基于粒子群改进的高铁隧道沉降预测研究

Research on Settlement Prediction of High-speed Railway Tunnel Based on Particle Swarm Optimization

高铁隧道的建设是高铁建设的重要一部分,大量的隧道建设会引起地表沉降。对沉降实测数据进行分析,得出隧道在沉降方面的长期沉降规律,可以实现隧道沉降预测,从而推进的隧道的安全、高速建设。本文针对高铁隧道沉降预测问题,运用粒子群算法(PSO)对灰色模型GM(1.1)进行改进,构建了灰色-时序组合模型对问题进行了预测研究。研究表明,基于粒子群改进的灰色-时序组合模型对高铁隧道的沉降预测具有实际意义,它能够更好地预测高铁隧道沉降趋势。

High-speed railway tunnel construction is an important part of high-speed railway construction,a large number of tunnel construction will cause surface subsidence.Through the analysis of the measured settlement data,the long-term settlement law of the tunnel in settlement can be obtained,and the prediction of the tunnel settlement can be realized,so as to promote the safe and high-speed construction of the tunnel.Aiming at the settlement prediction of high-speed railway tunnel,particle swarm optimization(PSO)is used to improve the grey model GM(1.1),and a grey-time series combination model is constructed to predict the problem.The results show that the grey-time series combined model based on particle sswarms has practical significance for the settlement prediction of high-speed railway tunnels,and it can better predict the settlement trend of high-speed railway tunnels.