【摘要】 砂土地震液化判别对指导水利工程的设计和施工具有非常重要的意义。本文基于支持向量机分类算法,分析了影响砂土液化的主要因素,建立了砂土液化预测的支持向量机模型。在此模型中,选取地震烈度、标准贯入击数、平均粒径、相对密度和上覆有效压力5个指标作为主要评价影响因素,同时将液化程度划分为不液化、轻度液化、中等液化和严重液化4个等级,进而使其评判结果更为细化。以砂土地震实测数据作为学习样本进行训练,建立相应判别函数对待判样本进行分类。通过算例分析,表明文中方法对砂土液化评判的合理性与有效性,可以在实际工程中推广。更多还原

【Abstract】 The identification of sand seismic liquefaction is significant in the hydraulic design and construction.In this work,a support vector machine(SVM) model is established with a SVM classification algorithm and the major factors that influence sand seismic liquefaction,such as earthquake intensity,standard penetration number,mean diameter,relative density and effective overburden pressure.To improve the evaluation accuracy,liquefaction is divided into three grades of no,medium and serious liquefaction,and the discriminate functions are obtained by training a large sample of sand seismic liquefactions.Application to sand soil liquefaction of practical projects shows a success and effectiveness of the proposed method.更多还原