铁道科学与工程学报2016，Vol.13Issue(5)：791-799,9.
基于GM（1，1）幂模型的冻胀区高速铁路轨面不平顺发展预测
Track irregularity evolution prediction for high speed railways in frozen ground region based on GM(1,1)power model
摘要
Abstract
According to the evolving characteristics of track irregularity of high speed railway in frozen ground region,the non-equal interval GM(1 ,1 )power model was established based on the grey system theory.When establishing the GM(1 ,1 )model,the track irregularity test data of high speed railway in fro-zen ground region were treated as the time series.The initial values and background values of the model were optimized to improve the prediction accuracy.The power exponent was solved by using particle swarm intelligence algorithm.In order to fit the random components of track irregularities better,periodic functions generated by harmonic transform and sine function were introduced to modify the residual error.According-ly,the track irregularity evolution of high speed railway in frozen ground region during the process of the subgrade frost heaving was predicted.The results show that the model can well reflect the time-dependent random fluctuation characteristics of track irregularity evolution of high speed railway in frozen ground re-gion.The average relative error of the fitted values is 5 .64% and the average relative error of the predictive value is 6 .47%.This model may provide references for the maintenance of track irregularity of high speed railway in frozen ground region.关键词
高速铁路/轨面不平顺/路基冻胀/GM(1 ,1 )幂模型/发展预测Key words
high speed railway/track irregularity/subgrade frost heaving/GM(1 ,1 )power model/develop-ment prediction分类
交通工程引用本文复制引用
郭毅,高建敏..基于GM（1，1）幂模型的冻胀区高速铁路轨面不平顺发展预测[J].铁道科学与工程学报,2016,13(5):791-799,9.基金项目
国家重点基础研究发展计划（973计划）项目（2013CB036205，2013CB036206）；中国铁路总公司科技研究开发计划资助项目（2014G001－1）；中央高校基本科研业务费专项资金资助项目（2682015CX045）；牵引动力国家重点实验室自主研究资助项目 （）
