机器学习在 TBM 掘进参数与围岩等级预测中的应用——以引绰济辽工程为例

丁巍 ,  魏师琳 ,  贾穗子 ,  李一丹 ,  楚一帆 ,  张效忠

有色金属(矿山部分) ›› 2026, Vol. 78 ›› Issue (6) : 75 -87.

PDF (6614KB)
有色金属(矿山部分) ›› 2026, Vol. 78 ›› Issue (6) : 75 -87. DOI: 10.20238/j.issn.1671-4172.2026.06.008
TBM专刊

机器学习在 TBM 掘进参数与围岩等级预测中的应用——以引绰济辽工程为例

作者信息 +

Application of machine learning in predicting TBM tunneling parameters and surrounding rock classification:a case study of the Yinchuojiliao water diversion project

Author information +
文章历史 +
PDF (6771K)

摘要

全断面隧道掘进机(TBM)施工过程中产生大量可反映地质状况的实时数据。为充分利用该数据并建立精确的掘进参数与围岩等级预测模型,本文提出了一种基于滑动均值滤波与一阶差分符号变化的掘进段自动分割方法,将掘进循环段划分为空推段、上升段与稳定段;并采用BP、SVM、GPR、RF 和RBF 五种机器学习方法进行对比建模。结果表明:GPR 在掘进参数回归预测中表现最优,基于上升段及进入稳定段60 s 内的数据,稳定段平均推力与单盘扭矩的测试集决定系数R2 分别达到0. 897 与0. 867;RF 在围岩等级分类中精度最高(ACC=0. 985,F1 均值=0. 985),GPR 次之(ACC=0. 930,F1 均值=0. 930)。综合考虑预测精度与模型统一性,本文选取GPR 作为统一预测模型,该模型在提供高精度掘进参数预测值的同时可输出预测置信区间与围岩等级预测概率,为TBM 操作人员提供地质- 机械联合决策支持,有效避免了多模型并行部署带来的工作量繁重与决策冲突等问题。

Abstract

A large amount of real-time data reflecting geological conditions is generated during the operation of Tunnel Boring Machine (TBM). To fully utilize this data and establish accurate prediction models for TBM tunneling parameters and surrounding rock classification,this paper proposes an automatic segmentation method for tunneling sections based on sliding mean filtering and first-order difference sign changes,dividing the tunneling cycle into air pushing section,rising section and stable section. Five machine learning methods (BP,SVM,GPR,RF and RBF) are compared for modeling. The results show that GPR performs best in the regression prediction of tunneling parameters,with the test set coefficients of determination (R2) for average thrust and single-disk torque reaching 0. 897 and 0. 867,respectively,based on data from the rising section and the first 60 s of the stable section. RF achieves the highest accuracy in surrounding rock classification (ACC=0. 985,F1 mean=0. 985),followed by GPR (ACC=0. 930,F1 mean=0. 930). Considering both prediction accuracy and model uniformity,GPR is selected as the unified prediction model,which can provide not only high-precision tunneling parameter predictions but also prediction confidence intervals and surrounding rock classification probabilities,offering geomechanical joint decision support for TBM operators and effectively avoiding the heavy workload and decision conflicts caused by multi-model parallel deployment.

关键词

TBM 掘进段 / 机器学习 / GPR / 围岩等级 / 掘进参数预测

Key words

TBM excavation section / machine learning / GPR / surrounding rock level / tunneling parameter prediction

引用本文

引用格式 ▾
丁巍,魏师琳,贾穗子,李一丹,楚一帆,张效忠. 机器学习在 TBM 掘进参数与围岩等级预测中的应用——以引绰济辽工程为例[J]. 有色金属(矿山部分), 2026, 78(6): 75-87 DOI:10.20238/j.issn.1671-4172.2026.06.008

登录浏览全文

4963

注册一个新账户 忘记密码

参考文献

[1]

荆留杰,张娜,杨晨. TBM 及其施工技术在中国的发展趋势[J]. 隧道建设,2016,36(3):331-337.

[2]

Jing Liujie,Zhang Na,Yang Chen. Development of TBM and its construction technologies in China[J]. Tunnel Construction,2016,36(3):331-337.

[3]

Jing Liujie,Li Jianbin,Yang Chen,et al. A case study of TBM performance prediction using field tunnelling tests in limestone strata[J]. Tunnelling and Underground Space Technology,2019,83:364-372.

[4]

Li Jianbin,Chen Zuyu,Li Xu,et al. Feedback on a shared big dataset for intelligent TBM Part Ⅰ:feature extraction and machine learning methods[J]. Underground Space,2023,11:1-25.

[5]

刘泉声,潘玉丛,余宏淦,等. 深部金属矿山巷道TBM 掘进技术应用现状及研究进展[J]. 有色金属(矿山部分),2024,76(6):25-41.

[6]

Liu Quansheng,Pan Yucong,Yu Honggan,et al. Application status and research progress of TBM tunnelling technology in deep metal mine roadways[J]. Nonferrous Metals (Mining Section),2024,76(6):25-41.

[7]

黄登侠,周小龙,赵健,等. 基于微震监测的TBM 掘进工程岩爆预警研究[J]. 有色金属(矿山部分),2024,76(6):105-112.

[8]

Huang Dengxia,Zhou Xiaolong,Zhao Jian,et al. Study on rockburst early warning in TBM excavation engineering based on microseismic monitoring[J]. Nonferrous Metals (Mining Section),2024,76(6):105-112.

[9]

Adoko A C,Gokceoglu C,Yagiz S. Bayesian prediction of TBM penetration rate in rock mass[J]. Engineering Geology,2017,226:245-256.

[10]

周小雄,龚秋明,殷丽君,等. 基于BLSTM—AM 模型的TBM 稳定段掘进参数预测[J]. 岩石力学与工程学报,2020,39(增刊2):3505-3515.

[11]

Zhou Xiaoxiong,Gong Qiuming,Yin Lijun,et al. Predicting boring parameters of TBM stable stage based on BLSTM networks combined with attention mechanism[J]. Chinese Journal of Rock Mechanics and Engineering,2020,39(S2):3505-3515.

[12]

Zhang Qianli,Liu Zhenyu,Tan Jianrong. Prediction of geological conditions for a tunnel boring machine using big operational data[J]. Automation in Construction,2019,100:73-83.

[13]

Hu Tao,Wang Jingcheng,Zhang Langwen. Prediction of hard rock TBM penetration rate using random forests[C]//The 27th Chinese Control and Decision Conference (2015 CCDC). May 23—25,2015,Qingdao,China. IEEE,2015:3716-3720.

[14]

JTJ 026— 1990 公路隧道设计规范[S].

[15]

JTJ 026— 1990 Design Specification for Highway Tunnel[S].

[16]

Pukelsheim F. The three sigma rule[J]. The American Statistician,1994,48(2):88-91.

[17]

王双敬,王玉杰,李旭,等. TBM 掘进数据标准化预处理方法研究[J]. 现代隧道技术,2022,59(2):38-44,52.

[18]

Wang Shuangjing,Wang Yujie,Li Xu,et al. Study of standardized pre—processing method of TBM tunnelling data[J]. Modern Tunnelling Technology,2022,59(2):38-44,52.

[19]

Gertsch R,Gertsch L,Rostami J. Disc cutting tests in Colorado Red Granite:implications for TBM performance prediction[J]. International Journal of Rock Mechanics and Mining Sciences,2007,44(2):238-246.

[20]

Singhal R K. Mechanical excavation in mining and civil industries[J]. International Journal of Mining,Reclamation and Environment,2014,28(3):214. DOI:10.1080/17480930.2014.912821.

[21]

Kohavi R. A study of cross—validation and bootstrap for accuracy estimation and model selection[C]//Proceedings of the 14th International Joint Conference on Artificial Intelligence—Volume 2. Montreal,Quebec,Canada:Morgan Kaufmann Publishers Inc.,1995:1137-1143.

[22]

Rumelhart D E,Hinton G E,Williams R J. Learning representations by back—propagating errors[J]. Nature,1986,323:533-536.

[23]

赵光祖,王亚旭,李尧,等. 基于优化BP 神经网络的TBM性能预测[J]. 河南理工大学学报(自然科学版),2020,39(5):139-145.

[24]

Zhao Guangzu,Wang Yaxu,Li Yao,et al. Prediction of TBM performance based on optimized BP neural network[J]. Journal of Henan Polytechnic University (Natural Science),2020,39(5):139-145.

[25]

Cortes C, Vapnik V. Support—vector networks[J]. Machine Learning,1995,20(3):273-297.

[26]

李建斌,武颖莹,李鹏宇,等. 基于局部线性嵌入和支持向量机回归的TBM 施工参数预测[J]. 浙江大学学报(工学版),2021,55(8):1426-1435.

[27]

Li Jianbin,Wu Yingying,Li Pengyu,et al. TBM tunneling parameters prediction based on Locally Linear Embedding and Support Vector Regression[J]. Journal of Zhejiang University(Engineering Science),2021,55(8):1426-1435.

[28]

Seeger M. Gaussian processes for machine learning[J]. International Journal of Neural Systems,2004,14(2):69-106.

[29]

Aha W. Lazy learning[J]. Artificial Intelligence Review,1997,11(1/2/3/4/5):7-10.

[30]

Breiman L. Random forests[J]. Machine Learning,2001,45(1):5-32.

[31]

Broomhead D S,Lowe D. Multivariable functional interpolation and adaptive networks[J]. Complex Systems,1988,2:321-355.

[32]

Khademi Hamidi J,Shahriar K,Rezai B,et al. Performance prediction of hard rock TBM using Rock Mass Rating (RMR)system[J]. Tunnelling and Underground Space Technology,2010,25(4):333-345.

[33]

李玉选,郭红斌,黄丹,等. 金属矿山TBM 地下始发硐室群设计及关键施工技术研究[J]. 有色金属(矿山部分),2024,76(6):152-160.

[34]

Li Yuxuan,Guo Hongbin,Huang Dan,et al. Study on design and key construction technology of underground starting chamber group of TBM in metal mine[J]. Nonferrous Metals (Mining Section),2024,76(6):152-160.

[35]

王照亚. 金属矿山超千米深TBM 主机组装硐室破坏形式分析与支护设计研究[J]. 有色金属(矿山部分),2023,75(5):26-35.

[36]

Wang Zhaoya. Failure forms and support design of over kilometer—deep TBM main engine assembly chamber in metal mine[J]. Nonferrous Metals (Mining Section),2023,75(5):26-35.

基金资助

贵州省科技计划项目(黔科合基础MS〔2025〕244)

贵州省科技厅计划项目(青年引导项目)(黔科合基础QN〔2026〕014-6)

AI Summary AI Mindmap
PDF (6614KB)

7

访问

0

被引

详细

导航
相关文章

AI思维导图

/

〈 〉