nerve cells in unseenble layer.