论文部分内容阅读
地铁车站深基坑变形预测是保证地铁车站安全施工的一个重要手段,为了能够更准确更有效的预测地铁车站深基坑变形,采用粒子群优化算法即PSO算法对传统的BP神经网络的权值和阀值进行了优化,同时对该预测模型中的输出样本添加噪声训练,建立了基于粒子群优化BP神经网络的地铁深基坑变形预测算法。以合肥市轨道交通2号线长丰南路站深基坑为工程实例,经计算表明该算法取得了良好的效果,所预测的变形数据具有较高的可信度。
In order to predict the deformation of deep foundation pit of subway station more accurately and effectively, the deformation prediction of deep foundation pit of metro station is an important means to ensure the safe construction of metro station. The particle swarm optimization (PSO) algorithm is used to estimate the weight of traditional BP neural network And the threshold are optimized. At the same time, noise training is added to the output samples of the prediction model, and a deformation prediction algorithm of deep foundation pit based on particle swarm optimization BP neural network is established. Taking the deep foundation pit of Changfeng South Road Station on the No.2 rail transit line of Hefei as an example, the calculation shows that the algorithm has achieved good results and the predicted deformation data has high credibility.