摘要
据地震液化的实测资料 ,即地震荷载下实测的各项土的物理力学参数 ,利用BP人工神经网络理论 ,建立粉土液化等级评别的反向神经网络模型进行判别 .与现有的方法比较 ,具有通用性、客观性、科学性 .因人工神经网络具有良好的非线性映射能力 ,可以灵活方便地对多成因的复杂的未知数进行高度的建模 .神经网络兼有概念直观 ,公式简洁 。
Based on the paractical date of earthquakes liquefaction and the soil physical parameters that are gained under the earthquake situation,the authors use BP artificial neural network theory to develop a back propagation neural network model of the evaluation of sandy loams earthquake liquefaction.Compared with conventional model,this model is more parctical and can be used,Meanwhile this model has the advantages of dislinct Coneept,brief formula,standavtiyation programcomposition and easy realigation.
出处
《昆明理工大学学报（理工版）》
2000年第4期63-65,共3页
Journal of Kunming University of Science and Technology(Natural Science Edition)
基金
云南省科委青年基金!(97E0 15Q)资助项目
关键词
神经网络
等级判别
粉土地震液化
sandy loam's liquefaction
artificial Neural Network
degree of liquefaction
