矿业科学学报2025，Vol.10Issue(2)：226-235,10.DOI:10.19606/j.cnki.jmst.2024922
岩土体单桥静力触探曲线MCP-DD预测方法研究
MCP-DD prediction method of single bridge static cone penetration curve of rock and soil
高睿 1胡修任 1王泽良 1李畅 1吴月秀2
作者信息
- 1. 武汉大学土木建筑工程学院,湖北武汉 430072||武汉大学湖北省数据驱动智能建造企校联合创新中心,湖北武汉 430072
- 2. 武汉大学土木建筑工程学院,湖北武汉 430072
- 折叠
摘要
Abstract
Static cone penetration test is often used in engineering practice to obtain relevant geological information.Yet the relatively sparse arrangement of test holes results in a large number of unknown ar-eas in the site,which could affect the accurate judgment of the actual geological information in engi-neering design and construction.Therefore,this study proposes MCP-DD(minimax concave penalty-distance determined)prediction method for single bridge static cone penetration curve of rock and soil.It contains three main parts:1)screen neighboring training data through the neighborhood radius search algorithm;2)compute trend estimation functions of selected data through the modified MCP al-gorithm based on the B-spline basis function;3)weight the trend estimation function by the spatial cor-relation function to obtain an integrated prediction model.This method was used to predict the single bridge static cone penetration curve of a certain engineering site.Results show that compared with the traditional linear interpolation method,the proposed method exhibits a higher coefficient of determina-tion R2.The mean absolute error MAE reduction reduced by 26.8％～55.8％and the root mean squared error RMSE reduces by 25.2％～54.9％.The optimal range for predicting the radius R0 is 25.0～37.8 m.Increasing average number of relevant data points leads to smaller average relative dis-tance between the predicted points and the relevant data points,thus bettering the prediction perform-ance of the model.关键词
单桥静力触探/趋势估计函数/空间相关性/MCP-DD算法Key words
single bridge static cone penetration test/trend estimation functions/spatial correlation/MCP-DD algorithm分类
土木建筑引用本文复制引用
高睿,胡修任,王泽良,李畅,吴月秀..岩土体单桥静力触探曲线MCP-DD预测方法研究[J].矿业科学学报,2025,10(2):226-235,10.
