论文部分内容阅读
针对沈阳地铁一号线重工街站至启工街站区间隧道开挖引发地面沉降变形的问题,利用现场实测的地表沉降变形数据建立BP神经网络模型,并进行网络训练与预测。预测结果表明,时间序列神经网络模型能够很好地表达地面沉降监测数据序列间的非线性关系。利用BP神经网络建立的预测模型,所得预测值与实测值拟合很好,是预测地铁施工引发地面沉降变形的一种有效方法,能为沈阳地铁隧道的设计及施工提供科学合理的依据。
Aiming at the problem of land subsidence and deformation caused by tunnel excavation in the section of Shenyang Heavy Rail Road from Shenyang to Gonggongjie, the BP neural network model is established based on the measured data of surface subsidence deformation. The network training and forecasting are carried out. The prediction results show that the time series neural network model can well express the nonlinear relationship between the sequence of land subsidence monitoring data. The prediction model established by BP neural network fits well with the measured data, which is an effective method to predict the ground settlement induced by subway construction. It can provide a scientific and reasonable basis for the design and construction of Shenyang Metro Tunnel.