多源数据融合的土性参数预测方法  

Multi-source data fusion method for prediction of soil parameters

作　　者：汪明元 陈松庭 王耿鑫 彭成威 李欣益 WANG Mingyuan;CHEN Songting;WANG Gengxin;PENG Chengwei;LI Xinyi(Zhejiang Huadong Construction Engineering Co.,Ltd.,Hangzhou 310014,China;Power China Huadong Engineering Co.,Ltd.,Hangzhou 311122,China;College of Civil Engineering,Zhejiang University of Technology,Hangzhou 310023,China)

机构地区：[1]浙江华东建设工程有限公司,浙江杭州310014 [2]中国电建集团华东勘测设计研究院有限公司,浙江杭州311122 [3]浙江工业大学土木工程学院,浙江杭州310023

出　　处：《浙江工业大学学报》2024年第4期430-436,共7页Journal of Zhejiang University of Technology

摘　　要：场地勘察是岩土工程建设中至关重要的环节,静力触探测试(Cone penetration test,CPT)和多通道表面波试验(Multi-channel analysis of surface waves,MASW)分别是常用的岩土工程勘察和地球物理探测方法,两种方法各有优势和局限性。首先,通过多源数据融合的土性参数预测方法将MASW试验获得的剪切波速(V S)转换为锥尖阻力(q_(c));然后,基于随机森林算法将转换结果与CPT获得的实测q_(c)相结合,从而实现对目标场地剖面上q_(c)的预测;最后,根据实测CPT参数采用准确性评价指标评价该预测方法的准确性。研究结果表明:V S与q_(c)之间有较强的相关性,采用转换模型将V S转换为q_(c)的预测准确性高于经验公式,所提方法能够有效预测目标场地的土性参数,相较于未融合MASW参数的预测模型,采用多源数据融合方法获得的模型准确性有所提升。Site investigation is a crucial part of geotechnical construction.The cone penetration test(CPT)and the multichannel analysis of surface waves(MASW)are the main geotechnical investigation and geophysical exploration methods,both of which have their own advantages and limitations.This paper proposes a multi-source data fusion method for predicting soil parameters,which converts the shear wave velocity(V S)obtained from the MASW test into the cone tip resistance(q_(c)),combines the conversion results with q_(c) obtained from the CPT by a random forest algorithm to predict q_(c) on the target site profile,and evaluates the accuracy of this prediction method by the accuracy evaluation indexes based on the measured CPT values.The results show that there is a strong correlation between V S and q_(c),the prediction accuracy of the transformation model from V S into q_(c) is higher than that of empirical formulas,the method used can effectively predict the target site soil parameters,and the accuracy of the model obtained by the multi-source data fusion method is improved through comparing with the prediction model without fused MASW parameters.

关 键 词：CPT MASW 土性参数 随机森林 数据融合 

分 类 号：TU41[建筑科学—岩土工程]