首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于BP神经网络的深基坑变形预测
引用本文:李水兵,李培现.基于BP神经网络的深基坑变形预测[J].测绘信息与工程,2011,36(5):41-42,45.
作者姓名:李水兵  李培现
作者单位:中国矿业大学环境与测绘学院,徐州市三环南路269号,221008
摘    要:建立深基坑变形监测数据处理的BP神经网络模型,采用双曲正切S形函数进行输入和输出层传递,选择批处理梯度下降法训练前向网络,并采用附加动量法和学习速率自适应调整进行改进,运用Matlab建立BP神经网络模型。预测结果表明,改进的BP神经网络模型预测精度更高,提高了学习速度并增加了算法的可靠性。

关 键 词:深基坑  变形监测  BP神经网络  Matlab

Deep Foundation Pit Considering Excavation Effect Based on BP Neural Network Model
LI Shuibing LI Peixian.Deep Foundation Pit Considering Excavation Effect Based on BP Neural Network Model[J].Journal of Geomatics,2011,36(5):41-42,45.
Authors:LI Shuibing LI Peixian
Institution:LI Shuibing LI Peixian(1 School of Environment Science and Spatial Informatics,China University of Mining and Technology,269 South Sanhuan Road,Xuzhou 221008,China)
Abstract:We set up BP neural network model of deep foundation pit considering the excavation effect.Sigmoid is applied in transmitting between input and output layer.Batching descent iselected gradient to train reverse direction network,and BP network is optimized by additional momentum and adaptive tuning for the learning step sizes of the BP learning algorithm.We set up BP neural network model based on Matlab.The prediction results prove that the optimized BP network has a better precision,and improve the learning rate and increases the reliability of prediction.
Keywords:deep foundation pit  deformation monitoring  BP neural network  Matlab
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号