摘要
选取试验深度、粘粒含量、比贯入阻力和计算土层厚度为基本输入量,建立了一个推算液化指数的神经网络模型。以实际工程21组数据为学习样本,对工程中5个点进行了计算。计算结果表明,利用人工神经网络由静力触探推算液化指数是可行的。
The test depth,the content of the clay particle,the Ps and the thickness of the calculating soil are chosen as the input parameters for the neural network model build in this paper.The neural network model studied 21 samples and calculate 5 locations.The result shows that it is feasible to use artificial neural network model to calculate the liquation index by static cone penetration test.
出处
《四川建筑科学研究》
2004年第2期66-67,69,共3页
Sichuan Building Science
