基于神经网络的层状周期结构能量传输谱预测

Prediction of Energy Transmission Spectrum of Layered Periodic Structures by Neural Networks

本文对层状周期结构的能量传输谱预测方法进行了研究.在考虑几何参数、物理参数单独变化以及同时变化3种情况下,通过构建深层反向传播(BP)神经网络,实现层状周期结构能量传输谱的精准预测.与径向基函数(RBF)神经网络进行对比实验,实验结果验证了所提方法的有效性.

In this paper,the prediction of the energy transmission spectrum for layered periodic structures is studied.By considering three cases of geometric parameters and physical parameters changing individually or simultaneously,a deep back propagation(BP)neural network is constructed to realize accurate prediction of the energy transmission spectrum of layered periodic structure.A comparison of the predicted results with those obtained by the radial basis function(RBF)neural network verifies the effectiveness of the proposed method.