基于BP-RBF神经网络的地下连续墙变形预测

详细信息

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

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。
- 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
Abstract: 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 , 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.
- diaphragm wall /
- deformation forecasting /
- BP neural network /
- RBF neural network /
- BP-RBF neural network model