基于集成CART算法的TBM掘进参数与围岩等级预测

doi:10.13722/j.cnki.jrme.2019.0924

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (3158 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要全断面隧道掘进机(TBM)运行过程中将会产生大量可以反映当时地质状况的数据，旨在充分利用TBM运行数据，使用基于集成CART算法的随机森林和AdaCost，实现岩体信息实时感知与掘进参数智能优化。为建立快速、准确的TBM掘进参数与围岩等级预测模型，提出了一种掘进模式识别方法，将TBM掘进循环分为空推段、上升段与稳定段；并使用随机森林模型和上升段前30 s数据，实时预测稳定掘进时掘进推力与刀盘扭矩的取值，预测精度分别达到0.90和0.87；继而使用代价敏感的AdaCost算法预测围岩等级，解决了传统机器学习算法不适用于岩体级别数据不均衡的场景，相较于随机森林模型，对于IV级和V级岩体的预测正确率分别提升了16%与50%。此外，总推进力、刀盘功率、刀盘扭矩、推进速度等TBM运行参数被证明与TBM掘进情况密切相关；刀盘转速、撑靴压力、撑靴俯仰角、推进速度和撑靴滚动角等参数被证明能更好地反映围岩状况。这些认识与成果对TBM掘进参数优化和风险预警有着重要意义，并将为建立基于数据挖掘的TBM智能决策控制平台提供参考。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	朱梦琦1
	朱合华1
	2
	王昕1
	程盼盼1

关键词 ：岩石力学, TBM掘进参数, 围岩等级, 不均衡数据集, 随机森林, AdaCost算法

Abstract：There are numerous data available to reflect the geological conditions during the operation period of full-section tunnel boring machine(TBM). The aims of this paper are to measure information of rockmasses in time and to intelligently optimize the tunneling parameters based on TBM operating data and CART-based ensemble learning algorithms，i.e. random forest and AdaCost. In order to establish models for rapidly and accurately predicting TBM tunneling parameters and surrounding rockmass conditions，a new pattern recognition method is proposed to divide a TBM tunneling cycle into empty pushing section，ascending section and stable section. Random forest model and the first 30 seconds data of ascending section are used to predict the values of the thrust and cutterhead torque during stable section，with the accuracy of 0.90 and 0.87 respectively. Moreover，a cost-sensitive AdaCost algorithm is used to predict the surrounding rockmass conditions with 16% and 50% precision improvements of grades IV and V compared to the random forest model，which solves the problem that the traditional machine learning algorithms are not applicable to imbalanced database. TBM operating parameters such as thrust，cutterhead power，cutterhead torque and advance rate are proved to be closely related to TBM tunneling，while cutterhead rotational speed，boot pressure，boot angle of pitch，advance rate and boot roll position and so on are shown to better reflect the surrounding rockmass conditions. These results are of great significance to TBM tunneling parameters optimizing and risk warning and will provide a reference to establish a data-based TBM intelligent decision and control platform in the future.

Key words： rock mechanics TBM tunnelling parameters surrounding rockmass conditions imbalanced database random forest AdaCost algorithm

引用本文:

朱梦琦1，朱合华1，2，王昕1，程盼盼1. 基于集成CART算法的TBM掘进参数与围岩等级预测[J]. 岩石力学与工程学报, 2020, 39(9): 1860-1871.
ZHU Mengqi1，ZHU Hehua1，2，WANG Xin1，CHENG Panpan1. Study on CART-based ensemble learning algorithms for predicting TBM tunneling parameters and classing surrounding rockmasses#br#. , 2020, 39(9): 1860-1871.

链接本文:

http://rockmech.whrsm.ac.cn/CN/10.13722/j.cnki.jrme.2019.0924 或 http://rockmech.whrsm.ac.cn/CN/Y2020/V39/I9/1860

[30]	GAO X J，SHI M L，SONG X G，et al. Recurrent neural networks for real-time prediction of TBM operating parameters[J]. Automation in Construction，2018，98：225-235.
[1]	ZHU H H，YAN J X，LIANG W H. Challenges and development prospects of ultra-long and ultra-deep mountain tunnels[J]. Engineering，2019，5(3)：384-392.
[2]	SUN W，SHI M L，ZHANG C，et al. Dynamic load prediction of tunnel boring machine (TBM) based on heterogeneous in-situ data[J]. Automation in Construction，2018，92(15)：23-34.
[4]	JUNG J H，CHUNG H，KWON Y S，et al. An ANN to predict ground condition ahead of tunnel face using TBM operational data[J]. KSCE Journal of Civil Engineering，2019，23(7)：3 200-3 206.
[37]	BREIMAN L. Random forests[J]. Machine Learning，2001，45(1)：5-32.
[5]	JING L J，LI J B，YANG C，et al. A case study of TBM performance prediction using field tunnelling tests in limestone strata[J]. Tunnelling and Underground Space Technology，2019，83(1)：364-372.
[8]	CHUNG H Y，LEE I M，JUNG J H，et al. Bayesian networks-based shield TBM risk management system：methodology development and application[J]. KSCE Journal of Civil Engineering，2019，23(1)：452-465.
[11]	LI S C，LI S C，ZHANG Q S，et al. Predicting geological hazards during tunnel construction[J]. Journal of Rock Mechanics and Geotechnical Engineering，2010，2(3)：232-242.
[12]	SHI S S，LI S S，LI L P，et al. Advance optimized classification and application of surrounding rock based on fuzzy analytic hierarchy process and Tunnel Seismic Prediction[J]. Automation in construction，2014，37(1)：217-222.
[15]	ERHARTER G H，MARCHER T，REINHOLD C. Artificial neural network based online rockmass behavior classification of TBM data[C]// Proceedings of the 3rd International Conference (ICITG). [S. l. ]：[s. n.]，2019：178-188.
[17]	GALENDE-HERNANDEZ M，MENENDEZ M，FUENTE M J，et al. Monitorwhile-drilling-based estimation of rock mass rating with computational intelligence：the case of tunnel excavation front[J]. Automation in Construction，2018，93：325-338.
[19]	GONG Q M，ZHAO J. Development of a rock mass characteristics model for TBM penetration rate prediction[J]. International Journal of Rock Mechanics and Mining Sciences，2009，46(1)：8-18.
[21]	ROSTAMI J，OZDEMIR L. A new model for performance prediction of hard rock TBMs[C]// Proceedings of the Rapid Excavation and Tunneling Conference. [S. l.]：[s. n.]，1993：793-809.
[3]	OKUBO S，FUKUI K，CHEN W，Expert system for applicability of tunnel boring machines in Japan[J]. Rock Mechanics and Rock Engineering，2003，36(4)：305-322.
[10]	LI S C，LIU B，XU X J，et al. An overview of ahead geological prospecting in tunneling[J]. Tunnelling and Underground Space Technology，2017，63(3)：69-94.
[18]	YAMAMOTO T，SHIRASAGI S，YAMAMOTO S，et al. Evaluation of the geological condition ahead of the tunnel face by geostatistical techniques using TBM driving data[J]. Tunnelling and Underground Space Technology，2003，18(2)：213-221.
[23]	周思阳，亢一澜，苏翠霞，等. 基于力学分析的TBM掘进总推力预测模型研究[J]. 机械工程学报，2016，52(20)：76-82.(ZHOU Siyang，KANG Yilan，SU Cuixia，et al. Prediction of thrust force requirement for TBMs based on mechanical analysis[J]. Journal of Mechanical Engineering，2016，52(20)：76-82.(in Chinese))
[25]	韩美东. 全断面岩石掘进机刀盘掘进载荷特性与结构性能研究[博士学位论文][D]. 天津：天津大学，2017.(HAN Meidong. Study on tunneling loads and structural performance of cutterhead of full face rock tunnel boring machine[Ph. D. Thesis][D]. Tianjin：Tianjin University，2017.(in Chinese))
[26]	王俊，胡瑞青，周晓军. 中砂层地层TBM掘进三维离散元研究[J]. 施工技术，2016，45(22)：19-21.(WANG Jun，HU Ruiqing，ZHOU Xiaojun. Study on the TBM tunneling in medium sandstone using 3D DEM[J]. Construction Technology，2016，45(22)：19-21.(in Chinese)).
[27]	ROSTAMI J. Study of pressure distribution within the crushed zone in the contact area between rock and disc cutters[J]. International Journal of Rock Mechanics and Mining Sciences，2013，57：172-186.
[29]	SALIMI A，ROSTAMI J，MOORMANN C，et al.，Application of non-linear regression analysis and artificial intelligence algorithms for performance prediction of hard rock TBMs[J]. Tunneling and Underground Space Technology，2016，58(2)：236-246.
[32]	张娜，李建斌，荆留杰，等. TBM掘进参数智能控制系统的研究与应用[J]. 隧道建设，2018，38(10)：150-156.(ZHANG Na，LI Jianbin，JING Liujie，et al. Study and application of intelligent control system of TBM tunneling parameters[J]. Tunnel Construction，2018，38(10)：150-156.(in Chinese))
[33]	QUINLAN J R. Induction on decision tree[J]. Machine Learning，1986，1(1)：81-106.
[35]	WYNER A D. Shannon-theoretic approach to a Gaussian cellular multiple-access channel[J]. IEEE Transactions on Information Theory，1994，40(6)：1 713-1 727.
[38]	RUDZIANSKAITE K，APANAVICIENE R R，GELZINIS A. Modelling the effectiveness of PPP road infrastructure projects by applying random forests[J]. Journal of Civil Engineering and Management，2015，21：290-299.
[9]	KIM J I，FISCHER M，KAM C. Generation and evaluation of excavation schedules for hard rock tunnels in preconstruction and construction[J]. Automation in Construction，2018，96(12)：378-397.
[16]	SUN W，SHI M L，ZHANG C，et al. Dynamic load prediction of tunnel boring machine(TBM) based on heterogeneous in-situ data[J]. Automation in Construction，2018，92(8)：23-34.
[24]	夏毅敏，朱湘衡，林赉贶，等. TBM刀盘掘进载荷影响因素研究[J]. 现代制造工程，2015，(9)：1-6.(XIA Yimin，ZHU Xiangheng，LIN Laikuang，et al. Analysis of influence factors on load of TBM cutterhead[J]. Modern Manufacturing Engineering，2015，(9)：1-6.(in Chinese))
[31]	罗华，陈祖煜，龚国芳，等. 基于现场数据的TBM掘进速率研究[J]. 浙江大学学报：工学版，2018，52(8)：141-149.(LOU Hua，CHEN Zuyu，GONG Guofang，et al. Advance rate of TBM based on field boring data[J]. Journal of Zhejiang University：Engineering Science，2018，52(8)：141-149.(in Chinese))
[34]	QUINLAN J R. Probabilistic decision trees[J]. Machine Learning，1990，3：140-152.
[39]	YU B，WANG H Z，SHAN W X，et al. Prediction of bus travel time using random forests based on near neighbors[J]. Computer-Aided Civil and Infrastructure Engineering，2018，33(4)：333--350.
[42]	EVERITT B S. Classification and regression trees[J]. Encyclopedia of Statistics in Behavioral Science，2005，1：287-290.
[6]	FRID V. Rockburst hazard forecast by electromagnetic radiation excited by rock fracture[J]. Rock Mechanics and Rock Engineering，1997，30(4)：229-236.
[7]	WANG J A，PARK H D. Comprehensive prediction of rockburst based on analysis of strain energy in rocks[J]. Tunnelling and Underground Space Technology，2001，16(1)：49-57.
[13]	HU M，ZHOU F，ZHANG Y，et al. Acoustic emission monitoring on damage evolution of surrounding rock during headrace tunnel excavation by TBM[J]. European Journal of Environmental and Civil Engineering，2019，23(10)：1 248-1 264.
[14]	ZHANG Q，LIU Z，TAN J. Prediction of geological conditions for a tunnel boring machine using big operational data[J]. Automation in Construction，2019，100(4)：73-83.
[20]	YAGIZ S，KARAHAN H. Application of various optimization techniques and comparison of their performances for predicting TBM penetration rate in rock mass[J]. International Journal of Rock Mechanics and Mining Sciences，2015，80：308-315.
[22]	顾健健. 地应力下TBM盘形滚刀载荷特性及破岩参数匹配研究[硕士学位论文][D]. 长沙：中南大学，2013.(GU Jianjian. Mechanical characteristics of TBM disc cutter under the crustal stress and the parameters matching researches of rock-breaking[M. S. Thesis][D]. Changsha：Central south University，2013.(in Chinese))
[28]	王超，龚国芳，杨华勇，等. NSVR硬岩隧道掘进机刀盘扭矩预测分析[J]. 浙江大学学报：工学版，2018，52(3)：479-486.(WANG Chao，GONG Guofang，YANG Huayong，et al. NSVR based predictive analysis of cutterhead torque for hard rock TBM[J]. Journal of Zhejiang University：Engineering Science，2018，52(3)：479-486.(in Chinese))
[36]	ABELLAN J，MANTAS C J，CASTELLANO J G. A random forest approach using imprecise probabilities[J]. Knowledge-Based Systems，2017，134：72-84.
[43]	SELIYA N，KHOSHGOFTAAR T M，The use of decision trees for cost-sensitive classification：an empirical study in software quality prediction[J]. Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery，2011，1(5)：448-459.
[45]	曹正凤. 随机森林算法优化研究[博士学位论文][D]. 北京：首都经济贸易大学，2014.(CAO Zhengfeng. Study on optimization of random forests algorithm[Ph. D. Thesis][D]. Beijing：Capital University of Economics and Business，2014.(in Chinese))
[40]	ZHOU J，SHI X Z，DU K，et al. Feasibility of random-forest approach for prediction of ground settlements induced by the construction of a shield-driven tunnel[J]. International Journal of Geomechanics，2017，17(6)：1-12.
[41]	NOJIMA Y，MIHARA S，ISHIBUCHI H. Application of parallel distributed genetics-based machine learning to imbalanced data sets[C]// 2012 IEEE International Conference on Fuzzy Systems. [S. l.]：[s. n.]，2012：1-6.
[44]	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. [S. l.]：[s. n.]，1995：1 137-1 145.
[46]	中华人民共和国国家标准编写组. GB50487—2008 水利水电工程地质勘察规范[S]. [S. l]：[s. n.]，2008.(The National Standards Compilation Group of the People's Republic of China. GB50487—2008 Code for Engineering geological investigation of water resources and hydropower[S]. [S. l]：[s. n.]，2008.(in Chinese))