Relying on 1 765 drilling parameter samples from the Yichang-Zhengwan High-Speed Railway tie-line tunnel project, based on the analysis of the time series curve characteristics of drilling parameters, a classification feature extraction method of surrounding rock of drilling parameters based on dynamic linear piecewise representation is proposed by combining Bayesian confidence interval test, dynamic linear piecewise representation, Kalman filtering and linear piecewise mean processing methods. The application effect of this method is verified through comparing discreteness and difference of drilling parameter samples of tunnel face before and after processing, and the accuracy of surrounding rock classification model under 6 different kinds of machine learning algorithms before and after processing. The results show that the time series of drilling parameters has obvious characteristics of longitudinal piecewise, interval fluctuation and random dispersion. After processing with this method, the average standard deviation of sample data under the same surrounding rock level is reduced by 28.72%-82.68%, and the average distance between sample classes under different surrounding rock level is increased by 66.79%-77.37%. The classification accuracy of surrounding rock classification model under 6 machine learning algorithms is improved from 85.3%-88.8% to 88.1%-89.9%. As a basic data processing method, it can avoid the influence of various non-geological factors on the classification accuracy of surrounding rock, better reflect the good response relationship between drilling parameters and surrounding rock quality, and improve the accuracy of surrounding rock quality evaluation in concrete practice.
钻进参数监测技术在国外又被称为随钻测量(Measurement while Drilling,MWD),目前已广泛应用于采矿、冶金和地质勘探领域[4-5]。已有研究证实各钻进参数之间存在相互影响[6-7],且逐渐形成并用多项钻进参数(如钻进速度、操作压力、转速和反馈压力)而非仅用单个钻进参数(如钻进速度)的共识[8-9]。如在表征岩石质量时,钻进参数可用于估算岩体特征,如节理或裂缝、岩石界面和岩石质量指标(RQD)等[10-12],多项钻进参数还可有效估计岩石的某些力学性质,如单轴饱和抗压强度、岩石剪切强度等[13-15]。在此基础上,许多学者开始尝试在隧道施工阶段直接使用钻进参数进行围岩分级,并在RMR法[16]、Q方法[17]、ROS方法[18]以及基于岩体质量指标(BQ)的国内隧道围岩分类方法[19-21]等多个现有围岩分类体系下取得良好成效。
基于钻进参数的围岩分级属于机器学习中的分类任务,而基于机器学习的样本分类在本质上属于在参数空间内找寻决策分类面。理论上无论何种算法,各类样本输入参数空间差异性越大、越容易找到更优的决策分类面[24]。为定量衡量各类样本输入参数空间的差异性,定义类间距离Dc(Distance Between Classes),计算式见式(4),其含义为2个样本钻进参数数据空间的欧式距离。
WANGZhijian. Status and Prospect of Intelligent Construction Technology of Tunnel of Zhengzhou-Wanzhou High-Speed Railway [J]. Tunnel Construction, 2021, 41 (11): 1877-1890. in Chinese
YUEZhongqi. Drilling Process Monitoring for Refining and Upgrading Rock Mass Quality Classification Methods [J]. Chinese Journal of Rock Mechanics and Engineering, 2014, 33 (10): 1977-1996. in Chinese
YIWenhao, WANGMingnian, TONGJianjun, et al. Inhomogeneity Identification Method for Surrounding Rock of Large-Section Rock Tunnel Face Based on Support Vector Machine [J]. China Railway Science, 2021, 42 (5): 112-122. in Chinese
[7]
MANZOORS, LIAGHATS, GUSTAFSONA, et al. Establishing Relationships between Structural Data from Close-Range Terrestrial Digital Photogrammetry and Measurement while Drilling Data [J]. Engineering Geology, 2020, 267: 105480.
YUEZhongwen, YUEXiaolei, YANGRenshu, et al. Progress of Lithology Identification Technology while Drilling [J]. Journal of Mining Science and Technology, 2022, 7 (4): 389-402. in Chinese
BIYongsheng, TANZhuoying, DINGYu. Study on Interaction Mechanism of Drilling Parameters Based on Finite Element Method [J]. Metal Mine, 2022 (2): 19-28. in Chinese
[16]
LIY L, SHEL, WENL F, et al. Sensitivity Analysis of Drilling Parameters in Rock Rotary Drilling Process Based on Orthogonal Test Method [J]. Engineering Geology, 2020, 270: 105576.
LIZhe, XUBaozhi, NONGJi. Analysis of Work-Velocity Ratio and Response Characteristics of Surrounding Rock in Tunnel Advance Horizontal Drilling [J]. Chinese Journal of Underground Space and Engineering, 2018, 14 (): 136-147. in Chinese
LIUZonghui, GUANQiyu, RAOKunrong, et al. Precise Prediction Method for Advanced Drilling of Tunnel in Karst Area Based on Energy Theory [J]. Highway, 2021, 66 (11): 342-349. in Chinese
TANZhuoying, CAIMeifeng, YUEZhongqi, et al. Identification of Interface of Earth Fill with Weathered Granite in Site Investigation of Hong Kong [J]. Chinese Journal of Geotechnical Engineering, 2007, 29 (2): 169-173. in Chinese
TIANXuehao, KANGJia’an, JIANGShuai, et al. Research on Geological Prediction System of Rock Drilling Jumbo Based on Least Squares Support Vector Machine [J]. Tunnel Construction, 2022, 42 (): 267-273. in Chinese
[25]
KALANTARIS, HASHEMOLHOSSEINIH, BAGHBANANA. Estimating Rock Strength Parameters Using Drilling Data [J]. International Journal of Rock Mechanics and Mining Sciences, 2018, 104: 45-52.
WANGQi, QINQian, GAOSong, et al. Relationship between Rock Drilling Parameters and Rock Uniaxial Compressive Strength Based on Energy Analysis [J]. Journal of China Coal Society, 2018, 43 (5): 1289-1295. in Chinese
[28]
GALENDE-HERNÁNDEZM, MENÉNDEZM, FUENTEM J, et al. Monitor-while-Drilling-Based Estimation of Rock Mass Rating with Computational Intelligence: the Case of Tunnel Excavation Front [J]. Automation in Construction, 2018, 93: 325-338.
[29]
VAN ELDERTJ, SCHUNNESSONH, JOHANSSOND, et al. Application of Measurement while Drilling Technology to Predict Rock Mass Quality and Rock Support for Tunnelling [J]. Rock Mechanics and Rock Engineering, 2020, 53 (3): 1349-1358.
[30]
LIUJ K, JIANGY J, HANW, et al. Optimized ANN Model for Predicting Rock Mass Quality ahead of Tunnel Face Using Measure-while-Drilling Data [J]. Bulletin of Engineering Geology and the Environment, 2021, 80 (3): 2283-2305.
[31]
姚萌. 基于凿岩台车钻进参数的隧道围岩智能分级方法研究[D]. 成都:西南交通大学,2020.
[32]
YAOMeng. Study on Intelligent Classification of Surrounding Rock Based on Drilling Jumbo’s Drilling Parameters [D]. Chengdu: Southwest Jiaotong University, 2020. in Chinese
[33]
ZHAOS G, WANGM N, YIW H, et al. Intelligent Classification of Surrounding Rock of Tunnel Based on 10 Machine Learning Algorithms [J]. Applied Sciences, 2022, 12 (5): 2656.
[34]
WANGM N, ZHAOS G, TONGJ J, et al. Intelligent Classification Model of Surrounding Rock of Tunnel Using Drilling and Blasting Method [J]. Underground Space, 2021, 6 (5): 539-550.
[35]
SCHUNNESSONH, HOLMEK. Drill Monitoring for Geological Mine Planning in the Viscaria Copper Mine [J]. CIM Bulletin, 1997, 90: 83-89.
[36]
SCHUNNESSONH. Rock Characterisation Using Percussive Drilling [J]. International Journal of Rock Mechanics and Mining Sciences, 1998, 35 (6): 711-725.
SHUYunxing. Research on Fault Diagnosis and Quality Prediction Using Support Vector Machines in Cement Burning System [D]. Wuhan: Wuhan University of Technology, 2008. in Chinese
[39]
刘飞香.隧道全电脑凿岩台车技术及应用[M].北京:人民交通出版社,2019.
[40]
LIUFeixiang. Tunnel Full Computerized Drill Jumbo Technology and Application [M]. Beijing: China Communications Press, 2019. in Chinese
XUXuefeng, ZHOUZhihong, TIANXiang, et al. Technical Characteristics of Hydraulic Drifters from France-Based Montabert [J]. Rock Drilling Machinery & Pneumatic Tools, 2019 (1): 1-15. in Chinese
[43]
SCHUNNESSONH. Drill Process Monitoring in Percussive Drilling: a Multivariate Approach to Data Analysis [M]. Finland: Lapland University of Applied Sciences, 1990.
WANGZhijian. Research on Key Technology of Large Cross-Sectional Mechanized Construction of Zhengzhou-Wanzhou High-Speed Railway Tunnel [J]. Tunnel Construction, 2018, 38 (8): 1257-1270. in Chinese
[46]
WANGC J, YAOC R, QIANGB, et al. A Machine Learning Framework for Predicting Bridge Defect Detection Cost [J]. Infrastructures, 2021, 6 (11): 152.
CHENShuaifei, XinLÜ, QIRongzhi, et al. Linear Representation Method Based on Key Points for Time Series [J]. Computer Science, 2016, 43 (5): 234-237. in Chinese
YANLi, DENGFangming. Defect Detection Scheme for Key Equipment of Transmission Line in Complex Environment [J]. Radio Engineering, 2022, 52 (12): 2237-2244. in Chinese
QUJia, WANGXudong, WUNan, et al. Indoor Visible Light Fingerprint Positioning Method Based on Random Forest Algorithm [J]. Optical Communication Technology, 2023, 47 (1): 1-7. in Chinese
[53]
WANGC J, YAOC R, ZHAOS G, et al. The Theory and Method of Data Acquisition of Mixed Traffic Popular People and Nonmotor Vehicles Based on Image Processing [J]. Mobile Information Systems, 2022, 2022: 9699162.