• 中国科学引文数据库(CSCD)核心期刊
  • 中文核心期刊中文科技核心期刊
  • Scopus RCCSE中国权威学术期刊
  • 美国EBSCO数据库 俄罗斯《文摘杂志》
  • 《日本科学技术振兴机构数据库(中国)》
二维码

隧道建设(中英文) ›› 2023, Vol. 43 ›› Issue (9): 1549-1557.DOI: 10.3973/j.issn.2096-4498.2023.09.012

• 地质与勘察 • 上一篇    下一篇

基于机器学习的隧道地质勘察岩性识别分析及应用研究

程勇1, 王琛2, 刘夏临1, 3, 刘继国1, 3, 陈世纪4, 黄胜4   

  1. 1. 中交第二公路勘察设计研究院有限公司, 湖北 武汉 430056 2. 中国交建总承包经营分公司, 北京 100088; 3. 中国交建隧道与地下空间工程技术研发中心, 湖北 武汉 430056; 4. 中山大学土木工程学院, 广东 珠海 519082)

  • 出版日期:2023-09-20 发布日期:2023-10-16
  • 作者简介:程勇(1975—),男,湖北武汉人,1997年毕业于同济大学,隧道与地下工程专业,本科,教授级高级工程师,现从事隧道与地下工程设计、科研、管理方面的工作。 E-mail: 654521051@qq.com。

Application of Machine LearningBased Lithology Identification Analysis for Tunnel Geological Survey

CHENG Yong1, WANG Chen2, LIU Xialin1, 3, LIU Jiguo1, 3, CHEN Shiji4, HUANG Sheng4   

  1. (1. CCCC Second Highway Consultants Co., Ltd., Wuhan 430056, Hubei, China; 2. China Communications Construction General Contracting and Operation Branch, Beijing 100088, China; 3. CCCC Research and Development Center on Tunnel and Underground Space Technology, Wuhan 430056, Hubei, China; 4. School of Civil Engineering, Sun YatSen University, Zhuhai 519082, Guangdong, China)

  • Online:2023-09-20 Published:2023-10-16

摘要: 为提高水平定向钻勘察中岩性识别的效率,基于机器学习算法采用钻进参数识别围岩岩性。以新疆某隧道工程为例,通过对水平定向钻的工作原理进行分析,采用钻进速度、校正后的钻孔底部压强、泥浆压力和进浆流量作为输入特征预测围岩岩性。对KNN(k-nearest neighbor)算法和随机森林算法各设置48个超参数,测试集的平均准确率分别为83.28%93.04%,模型不存在欠拟合和过拟合问题。将五分类问题转化为5个二分类问题,2种算法的准确率、精确率、召回率、F1值基本均在90.00%以上,受试者工作特征(receiver operating characteristic,ROC)曲线中曲线下面积(area under curveAUC)也接近于1。〖JP2〗使用Smote过采样后的KNN算法和随机森林算法都具有良好的鲁棒性和泛化能力,但综合各项评价指标可知,使用随机森林模型预测围岩岩性的效果更佳。

关键词: 隧道, 地质勘察, 水平定向钻, 岩性识别, KNN算法, 随机森林算法, 机器学习

Abstract: In horizontal directional drilling surveys, the lithology of the surrounding rock is generally determined by coring or drilling into rock chips. However, owing to the limitation of coring efficiency during drilling, determining the lithology of the surrounding rock throughout the entire borehole line based on rock chips is a tedious process. Therefore, to improve the efficiency of lithology identification, the authors use machine learning algorithms to identify the surrounding rock lithology using drilling parameters. A case study is conducted on a tunnel in Xinjiang, China, and the drilling speed, corrected bottom pressure of the borehole, mud pressure, and feed flow rate are input features to estimate the surrounding rock lithology based on the analysis of the working principle of horizontal directional drilling. Fortyeight hyperparameters are set for each knearest neighbor(KNN) and the random forest algorithms and the average accuracies of the test set are 83.28% and 93.04%, respectively, with no underfitting or overfitting concerns in the models. Furthermore, the five classification issues are transformed into five binary classification problems; the accuracy, precision, recall, and WT5《TNR#I》〗FWT5《TNR》〗1 values of both algorithms are above 90.00%. The area undercurve values in the receiver operating characteristic curves are close to 1. The results show that the KNN and random forest algorithms have good robustness and generalization ability after using Smote oversampling; however, the random forest model is more effective in predicting the rock properties of the surrounding rocks when the evaluation metrics are combined.

Key words:

tunnel, geological survey, horizontal directional drilling, lithology identification, knearest neighbor algorithm, random forest algorithm, machine learning