摘要
在钻探施工条件的极端化和新一代信息技术发展引起的产业变革的双重影响下,钻探技术的智能化成为了钻探技术发展的必然趋势。文章聚焦于基于随钻关键参数的岩体智能识别这个最为关键的智能钻探难题,对基于钻进过程的不取心原位岩体测试技术进行综合阐述,最后对钻探工程的智能化发展进行展望。通过综述目前在该领域的最新技术和研究进展,提出了随钻过程-物理多模态信息深度融合的全新识别体系,以期实现钻探过程的岩土体智能识别能力,提高重大基础设施工程勘察质量和效率。
上天、入地、下海、登极是我国科学研究的重要抓力点。钻探技术作为入地的最关键手段,服务于几乎所有的工程领
以人工智能、机器学习、深度学习、图像识别等技术为基础,以智能采集、智能分析和设计、智能决策与反馈体系为表现形式的智能钻探成为地质勘查的必然趋
自20世纪80年代以来,研究人员发现岩体力学特征与钻进过程中钻具响应信息之间具有很强的相关性,试图研发随钻监测系统,通过监测钻进过程中的钻具参数变化快速评估钻孔沿线地质信息。随钻测量系统(MWD
在国内,香港大学岳中琦教授团队是最早系统性开展相关研究
国家 | 研 究 机 构 | 监 测 信 息 | 主 要 工 作 |
---|---|---|---|
国内 | 中国石油集团有限公司 | 温度、井底钻压、扭矩、涡轮钻速 | 通过对井下地质情况的实时监测,为安全、高效的油气开采提供有力保障 |
香港大学 | 转速、气压强、位移、轴力 | 基于自研DPM钻机的花岗岩随钻识别体系 | |
山东大学 | 钻压、扭矩、转速、钻速 | 岩石单轴抗压强度与剪切强度的随钻测试 | |
西安理工大学 | 钻进速率、透水率、电阻率、声波、灌浆量 | 不良地质体的智能判识 | |
中国科学院武汉岩土力学研究所 | 钻压、转速、扭矩、角度、进尺、钻速、振动、微震监测 | 综合随钻物探技术的岩溶随钻判识 | |
成都理工大学 | 钻压、转速、扭矩、钻速、振动、声音 | 砂泥岩、花岗岩、板岩地层的岩石力学参数,岩体质量等级随钻预测 | |
国外 | 斯伦贝谢、哈里伯顿、贝克休斯等公司 | 方位、倾角、旋转角速度、温度、钻压、振动 | MWD用于采矿工程、隧道工程和石油钻井领域,优点在于不妨碍钻孔操作,配备现有的地球物理勘探技术,能快速获取高分辨率的岩体质量图像 |
斯伦贝谢公司 | 地层电阻率、自然伽马辐射、声波传播速度、密度 、中子衰变 | LWD主要用于石油工程,可对钻孔进行电阻率CT、核磁共振、密度、孔隙率和钻具参数实时监测 |
基于随钻关键参数的岩体智能评价是钻探智能化的核心组成部分,主要涵盖数据采集智能化、决策智能化两个部

图1 智能钻探整体解决方案
Fig.1 Integrated solution for intelligent drilling
基于极限平衡原理,通过空间某点处的极限应力大于单轴抗压强度的基本假设,本文给出了基于随钻关键参数的岩石力学特征的本构模型(如

图2 基于随钻关键参数的岩石力学参数本构力学方法构建
Fig.2 Construction of rock mechanical parameters constitutive model based on key drilling parameters
基于“采集—传输—处理—分析—反馈”的流思想,在此基础上,系统性构建了基于随钻关键参数的物理-信息融合方法的随钻智能实时预测与评价体系,如

图3 基于物理-信息融合的智能化随钻岩石预测整体解决方案
Fig.3 Integrated solution for intelligent rock prediction during drilling based on physical‑information fusion
基于笔者所构建的物理-信息融合的智能化随钻岩体特征预测思想,将随钻测试的技术在几个代表性现场进行了应用。
某隧道边坡主要地层岩性为花岗岩,边坡的稳定性直接关系到铁路的正常通行,安全运行,需要准确地判断岩石的单轴抗压强度、粘聚力与内摩擦角。本文提出的评价方法实现了原位测试岩石的单轴抗压强度和剪切强度,为边坡的稳定性评价提供了原位真实的c、值,较之取心测试的结果相比,单轴抗压强度的相对误差在10%以内,c、值的相对误差在20%以内,且相比于取心测试的结果,其数值更能够准确地反映出岩石的原位力学状态,更好地为勘察设计服务(如

图4 隧道边坡地质岩体随钻调查
Fig.4 Drilling investigation of geological rock mass in tunnel side slopes
本应用场地位于四川西部某隧道掌子面,岩体破碎存在不良地质风险的问题。现场紧密结合超前地质钻探孔,基于岩体力学参数随钻智能测试仪获得了随钻数据,对岩石的单轴抗压强度进行随钻智能预测,最终的预测准确性与现场点荷载的判识结果相对误差保持在25%以内,分布规律与钻孔电视的结果保持基本一致(如

图5 隧道掌子面超前地质预报随钻调查
Fig.5 Drilling investigation for advanced geological prediction in tunnel face
某引水隧洞工程砂泥岩互层,且含有煤层,地下水大量发育,存在取心困难甚至无法取心的难题,传统的勘察技术方法无法准确定量评价岩石的强度与结构特征,采用本文所提出的基于随钻关键参数的评价体系,实现对工程前期取样岩体的岩体质量等级的准确评价,在不取心的情况下快速完成砂泥岩互层地质条件下岩体质量等级的随钻快速判识,准确率达到97%,能够实现对突变地层、地层界面、岩体强硬变化的随钻精确感知,如

图6 随钻技术在工程前期勘察的应用
Fig.6 Application of drilling technology in preliminary engineering investigation
本文对于基于随钻关键参数的岩体智能探测方法从研究现状、技术体系以及应用情况等做了综述,并提出了基于随钻关键参数物理-信息融合的整体解决方案与思路,并列举了几个工程的具体应用,取得了一定的效果,但依然存在着一定的不足。
(1)人工智能方法依赖大数据的驱动,受限于地下岩土体钻掘技术与施工组织安排的局限性,原位数据采集量还不够,训练基于真实数据的随钻智能反演模型存在很大的困难。
(2)物理方法的研究不够深入,特别是基于弹性力学的岩石破碎模型仅仅反映了岩石破碎的某个阶段的特有规律,岩石特别是岩体的裂解是一个十分复杂的非线性过程,需要从微观层面更深层次理解岩石的破坏过程,从而建立更为普适性的物理准则。
(3)物理-信息的融合模式决定了物理知识对于模型的约束能力和约束方式,针对随钻这种特定场合下的约束,应该有适应于数据特点的融合方法,这方面的研究还比较少。
(4)钻探智能化是服务于勘察、施工以及建造全过程的一种全新思想,如何将工程中的各个环节更好地融入智能钻探的技术体系中,是一个发展的重点。
参考文献
周英操,崔猛,查永进.控压钻井技术探讨与展望[J].石油钻探技术,2008,36(4):1-4. [百度学术]
ZHOU Yingcao, CUI Meng, ZHA Yongjin. Discussion and prospect of managed pressure drilling technology[J]. Petroleum Drilling Techniques, 2008,36(4):1-4. [百度学术]
冉恒谦,张金昌,谢文卫,等.地质钻探技术与应用研究[J].地质学报,2011,85(11):1806-1822. [百度学术]
RAN Hengqian, ZHANG Jinchang, XIE Wenwei, et al. Applications study of geo‑drilling technology[J]. Acta Geologica Sinica, 2011,85(11):1806-1822. [百度学术]
苏兴涛,冉灵杰,祝强,等.地表基质钻探取样技术方法与应用研究[J].地质论评,2023,69(6):2239-2246. [百度学术]
SU Xingtao, RAN Lingjie, ZHU Qiang, et al. Method and application research on drilling sampling techniques of surface substrate[J]. Geological Review, 2023,69(6):2239-2246. [百度学术]
石智军,姚克,姚宁平,等.我国煤矿井下坑道钻探技术装备40年发展与展望[J].煤炭科学技术,2020,48(4):1-34. [百度学术]
SHI Zhijun, YAO Ke, YAO Ningping, et al. 40 years of development and prospect on underground coal mine tunnel drilling technology and equipment in China[J]. Coal Science and Technology, 2020,48(4):1-34. [百度学术]
张林霞,李艺,周红军.我国地质找矿钻探技术装备现状及发展趋势分析[J].探矿工程(岩土钻掘工程),2012,39(2):1-8. [百度学术]
ZHANG Linxia, LI Yi, ZHOU Hongjun. Analysis on the present situation of drilling technical equipment and the development trend of geological prospecting in China[J]. Exploration Engineering (Rock & Soil Drilling and Tunneling), 2012,39(2):1-8. [百度学术]
吴纪修,尹浩,张恒春,等.水平定向勘察技术在长大隧道勘察中的应用现状与展望[J].钻探工程,2021,48(5):1-8. [百度学术]
WU Jixiu, YIN Hao, ZHANG Hengchun, et al. Application status and R & D trend of horizontal directional investigution technology for long tunnel investigution[J]. Drilling Engineering, 2021,48(5):1-8. [百度学术]
马映辉,贾宏福,李成志,等.某铁路勘察近水平孔取心钻探施工技术[J].地质与勘探,2021,57(1):190-197. [百度学术]
MA Yinghui, JIA Hongfu, LI Chengzhi, et al. Nearly‑horizontal borehole coring and drilling techniques in the survey of a railway[J]. Geology and Exploration, 2021,57(1):190-197. [百度学术]
肖华,刘建国,徐正宣,等.川藏铁路勘察超长水平孔绳索取心钻探技术[J].钻探工程,2021,48(5):18-26. [百度学术]
XIAO Hua, LIU Jianguo, XU Zhengxuan, et al. Wire‑line core drilling technology of ultra‑long horizontal investigation boreholes for the Sichuan-Tibet Railway[J]. Drilling Engineering, 2021,48(5):18-26. [百度学术]
王清峰,陈航.瓦斯抽采智能化钻探技术及装备的发展与展望[J].工矿自动化,2018,44(11):18-24. [百度学术]
WANG Qingfeng, CHEN Hang. Development and prospect on intelligent drilling technology and equipment for gas drainage[J]. Industry and Mine Automation, 2018,44(11):18-24. [百度学术]
李军,李勇,谢小国,等.狮子洋主航道水平勘察孔测井评价方法研究与应用[J].钻探工程,2022,49(6):21-29. [百度学术]
LI Jun, LI Yong, XIE Xiaoguo, et al. Research and application of the logging evaluation method for horizontal holes in the main channel of Shiziyang[J]. Drilling Engineering, 2022,49(6):21-29. [百度学术]
鄢泰宁,龚元明,姚爱国,等.钻探微机智能监测系统的研制与应用[J].探矿工程,1998(4):26-27,29. [百度学术]
YAN Taining, GONG Yuanming, YAO Aiguo, et al. The Development and Applications of the Intelligent Drilling Computer Monitor System [J]. Exploration Engineering, 1998(4):26-27,29. [百度学术]
房昱纬,吴振君,盛谦,等.基于超前钻探测试的隧道地层智能识别方法[J].岩土力学,2020,41(7):2494-2503. [百度学术]
FANG Yuwei, WU Zhenjun, SHENG Qian, et al. Intelligent recognition of tunnel stratum based on advanced drilling tests[J]. Rock and Soil Mechanics, 2020,41(7):2494-2503. [百度学术]
蒲清平,黄媛媛.习近平总书记关于新质生产力重要论述的生成逻辑、理论创新与时代价值[J].西南大学学报(社会科学版),2023,49(6):1-11. [百度学术]
PU Qingping, HUANG Yuanyuan. Generation logic, theoretical innovation and time value of general secretary Xi jinping’s important exposition on new quality productivity[J]. Journal of Southwest University (Social Sciences Edition), 2023,49(6):1-11. [百度学术]
黄群慧,盛方富.新质生产力系统:要素特质、结构承载与功能取向[J].改革,2024(2):15-24. [百度学术]
HUANG Qunhui, SHENG Fangfu. New productive forces system: factor characteristics, structural bearing and functional orientation[J]. Reform, 2024(2):15-24. [百度学术]
薛倩冰,张金昌.智能化自动化钻探技术与装备发展概述[J].探矿工程(岩土钻掘工程),2020,47(4):9-14. [百度学术]
XUE Qianbing, ZHANG Jinchang. Advances in intelligent automatic drilling technologies and equipment[J]. Exploration Engineering (Rock & Soil Drilling and Tunneling), 2020,47(4):9-14. [百度学术]
王新苗.智能开采工作面精细地质建模研究——以黄陵某工作面为例[D].北京:煤炭科学研究总院,2021. [百度学术]
WANG Xinmiao. Research on Fine Geological Modeling of intelligent Mining Face—Taking a face in Huangling as an example[D]. Beijing: China Coal Research Institute, 2021. [百度学术]
李文.基于钻进响应的岩石(体)特性识别理论与方法研究[D].北京:北京科技大学,2017. [百度学术]
LI Wen. Research on Theory and method for identification of rock mass properties based on drilling response[D]. Beijing: University of Science and Technology Beijing, 2017. [百度学术]
张幼振,范涛,阚志涛,等.煤矿巷道掘进超前钻探技术应用与发展[J].煤田地质与勘探,2021,49(5):286-293. [百度学术]
ZHANG Youzhen, FAN Tao, KAN Zhitao, et al. Application and development of advanced drilling technology for coal mine roadway heading[J]. Coal Geology & Exploration, 2021,49(5):286-293. [百度学术]
Chen J., Li S., & Wang Z.. Drilling technology in coal mining: Current status and development trends[J]. International Journal of Coal Geology, 2019,212:12-24. [百度学术]
朱恒银,王强,刘兵,等.5000 m新型能源勘探智能钻探装备与技术研究[J].钻探工程,2022,49(1):110-119. [百度学术]
ZHU Hengyin, WANG Qiang, LIU Bing, et al. Research on 5000m new energy exploration intelligent drilling equipment and technology[J]. Drilling Engineering, 2022,49(1):110-119. [百度学术]
甘超,汪祥,王鲁朝,等.基于区域多井数据优选与模型预训练的深部地质钻探过程钻速动态预测方法[J].钻探工程,2023,50(4):1-8. [百度学术]
GAN Chao, WANG Xiang, WANG Luchao, et al. Dynamic prediction method of rate of penetration(ROP)in deep geological drilling process based on regional multi‑well data optimization and model pre‑training[J]. Drilling Engineering, 2023,50(4):1-8. [百度学术]
周长春,姜杰,李谦,等.基于融合特征选择算法的钻速预测模型研究[J].钻探工程,2022,49(4):31-40. [百度学术]
ZHOU Changchun, JIANG Jie, LI Qian, et al. Research on drilling rate prediction model based on fusion feature selection algorithm[J]. Drilling Engineering, 2022,49(4):31-40. [百度学术]
甘超,曹卫华,王鲁朝,等.深部地质钻探钻进过程流式大数据分析与动态预处理——以辽宁丹东3000 m科学钻探工程为例[J].钻探工程,2022,49(4):1-7. [百度学术]
GAN Chao, CAO Weihua, WANG Luchao, et al. Streaming big data analysis and dynamic pre‑processing in deep geological drilling process: A case study on the 3000m scientific drilling project in Dandong, Liaoning province[J]. Drilling Engineering, 2022, 49(4): 1-7. [百度学术]
Rai P, Schunesson H, Lindqvist PA, et al. An overview on measurement‑while‑drilling technique and its scope in excavation industry[J]. Journal of The Institution of Engineers (India): Series D, 2015,96(1):57-66. [百度学术]
陈必权,王利斌,何万通,等.保德区块煤层气丛式井无线随钻测量技术(MWD)快速钻井施工工艺[J].中国煤炭地质,2020,32(4):67-71. [百度学术]
CHEN Biquan, WANG Libin, HE Wantong, et al. CBM cluster wells wireless MWD technology rapid drilling operation technology in baode block[J]. Coal Geology of China, 2020,32(4):67-71. [百度学术]
Reijonen J. Nuclear tools for oilfield logging‑while‑drilling applications[J]. AIP Conference Proceedings, 2011,1336(7):433-436. [百度学术]
Liu L., Li S., Jiang X., et al. A new two‑sensor non‑destructive testing method of grouted rock bolts[J]. Constr Build Mater, 2022,317:125919.. [百度学术]
Yue Z. Q., Lee C. F., Law K. T., et al. Automatic monitoring of rotary‑percussive drilling for ground characterization—Illustrated by a case example in Hong Kong[J]. Int J Rock Mech Min Sci, 2004,41(4):573-612. [百度学术]
谭卓英,岳中琦,谭国焕,等.金刚石钻进能量与花岗岩地层风化程度的关系[J].北京:北京科技大学学报,2008,168(4): 339-343. [百度学术]
TAN Zhuoying, YUE Zhongqi, TAN Guohuan, et al. Relationship between diamond penetrating energy and weathered degree in granite formation[J]. Journal of University of Science and Technology Beijing, 2008,30(4):339-343. [百度学术]
田昊,李术才,薛翊国,等.基于钻进能量理论的隧道凝灰岩地层界面识别及围岩分级方法[J].岩土力学,2012,33(8):2457-2464. [百度学术]
TIAN Hao, LI Shucai, XUE Yiguo, et al. Identification of interface of tuff stratum and classfication of surrounding rock of tunnel using drilling energy theory[J]. Rock and Soil Mechanics, 2012,33(8):2457-2464. [百度学术]
高红科,王琦,李术才,等.注浆岩体强度随钻评价试验研究[J].采矿与安全工程学报,2021,38(2):326-333. [百度学术]
GAO Hongke, WANG Qi, LI Shucai, et al. Experimental study on the while‑drilling evaluation of the strength of grouted rock mass[J]. Journal of Mining and Safety Engineering, 2021,38(2):326-333. [百度学术]
Bai J., Wang S., Xu Q., et al. Intelligent regional subsurface prediction based on limited borehole data and interpretability stacking technique of ensemble learning[J]. Bull Eng Geol Environ, 2024,83(7):272. [百度学术]
尹生阳,曾维,王胜,等.基于声波信号的岩性智能分类方法[J].吉林大学学报(地球科学版),2022,52(6):2060-2070. [百度学术]
YIN Shengyang, ZENG Wei, WANG Sheng, et al. Lithology intelligent classification method based on acoustic signal[J]. Journal of Jilin University(Earth Science Edition), 2022,52(6):2060-2070. [百度学术]
王胜,赖昆,张拯,等.基于随钻振动信号与深度学习的岩性智能预测方法[J].煤田地质与勘探,2023,51(9):51-63. [百度学术]
WANG Sheng, LAI Kun, ZHANG Zheng, et al. Intelligent lithology prediction method based on vibration signal while drilling and deep learning[J]. Coal Geology & Exploration, 2023,51(9):51-63. [百度学术]
Bai J., Wang S., Xu Q., et al. Intelligent real‑time predicting method for rock characterization based on multi‑source information integration while drilling[J]. Bull Eng Geol Environ, 2023,82(4):150. [百度学术]
张鑫.滑动定向钻探过程的智能决策算法研究与实现[D].成都:电子科技大学,2020. [百度学术]
ZHANG Xin. Research and implementation of intelligent decision algorithm for sliding directional drilling[D]. Chengdu: University of Electronic Science and Technology of China, 2020. [百度学术]
孙平贺.火星取样钻探技术分析[J].探矿工程(岩土钻掘工程),2018,45(10):160-165. [百度学术]
SUN Pinghe. Study on Mars sample drilling technology[J]. Exploration Engineering (Rock & Soil Drilling and Tunneling), 2018, 45(10): 160-165. [百度学术]
吴桐.工程勘察钻探现场质量信息采集与智能分析系统研究[D].南京:东南大学,2021. [百度学术]
WU Tong. Research on acquisition and intelligent analysis syetem of geotechnical drilling[D]. Nanjing: Southeast University, 2021. [百度学术]
王滨,赵铁龙.工程地质钻探中的智能控制技术[J].林业科技情报,2011,43(3):86-87. [百度学术]
WANG Bin, ZHAO Tielong. Intelligent control technique in engineering geology drilling[J]. Forestry Science and Technology Information, 2011(3):86-87. [百度学术]
贾晓亮,秦怡.煤矿坑道钻探钻杆断裂智能CT检测研究[J].煤炭科学技术,2021,49(3):135-140. [百度学术]
JIA Xiaoliang, QIN Yi. Research on intelligent CT detection of drill pipe fracture in coal mine tunnel drilling[J]. Coal Science and Technology, 2021,49(3):135-140. [百度学术]
李仁发,谢勇,李蕊,等.信息-物理融合系统若干关键问题综述[J].计算机研究与发展,2012,49(6):1149-1161. [百度学术]
LI Renfa, XIE Yong, LI Rui, et al. Survey of Cyber-Physical systems[J]. Journal of Computer Research and Development, 2012,49(6):1149-1161. [百度学术]
Poblet J., Bulnes M., Uzkeda H., et al. Using the schmidt hammer on folds: An example from the Cantabrian Zone (NW Iberian Peninsula)[J]. J. Struct. Geol., 2022,155:104512. [百度学术]