路基压实度预测模型的建立及评价

The Establishment and Evaluation of the Prediction Model of Subgrade Compaction Degree

  • 打印
  • 收藏
收藏成功


打开文本图片集

1,2,3,3,2,(1.,;2.,;3.,)

中图分类号:U447 文献标志码:A 文章编号:1005-8249(2025)01-0124-06

DOI:10.19860/j.cnki.issn1005-8249.2025.01.023

LONG Kai1,DENG Jingxiang2,LI Hongzhao3,HUI Bing3,SHI Yaqiang2, ZHANG Wenjun3 (1. Ji'ning Highway Devlopment Center, Ji'ning 272OO8,China; 2.Gezhouba Group Transportation Investment Co.,Ltd.,Yichang 4430O5,China; 3.Shandong Transportation Institute, Ji’nan 25OO31,China)

Abstract:Subradecompactioniscloselyrelatedtothequalityoftheroadanddirectlyafectstestabilityanddurabilityof the project.Inorderto establishthe prediction model of subgradecompaction,carryoutthe field testof subgradecompaction, throughthecontrolofthenumberofrollng,rollngspeedandwatercontentofthetestmethodonthecompactionofthelaw,the useof nonlinearregression,decision tree,supportvector machine,neural laticeand XGBoostalgorithms toestablishasix compactionprediction model,and itsprediction performanceevaluation.Theconclusion shows:Thesubgrade compaction degreeis positivelyproportional tothenumberofolingtimesand inverselyproportionaltotherollngspeed.Whenthewater content isattheoptimal watercontent,the subgradecompactionismaximum.Theefectsof watercontent,numberofroling timesandrollngspeedoncompactionarereduced inoder;thesupportvectormachine modelhasapoorpredictionefectonthe training set,andthe decision tree modelhasa por predictionefecton the predictionset,which isnotapplicable to the predictioofsubgradecompaction;thetwononlinearregressionmodelsofthepowerfunctionandthelogarithmicfunction,and thetwo machinelearning modelsof theneuralnetworkandthe XGBoostareapplicabletothepredictionof thecompactiondegree of the subgrade.The prediction performance of machine learning is higher than the nonlinear regression model.

Keywords:subgrade compaction degree;field test;predictive modeling;performance evaluation;machine learning

0 引言

基础是建筑物最下部的承重构件,承受建筑物的全部荷载,其施工质量对于上覆结构的耐久性和长期功能有着重要的影响。(剩余8618字)

monitor