A Rock Drillability Characterization Method Based on Big Data and Unsupervised Clustering Algorithm

doi:10.12388/j.issn.1673-2677.2024.02.004

Abstract

Abstract:

The evaluation of rock drillability is of great significance in geological prospecting and drilling engineering. The traditional evaluation methods are mainly based on the core drillability testing，but due to the technical difficulties and high costs of coring，new unsupervised learning methods have become increasingly important. This study proposes a continuous formation drillability evaluation method based on well logging big data and unsupervised clustering algorithm to address this issue. Firstly，a self-organizing mapping neural network is used to cluster a large amount of well logging data and effectively extracting and classifying stratigraphic features. Then，by analyzing the penetration rate distribution of the formation corresponding to each cluster，the formation is graded by six drillability levels，thus achieving effective evaluation of the formation drillability. The core value of this study lies in utilizing big data and advanced unsupervised learning algorithms to overcome the reliance on a large number of core drillability test results in traditional methods，and deliver significantly improved evaluation performance. Through this method，the drillability classification of formations of the test well is successfully carried out，which validates the effectiveness of the method. The research results show that as the drillability level increases，the average penetration rate of the formation gradually decreases，and compared with the core test method，no notable deviation of the rock drillability level classification results is observed. This finding further confirms the importance and accuracy of this method in continuous formation drillability evaluation.

Key words:

drilling, drillability, machine learning, rate of penetration, neural network, big data

摘要：

岩石可钻性的评估在地质勘探和钻井工程中具有重要意义。传统的评价方法主要基于岩心可钻性测试结果，但受制于岩心获取困难和费用昂贵的限制，开发新的无监督学习方法变得愈发重要。针对这一问题，提出了基于测井大数据和无监督聚类算法的连续地层可钻性评估方法。首先，利用自组织映射神经网络对大量的测井数据进行聚类，将地层特征进行有效提取和分类；然后，通过分析每个聚类对应地层的机械钻速分布，将地层分成了6个可钻性等级，从而实现了对地层可钻性的有效评估。这项研究的核心价值在于利用了大数据和先进的无监督学习算法，克服了传统方法中对大量岩心可钻性测试结果的依赖，并取得了显著的成果。通过该方法成功对测试井地层进行了可钻性分级，并验证了其有效性。研究结果显示，随着可钻性等级的增加，地层所对应的平均机械钻速逐渐降低；并且与岩心实测法相比较，模型得到的岩石可钻性等级划分结果偏差不大。这一结果进一步印证了该方法在连续地层可钻性评估中的重要性和准确性。

关键词:

钻井, 可钻性, 机器学习, 机械钻速, 神经网络, 大数据

CLC Number:

TE24 ','1');return false;" target="_blank">
TE24

TIAN Long, ZHU Zhihua, WANG Liwei, YU Jiawei, WANG Yifan.

A Rock Drillability Characterization Method Based on Big Data and Unsupervised Clustering Algorithm

[J]. Xinjiang Oil & Gas, 2024, 21(2): 29-.

田龙, 朱智华, 王立伟, 于佳伟, 王一帆.

基于大数据和无监督聚类算法的岩石可钻性表征和预测方法

[J]. 新疆石油天然气, 2024, 21(2): 29-.

References

［1］王颖颖，庄毅，孙逸帆. 基于粒子群优化BP神经网络的可靠性评估模型［J］. 计算机与现代化，2022，（12）：42-49.WANG Y Y，ZHUANG Y，SUN Y F. Reliability evaluation model of BP neural network based on particle swarm optimization［J］. Computer and Modernization，2022，（12）：42-49.

［2］孔祥伟，陈昊，叶佳杰，等. 基于PCA预测岩石可钻性级值的钻头优选［J］. 新疆石油天然气，2022，18（3）：6-11.KONG X W，CHEN H，YE J J，et al. Bit selection based on PCA to predict drillability level of hard rocks［J］ Xinjiang Oil & Gas，2022，18（3）：6-11.

［3］胡宗敏，张立刚，罗光东，等. 基于元素录井的深层火成岩抗钻特性评价［J］. 录井工程，2023，34（1）：24-28.HU Z M, ZHANG L G, LUO G D, et al. Evaluation of anti-drilling properties of deep igneous rocks based on element logging［J］. Mud Logging Engineering, 2023，34（1）：24-28.

［4］CAGNATO C，NLEND P，NGOUOH F，et al. Analysis of early Iron Age （2500 BP） and modern period （150 BP） starch grains in Western Central Africa［J］. Scientific Reports，2022，12（1）：18956.

［5］史晓亮，段隆臣，王蕾，等. 微钻法进行岩石可钻性分级［J］. 金刚石与磨料磨具工程，2002，42（3）：32-34.SHI X L，DUAN L C，WANG L，et al. Classification of rock drillability using micro drilling method［J］. Diamond and Abrasive Engineering，2002，42（3）：32-34.

［6］ANDREWS R，HARELAND G，NYGAARD R，et al. Methods of using logs to quantify drillability［C］. Rocky Mountain Oil & Gas Technology Symposium，Denver，Colorado，USA，April 2007.

［7］王亚飞，张占荣，刘华吉，等. 基于模型融合的钻进参数识别岩石类型研究［J］钻探工程，2023，50（2）：17-25.WANG Y F，ZHANG Z R，LIU H J，et al. Data⁃driven model for the identification of the rock type by drilling data［J］. Drilling Engineering，2023，50（2）：17-25.

［8］MA H，WANG Y J. Formation drillability prediction based on PSO-SVM［C］. IEEE 10th International Conference on Signal Processing，2010：2497-2500.

［9］MA H. Formation drillability prediction based on multi-source information fusion［J］. Journal of Petroleum Science and Engineering. 2011，78 （2）：438-446.

［10］OLORUNTOBI O，BUTT S. Application of specific energy for lithology identification［J］. Journal of Petroleum Science and Engineering，2020，184：106402.

［11］张辉，高德利. 钻头下部未钻开地层的可钻性预测新方法［J］. 石油学报，2006，27（1）：97-100.ZHANG H，GAO D L. A new method for predicting the drillability of un-drilled formation［J］. Acta Petrolei Sinica，2006，27（1）：97-100

［12］SAEIDI O，TORABI S R，ATAEI M，et al. Development of a new index to assess the rock mass drillability［J］. Geotechnical and Geological Engineering，2013，31（5）：1477-1495.

［13］GAN C，CAO W H，WU M，et al. Intelligent Nadaboost-ELM modeling method for formation drillability using well logging data［J］. Journal of Advanced. Computational Intelligence and Intelligent Informatics，2016，20（7）：1103-1111.

［14］董青青，梁小丛. 基于优化的BP神经网络地层可钻性预测模型［J］. 探矿工程（岩土钻掘工程），2012，39（11）：26-28.DONG Q Q，LIANG X C. A model for predicting formation drillability based on optimized BP neural network［J］. Exploration Engineering （Rock & Soil Drilling and Tunneling），2012，39 （11）：26-28.

［15］杜宇，潘遥. 基于GA-BP神经网络岩石可钻性预测模型［J］. 科学技术创新，2020，（25）：57-59.DU Y，PAN Y. Rock drillability prediction model based on GA-BP neural network［J］. Scientific and Technological Innovation，2020，（25）：57-59.

［16］FANG X X，FENG H，WANG H. Study on intelligent prediction method of rock drillability based on Bayesian lithology classification and optimized BP neural network［J］. Petroleum Science and Technology，2022，40（17）：2141-2162.

［17］蒲先渤，李泽群，尹飞，等. 基于PCA-LM-BP神经网络的岩石可钻性预测研究［J］. 钻探工程，2023，50（6）：63-68.PU X B，LI Z Q，YIN F，et al. Research on rock drillability prediction based on PCA-LM-BP neural network［J］. Drilling Engineering，2023，50（6）：63-68.

［18］HE M M，ZHANG Z Q，REN J，et al. Deep convolutional neural network for fast determination of the rock strength parameters using drilling data［J］. International Journal of Rock Mechanics and Mining Sciences，2019，123：104084.

［19］HE M M，LI N，ZHU J W，et al. Advanced prediction for field strength parameters of rock using drilling operational data from impregnated diamond bit［J］. Journal of Petroleum Science and Engineering，2020，187：106847.

［20］甘超. 复杂地层可钻性场智能建模与钻速优化［D］. 湖北武汉：中国地质大学，2019.GAN C. Intelligent modeling and drilling speed optimization of complex formation drillability field［D］. Wuhan，Hubei：China University of Geosciences，2019.

［21］XU R，WUNSCH D. Survey of clustering algorithms［J］. IEEE Transactions on Neural Networks，2005，16（3）：645-678.

［22］张文博，冯梅，李青. 分类和聚类算法在油气领域的应用研究［J］. 信息系统工程，2022（9）：59-62.ZHANG W B，FENG M，LI Q. Research on application of classification and clustering algorithms in the field of oil and gas［J］. China CIO News，2022 （9）：59-62.

［23］KOHONEN T. The self-organizing map［J］. Proceedings of the IEEE，1990，78（9）：1464-1480.

［24］李根，杨剑征，刘祺. 基于SOM-BP神经网络的船舶柴油机故障诊断方法［J］. 舰船科学技术，2023，45（22）：121-125.LI G，YANG J Z，LIU Q. Marine diesel engine fault diagnosis method based on SOM-BP neural network［J］ Ship Science and Technology，2023，45 （22）：121-125.

［25］郭昊天，张超越，郑新潮，等. 基于SOM-BiGRU串联神经网络的电费收入预测研究［C］. 吉林省电机工程学会. 吉林省电机工程学会2023年学术年会获奖论文集. 国网延边供电公司；国网吉林供电公司，2023：9.GUO H T，ZHANG C Y，ZHENG X C，et al. Research on electricity revenue prediction based on SOM-BiGRU series neural network［C］. 2023 Academic Annual Conference of Jilin Electric Engineering Society，State Grid Yanbian Power Supply Company；State Grid Jilin Power Supply Company，2023：9.

[1]	SHENG Mao, JIANG Fumin, HU Shimeng, LYU Zhenhu, KONG Mingwei, SI Lijuan, . The In-Situ Stress Interpretation in Heterogeneous Glutenite Reservoirs and Fracturing Design Optimization [J]. Xinjiang Oil & Gas, 2024, 21(2): 1-.
[2]	ZHONG Yiming, KEDILIYA Palihati, BAI Jiashuai, WANG Chaochen, LI Qihao. Real-Time Monitoring Model of PDC Bit Wear Based on GRU Neural Network [J]. Xinjiang Oil & Gas, 2024, 21(2): 21-.
[3]	PU Wanfen, JIN Xing, TANG Xiaodong, BAI Yuanyuan, WANG Aoyu. Prediction Model of Water Breakthrough Patterns of Low-Permeability Bottom Water Reservoirs Based on BP Neural Network [J]. Xinjiang Oil & Gas, 2024, 21(2): 37-.
[4]	LI Gensheng, MU Zongjie, TIAN Shouceng, HUANG Zhongwei, SUN Zhaowei. Research Status and Development Proposal of ROP Improvement Technology with Percussion Rock-Breaking Method [J]. Xinjiang Oil & Gas, 2024, 20(1): 1-12.
[5]	LIU Fan, LIU Yushuang, ZHANG Zhen, LI Yongjian, LIU Ce, MA Zhihu, . A Machine Learning-Based Bridging Particle Size Recommendation Method for Lost Circulation Control [J]. Xinjiang Oil & Gas, 2024, 20(1): 13-20.
[6]	SONG Xianzhi, GUO Yong, XIANG Dongmei, JU Pengfei, TAN Qiang, LIU Wei. Multi-Field Coupling Analysis of Wellbore Instability in Hutubi Anticline While Using Water-Based Drilling Fluid [J]. Xinjiang Oil & Gas, 2023, 19(4): 1-9.
[7]	LUO Ling , LI Yichang , WEI Liyao. Use of Metaverse Technology Clusters and Quantum Computing in CCUS：Research Status and Trends#br# [J]. Xinjiang Oil & Gas, 2023, 19(3): 86-94.
[8]	LI JingSong, LIU Zixiong, KOU Shuangyan, ZHANG Xiuming, LIU Rumin, WANG Jinwei. Study on Main Controlling Factors of Water Production in Tight Gas Wells [J]. Xinjiang Oil & Gas, 2022, 18(4): 20-25.
[9]	KONG Xiangwei, CHEN Hao, YE Jiajie, LI Yadong, GAN Yifeng. Bit Selection Based on PCA to Predict Drillability Level of Hard Rocks [J]. Xinjiang Oil & Gas, 2022, 18(3): 6-11.
[10]	LI Hongbo, LUO Pingya, BAI Yang, LI Daoxiong, CHANG Shuang, LIU Xinguo . Summary for Machine Learning Algorithms and Their Applications in Drilling Engineering [J]. Xinjiang Oil & Gas, 2022, 18(1): 1-13.
[11]	SONG Xianzhi, PEI Zhijun, WANG Pantao, ZHANG Gonglingyan, YE Shanlin. Intelligent Prediction for Rate of Penetration Based on Support Vector Machine Regression [J]. Xinjiang Oil & Gas, 2022, 18(1): 14-20.