Prediction onSurface Settlementina Deep Foundation Pit in Underground Space Structure Based on PSO-BP Neural Network
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.
DeepfoundationpitSurface settlementParticle Swarm Optimization-BP neural network model
国家科技期刊平台
NSTL
万方数据
