基于PSO-BP神经网络的地下空间结构深基坑地表沉降预测研究
Prediction onSurface Settlementina Deep Foundation Pit in Underground Space Structure Based on PSO-BP Neural Network
莫永春1
作者信息
摘要
文中以深圳市黄木岗大型地下空间综合交通枢纽为研究案例,开展了深基坑地表沉降预测研究.首先,收集 140 d沉降数据,分析规律,评判安全状态;然后,利用140 期监测数据分别构建传统BP和PSO-BP神经网络模型,结合未来10d的基坑沉降量验证了模型的效果.结果表明,BP和PSO-BP神经网络预测模型均可满足施工要求,而PSO-BP神经网络模型的预测精度更高,可用于类似工程的地表沉降预测.
Abstract
In this research,based on Huangmugang large-scale transportation hub underground in Shenzhen City,monitoring and predictionon the ground surface settlement isstudied.Firstly,the long-term settlement(up to 140 periods)of the 10-axis was monitored and analyzed,and its early warning status was evaluated.Then,the back propagation(BP)neural network model and Particle Swarm Optimization-BP(PSO-BP)neural network model for surface settlement were constructed according to 140 monitoring data,and the cumulative settlement of founda-tion pit in the following 10 periods was predicted to compare and verify the effectiveness of the two models.The results indicate that both neural network models can meet the construction requirements.Also,compared to the BP neural network model,the predicted values of the PSO-BP neural network model are more consistent with the measured values.The research results can provide valuable reference for predictionof surface settlement indeep foundation pit.
关键词
深基坑/地表沉降/PSO-BP神经网络模型Key words
Deepfoundationpit/Surface settlement/Particle Swarm Optimization-BP neural network model引用本文复制引用
基金项目
江西省教育厅科学技术研究项目(GJJ170398)
出版年
2024
国家科技期刊平台
NSTL
万方数据