论文部分内容阅读
盾构隧道施工中引起的地表沉降是衡量开挖方式是否合适的关键指标。文中在介绍BP神经网络及盾构施工引起变形情况的基础上,对基于BP神经网络的盾构隧道开挖引起的地表沉降预测进行了研究,考虑了训练样本中奇异数据的剔除,采用变步长的方法,并选取适当的动量项系数,综合考虑各种影响因素,建立了盾构隧道开挖引起的地表沉降预测的BP网络模型,并对广州地铁二号线进行了具体的预测分析。分析结果表明:理论计算结果与工程实际情况一致,误差小于5%,所建立的预测模型是令人满意的。
Surface subsidence caused by the construction of shield tunnels is a key indicator of whether excavation is suitable or not. Based on the introduction of BP neural network and the deformation caused by shield construction, the paper studies the prediction of surface subsidence caused by shield tunneling based on BP neural network, considers the singular data removal in training samples, Length method and select the appropriate momentum coefficient, comprehensively considering various influencing factors, a BP network model of ground settlement prediction caused by shield tunneling is established, and the specific prediction and analysis of Guangzhou Metro Line 2 is carried out. The analysis results show that the theoretical calculation results are consistent with the actual engineering conditions and the error is less than 5%. The prediction model established is satisfactory.