【作者】 肖哲哲； 刘陈续； 于桂兰；

【Author】 XIAO Zhe-zhe;LIU Chen-xu;YU Gui-lan;School of Civil Engineering, Beijing Jiaotong University;

【机构】 北京交通大学土木与建筑工程学院；

【摘要】 本文建立了一种人工神经网络,实现了饱和土体中周期空心桩频散曲线的预测。考虑了不同场地条件下饱和土参数的变化和空心桩内外径的变化。通过有限元数值模拟生成数据集,建立人工神经网络并进行训练和测试。结果表明,人工神经网络能够根据输入的饱和土参数和空心桩内外径准确预测结构的全模态频散曲线。本文的研究为饱和多孔介质中周期结构的隔振性能分析和反向设计提供了有价值的参考。更多还原

【Abstract】 In this paper, an artificial neural network is established to predict the frequency dispersion curve of periodic hollow pile in saturated soil, in which the changes of saturated soil parameters and the changes of internal and external radii of hollow pile under different site conditions are considered. The dataset is generated by numerical simulation with finite element method, and the artificial neural network is trained and tested. The results show that the artificial neural network can accurately predict the full mode dispersion curve of the periodic structure according to the input saturated soil parameters and internal and external radii of the hollow pile. The research of this paper provides a valuable reference for the vibration isolation performance analysis and reverse design of periodic structures in saturated porous media.更多还原