摘要
根据工程经验较全面地分析和总结了影响深基坑围护变形的主要因素,采用层次分析法建立了深基坑围护变形的评价指标体系,并列出评价体系的量化标准.选取杭州市钱江新城区域某深基坑工程作为实例,利用工程数据对建立的模型进行训练与验证,最终确定了48个网络模型以预测不同深度下围护结构深层土体的水平位移.最后,在另一深基坑工程中两个测斜孔不同工况下,利用建立的BP神经网络模型分别预测深基坑围护产生的深层土体水平位移,为工程安全建设提供依据.
On the basis of engineering experiences,the main factors which affect the deep foundation pit were comprehensively analysed and summarized.Then the analytic hierarchy process was used to establish the evaluation index system of the deep foundation pit,and the quantification values were listed for the evaluation system.For the case of a deep excavation in Qianjiang New City in Hangzhou,inclinometer displacement data were used for model selection and verification,and 48 network models were confirmed to be effective to predict the displacement in different depth of retained soil.At last,for another deep foundation pit,the proposed BP neural network models were used to predict soil horizontal displacements under two different construction conditions,providing a useful reference for the engineering construction.
出处
《浙江工业大学学报》
CAS
2014年第4期367-372,共6页
Journal of Zhejiang University of Technology
关键词
BP神经网络
层次分析法
变形预测
MATLAB仿真
BP neural network
analytic hierarchy process
deformation prediction
Matlab simulation
