大型地下空间综合交通枢纽中巨型斜柱长期沉降的监测及预测分析

结构及其重要构件的长期沉降是影响地下空间综合交通枢纽施工安全的关键因素之一,对其开展监测与预测具有重要的工程意义。以深圳市黄木岗大型地下空间综合交通枢纽为研究背景,采用自动化监测系统,首先监测了12轴巨型斜柱施工后的119期长期沉降,分析其长期沉降规律,并评判其预警状态。监测结果表明,斜柱施工后,长期的沉降规律为先在安全状态内小幅波动,再增大至黄色预警状态,最后在安全状态与预警状态之间小幅波动。然后,利用109期监测数据分别构建斜柱沉降的反向传播(back propagation, BP)神经网络模型和遗传算法-BP(genetic algorithm-BP,GA-BP)神经网络模型,并预测之后10期的斜柱累计沉降量以对比验证两种模型效果。结果表明,相比BP神经网络模型,GA-BP神经网络模型的预测值与实测值更吻合。

Long-term settlement monitoring and prediction analysis of giant inclined column in large underground space integrated transportation hub

The long-term settlement of structure is one of the key factors affecting the construction safety of underground integrated transportation hub, so monitoring and forecasting it has important engineering significance. Based on the research background of a underground integrated transportation hub in Shenzhen City, first this paper adopts an automated monitoring system to monitor the long-term settlement of a giant inclined column after construction (up to 120 days), analyze its long - term settlement rule and judge its safety state. The monitoring results show that, after the construction of inclined column, the long-term settlement law first fluctuates slightly in the safety state, then increases to the yellow warning state, and finally fluctuates slightly between the safety state and the warning state.Then, The BP neural network model and the GA-BP neural network model of the inclined column settlement were constructed by using the monitoring data of the 119 stage, and the cumulative settlement amount of the inclined column in the last 10 stages was predicted respectively and the effect of the model was verified. The results show that the predicted value of the GA-BP neural network model is more consistent with the measured value.