BP神经网络在静力触探确定单桩承载力中的应用  

THE APPLICATION OF BP NEURAL NET IN THE DETERMINATION OF THE BEARING CAPACITY OF SINGLE PILE USING THE RESULT OF STATIC CONTACT SURVEY

作　　者：曹茂森[1] 周翠玲[1] 戴景军[1] 

机构地区：[1]山东农业大学水利土木工程学院,山东泰安271018

出　　处：《山东农业大学学报（自然科学版）》2002年第3期338-342,共5页Journal of Shandong Agricultural University：Natural Science Edition

摘　　要：运用BP神经网络建立了静力触探成果与单桩承载力的相关关系 ,并通过工程实例将BP神经网络预报值与线性回归数学模型、规范公式方法计算值进行对比 ,说明BP神经网络在利用静力触探成果确定单桩承载力中是一种行之有效的方法 ,具有精度高 ,信息处理智能化等特点 ,计算结果明显优于传统的线性回归数学模型和规范公式方法 ,具有较好的应用价值。The relationship between the result of static contact survey and the bearing capacity of single pile is set up applying BP nerve net. By project examples, the comparison is made between the forecast result from BP nerve net and the calculation results from the mathematic model of linear regression and the standard formula. The conclusion of comparison shows that the method of applying BP nerve net to determine the bearing capacity of single pile using the result of static contact survey is effective, characteristic of high precision and intelligent information treatment, and is obviously superior to the traditional method of the mathematic model of linear regression and the standard formula, and so is good in application value.

关 键 词：BP神经网络 静力触探 单桩承载力 应用 线性回归 

分 类 号：TU47[建筑科学—结构工程]