岩土力学 ›› 2026, Vol. 47 ›› Issue (1): 267-280.doi: 10.16285/j.rsm.2025.0095CSTR: 32223.14.j.rsm.2025.0095

• 岩土工程研究 • 上一篇    下一篇

基于边界字典-随机森林模型的三维岩土地层重构方法

蒋水华1,钟越1,谢佳伟1,吕胜才2,周安楠1, 3,黄劲松1   

  1. 1.南昌大学 工程建设学院,江西 南昌 330031;2.中国电建集团贵阳勘测设计研究院有限公司,贵州 贵阳 550081; 3.皇家墨尔本理工学院 土木、环境和化学工程学院,澳大利亚 墨尔本
  • 收稿日期:2025-01-24 接受日期:2025-04-29 出版日期:2026-01-11 发布日期:2026-01-08
  • 作者简介:蒋水华,男,1987年生,博士,教授,博士生导师,主要从事岩土工程可靠度与风险分析方面的研究。E-mail: sjiangaa@ncu.edu.cn
  • 基金资助:
    国家自然科学基金项目(No.52579103,No.52222905,No.42272326);江西省自然科学基金项目(No.20253BDH410009,No.20252BCG330025,No.20242BAB24001)

Three-dimensional geotechnical stratigraphy reconstruction method based on boundary dictionary-random forest model

JIANG Shui-hua1, ZHONG Yue1, XIE Jia-wei1, LYU Sheng-cai2, ZHOU An-nan1,3, HUANG Jin-song1   

  1. 1. School of Infrastructure Engineering, Nanchang University, Nanchang, Jiangxi 330031, China; 2. PowerChina Guiyang Survey, Design and Research Institute Co., Ltd., Guiyang, Guizhou 550081, China; 3. School of Civil, Environmental and Chemical Engineering, Royal Melbourne Institute of Technology (RMIT), Melbourne, Australia
  • Received:2025-01-24 Accepted:2025-04-29 Online:2026-01-11 Published:2026-01-08
  • Supported by:
    This work was supported by the National Natural Science Foundation of China (52579103, 52222905, 42272326) and Jiangxi Provincial Natural Science Foundation (20253BDH410009, 20252BCG330025, 20242BAB24001).

摘要: 在岩土工程设计和施工前,通常需要充分了解工程场地地质条件以确保后期工程安全运行。重构三维岩土地层是了解场地地质条件的有效手段。由于地质构造空间特征的复杂性和场地勘探数据的稀疏性,传统方法基于少量钻探数据难以准确揭示不同地层间的边界形态及空间分布特征,基于有限钻探数据的三维岩土地层重构仍面临较大挑战。为解决这一问题,采用一系列三维距离场特征来表征不同地层之间的潜在边界特征,并引入距离场的特征选择过程,确定针对特定工程场地钻探数据的最优距离场特征组合,提出了基于边界字典-随机森林模型(boundary dictionary-random forest model,简称BD-RF)的三维岩土地层重构方法。通过两个工程实例验证了提出方法的有效性。结果表明:提出方法利用一系列三维距离场特征能够有效捕获钻探数据所揭示的地层分布规律。与其他方法相比,提出方法在预测不同地层之间边界特征方面具有明显的优势,为工程实际中基于少量钻探数据重构三维岩土地层模型提供了有效的分析工具。

关键词: 三维地层重构, 地层边界, 距离场特征, 随机森林, 边界字典

Abstract: Prior to geotechnical design and construction, it is quite necessary to thoroughly understand the geological conditions of the project site to ensure the safe operation of the project during subsequent stages. Reconstructing the three-dimensional geotechnical stratigraphy provides an effective approach for accurately understanding the geological conditions of the project site. Due to the complexity of geological structure spatial characteristics and the sparsity of site exploration data, it is difficult for traditional methods to reveal the boundary patterns and spatial distribution characteristics between different strata based on a small amount of site exploration data. Reconstruction of the three-dimensional stratigraphy based on limited site exploration data still faces considerable challenges. To address this problem, a series of three-dimensional distance field features is used to characterize the potential boundary characteristics between strata. This paper introduces the feature selection process of the distance field and proposes a three-dimensional stratigraphic reconstruction method based on a boundary dictionary-random forest (BD-RF) model. The effectiveness of the proposed method is validated through two engineering cases. The results indicate that the proposed method, by employing a series of three-dimensional distance field features, can effectively capture the stratigraphic distribution patterns revealed by drilling data. Compared with other methods, the proposed method has significant advantages in predicting the boundary characteristics between different strata, providing an effective analytical tool for reconstructing three-dimensional geotechnical models based on limited drilling data in practical engineering applications.

Key words: three-dimensional stratigraphy reconstruction, stratigraphic boundary, distance field feature, random forest, boundary dictionary

中图分类号: TU 470
[1] 解佩瑶, 陈卫忠, 赵武胜, 周帅, 秦长坤, 李翔, 蒋华, 何树江. 峰前循环剪切作用下岩体结构面剪切力学性质研究[J]. 岩土力学, 2026, 47(1): 115-129.
[2] 刘剑, 周宗红, 张晶, 王春, 侯廷凯, 乔木, . 闪长岩不同卸荷速率声发射特征及非稳定阶段识别[J]. 岩土力学, 2025, 46(1): 225-232.
[3] 肖思奇, 黄科锋, 周红波, . 基于动三轴试验的软黏土软化系数的分析与预测[J]. 岩土力学, 2024, 45(S1): 133-146.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!