基于BP-RBF神经网络的地下连续墙变形预测  

DIAPHRAGM WALL'S DEFORMATION FORECASTING BASED ON BP-RBF NEURAL NETWORKS

作　　者：徐炳伟[1] 姜忻良[1] 

机构地区：[1]天津大学建工学院,天津300072

出　　处：《工程力学》2009年第A01期163-166,共4页Engineering Mechanics

摘　　要：采用神经网络对地下连续墙变形进行预测,提取出影响地下连续墙变形的5个主要参数:土的粘聚力C、内摩擦角?、地下连续墙高度H、基坑开挖深度H1和测点深度h作为神经网络模型输入,建立了BP神经网络与RBF神经网络相结合的BP-RBF预测模型,与单纯的BP神经网络模型相比,具有提高训练效率,简化网络结构的特点,且预测精度满足工程需要。A artificial neural network is adopted to forecast diaphragm wall＇s deformations. Five parameters, the soil＇s cohesion C, the soil＇s internal friction angle φ, the wall＇s height H, the excavation depth H1 and the survey point＇s depth h, governing diaphragm wall＇s deformation are abstracted and taken as inputs of the artificial neural network model. A new hybrid neural network model, BP-RBF Neural Network Model is established by combining the traditional BP and RBF neural network. This new neural network model shows great superiority in higher efficiency and a simpler network structure compared with the traditional pure BP neural network model, at the same time the forecasting accuracy is ensured.

关 键 词：地下连续墙 变形预测 BP神经网络 RBF神经网络 BP-RBF神经网络模型 

分 类 号：TU476.3[建筑科学—结构工程] TU473[建筑科学—土工工程]