) 北京交通大学 土木建筑工程学院，北京 100044
收稿日期:2019-08-19出版日期:2021-01-01发布日期:2021-01-19通讯作者:于桂兰E-mail:glyu@bjtu.edu.cn作者简介:刘陈续(1995-)，男，江苏省徐州市人，博士生，主要从事周期结构减振隔震的研究．基金资助:国家自然科学基金资助项目(11772040)Prediction of Energy Transmission Spectrum of Layered Periodic Structures by Neural Networks
LIU Chenxu, YU Guilan() School of Civil Engineering, Beijing Jiaotong University, Beijing 100044, China
Received:2019-08-19Online:2021-01-01Published:2021-01-19Contact:YU Guilan E-mail:glyu@bjtu.edu.cn摘要/Abstract
摘要： 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．
关键词: 层状周期结构, 深层反向传播神经网络, 径向基函数神经网络, 能量传输谱, 衰减域
Abstract: 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.
Key words: layered periodic structure, deep back propagation (BP) neural network, radial basis function (RBF) neural network, energy transmission spectrum, attenuation domain
PDF全文下载地址:
点我下载PDF
