摘要
该文聚焦于高速铁路路基沉降预测,鉴于路基沉降对线路稳定性和平顺性的关键影响,对比多种预测方法后选用灰色预测模型。详细介绍GM(1,1)模型原理及粒子群算法(PSO)优化过程,以京沪高铁济南西客站ZH标段一工区K417+523和K417+573两断面69~339 d沉降观测数据为例展开实例分析。结果显示,PSO-GM(1,1)模型预测效果优于GM(1,1)模型,在两断面拟合平均误差分别为3.8%和3.9%,通过残差检验和级比偏差检验表明其精度更高、稳定性更好。该研究为灰色预测模型处理累积误差提供新思路,证明PSO-GM(1,1)模型在路基沉降预测方面具有较高可靠性与应用价值。
This paper focuses on the prediction of subgrade settlement of high-speed railway.In view of the key impact of subgrade settlement on the stability and smoothness of the line,the grey prediction model is selected after comparing various prediction methods.The principle of GM(1,1)model and the optimization process of particle swarm optimization(PSO)are introduced in detail.The 69~339 day settlement observation data of two sections K417+523 and K417+573 in the first work area of ZH section of Jinan West Railway Station of Beijing Shanghai high speed railway are taken as examples to carry out the case analysis.The results show that the prediction effect of PSO-GM(1,1)model is better than that of GM(1,1)model,and the average fitting errors at the two sections are 3.8%and 3.9%respectively.The residual error test and class ratio deviation test show that it has higher accuracy and better stability.This research provides a new idea for grey prediction model to deal with cumulative errors,and proves that PSO-GM(1,1)model has high reliability and application value in predicting subgrade settlement.
作者
曲昌晟
耿敏
QU Changsheng;GENG Min
出处
《科技创新与应用》
2025年第21期30-34,共5页
Technology Innovation and Application
关键词
高速铁路
路基沉降
GM(1
1)模型
沉降预测
粒子群算法
high-speed railway
subgrade settlement
GM(1,1)model
settlement prediction
particle swarm algorithm
