摘要
针对盾构施工与监测过程为一时间序列的特点 ,从滚动优化思想出发 ,建立了部分最小二乘神经网络模型 ,预测盾构掘进一定距离后产生的地面变形 .最后将该模型应用到上海市轨道交通某近距离重叠地铁区间隧道工程实例中 ,结果证明 ,其训练以及预测效果均可以满足工程需要 .
In considering that the shield tunnelling construction and measurement development in time sequence, an artificial neural networks model was made to predict the ground deformation. This model features in its conception of the receding optimization, which is realized by partial least squares networks. The application of this model in two overlapped tunnels of the Shanghai metro projects was successful.
出处
《同济大学学报（自然科学版）》
EI
CAS
CSCD
北大核心
2004年第9期1141-1144,1152,共5页
Journal of Tongji University:Natural Science
关键词
盾构隧道
地面变形预测
人工神经网络
滚动优化
shield tunnelling
ground deformation prediction
artificial neural networks
receding optimization
