Coal Geology & Exploration


The accurate characterization and dynamic analysis of drilling string mechanics are essential to ensure the safe and efficient drilling. In the classical soft/rigid string model for drag & torque of drilling string, the friction coefficient of the drilling string is determined by empirical estimation or post-drilling inversion, of which the accuracy and timeliness needs to be improved. Based on the effectiveness of artificial intelligence technology applied in complex nonlinear mapping, a drag and torque prediction method of drill string with mechanism-data fusion was proposed by predicting the friction coefficient. Firstly, the friction coefficient was inversed using the drilled and logged well data and the soft-string model, which provides the data basis for intelligent prediction of friction coefficient. As a result of the data processing and quantitative feature analysis of 74 wells, a Long Short-Term Memory (LSTM) network considering data series features was established, and the reasonability of the model was verified through drag & torque prediction and the interpretability analysis by Shapley Additive explanation (SHAP). The results show that the prediction error of the friction coefficient is 5.89%, and the prediction error of drag & torque is reduced by 4.41%. The mapping relationship between the input features of the model characterization and the friction coefficient is consistent with the mechanical mechanism of drilling string, which indicates that the model has strong stability and interpretability. Generally, this method could provide the theoretical and technical support for accurate characterization and dynamic analysis of drilling string mechanics.


intelligent prediction, drag & torque of drill string, friction coefficient, mechanism-data fusion, interpretability, deep learning




[1] 方浩舟. 山区页岩气大位移水平井管柱摩阻/扭矩分析研究[D]. 北京:中国石油大学(北京),2018.

FANG Haozhou. Analysis of drag & torque on downhole tubular string in horizontal well for shale gas in mountainous area[D]. Beijing:China University of Petroleum (Beijing),2018.

[2] 朱硕,宋先知,李根生,等. 钻柱摩阻扭矩智能实时分析与卡钻趋势预测[J]. 石油钻采工艺,2021,43(4):428−435.

ZHU Shuo,SONG Xianzhi,LI Gensheng,et al. Intelligent real–time drag and torque analysis and sticking trend prediction of drill string[J]. Oil Drilling & Production Technology,2021,43(4):428−435.

[3] JOHANCSIK C A,FRIESEN D B,DAWSON R. Torque and drag in directional wells–prediction and measurement[J]. Journal of Petroleum Technology,1984,36(6):987−992.

[4] LESAGE M,FALCONER I G,WICK C J. Evaluating drilling practice in deviated wells with torque and weight data[J]. SPE Drilling Engineering,1992,3(3):248−252.

[5] BRETT J F,BECKETT A D,HOLT C A,et al. Uses and limitations of drillstring tension and torque models for monitoring hole conditions[J]. SPE Drilling Engineering,1992,4(3):223−229.

[6] 黄文君,高德利. 受井眼约束带接头管柱的纵横弯曲分析[J]. 西南石油大学学报(自然科学版),2015,37(5):152−158.

HUANG Wenjun,GAO Deli. Deflection analysis of a tubular string with connectors constrained in a wellbore[J]. Journal of Southwest Petroleum University (Science & Technology Edition),2015,37(5):152−158.

[7] 李井辉,申静波,闫铁,等. 基于BP神经网络的摩擦系数预测方法研究[J]. 数学的实践与认识,2015,45(23):179−185.

LI Jinghui,SHEN Jingbo,YAN Tie,et al. The research of friction coefficient prediction based on BP neural network[J]. Mathematics in Practice and Theory,2015,45(23):179−185.

[8] 韩志勇. 井眼内钻柱摩阻的三维和两组模型的研究[J]. 石油大学学报(自然科学版),1993,17:6.

HAN Zhiyong. Three–dimensional and two–group models of drill string friction in borehole[J]. Journal of China University of Petroleum (Edition of Natural Sciences),1993,17:6.

[9] 秦永和,付胜利,高德利. 大位移井摩阻扭矩力学分析新模型[J]. 天然气工业,2006,26(11):77−79.

QIN Yonghe,FU Shengli,GAO Deli. A new model for analyzing torque and drag in extended reach wells[J]. Natural Gas Industry,2006,26(11):77−79.

[10] ZHU Shuo,SONG Xianzhi,ZHU Zhaopeng,et al. Intelligent prediction of stuck pipe using combined data–driven and knowledge–driven model[J]. Applied Sciences,2022,12(10):5282.

[11] HEGDE C,MILLWATER H,GRAY K. Classification of drilling stick slip severity using machine learning[J]. Journal of Petroleum Science and Engineering,2019,179:1023−1036.

[12] 丁培宇. 基于实测数据的摩阻扭矩预测[D]. 青岛:中国石油大学(华东),2014.

DING Peiyu. Drag and torque forecast based on measured data[D]. Qingdao:China University of Petroleum (East China),2014.

[13] 申静波,闫铁,李井辉,等. 基于改进BP算法的摩阻因数预测方法研究[J]. 计算机技术与发展,2018,28(1):164−168.

SHEN Jingbo,YAN Tie,LI Jinghui,et al. Research on friction coefficient prediction based on improved BP algorithm[J]. Computer Technology and Development,2018,28(1):164−168.

[14] 祝兆鹏,张瑞,宋先知,等. 数据拓展和增量更新的井底压力实时预测方法[J]. 石油机械,2023,51(6):1−10.

ZHU Zhaopeng,ZHANG Rui,SONG Xianzhi,et al. Real–time prediction of bottomhole pressure based on data expansion and incremental update[J]. China Petroleum Machinery,2023,51(6):1−10.

[15] 李根生,宋先知,田守嶒. 智能钻井技术研究现状及发展趋势[J]. 石油钻探技术,2020,48(1):1−8.

LI Gensheng,SONG Xianzhi,TIAN Shouceng. Intelligent drilling technology research status and development trends[J]. Petroleum Drilling Techniques,2020,48(1):1−8.

[16] 李根生,宋先知,祝兆鹏,等. 智能钻完井技术研究进展与前景展望[J]. 石油钻探技术,2023,51(2):1−13.

LI Gensheng,SONG Xianzhi,ZHU Zhaopeng,et al. Research progress and prospect of intelligent drilling and completion technology[J]. Petroleum Drilling Techniques,2023,51(2):1−13.

[17] 黄东山. 特征选择及半监督分类方法研究[D]. 武汉:华中科技大学,2011.

HUANG Dongshan. Research on feature selection and semi–supervised classification[D]. Wuhan:Huazhong University of Science and Technology,2011.

[18] 杨丽,吴雨茜,王俊丽,等. 循环神经网络研究综述[J]. 计算机应用,2018,38(增刊2):1−6.

YANG Li,WU Yuxi,WANG Junli,et al. Research on recurrent neural network[J]. Journal of Computer Applications,2018,38(Sup.2):1−6.

[19] 曾春艳,严康,王志锋,等. 深度学习模型可解释性研究综述[J]. 计算机工程与应用,2021,57(8):1−9.

ZENG Chunyan,YAN Kang,WANG Zhifeng,et al. Survey of interpretability research on deep learning models[J]. Computer Engineering and Applications,2021,57(8):1−9.

[20] 纪守领,李进锋,杜天宇,等. 机器学习模型可解释性方法、应用与安全研究综述[J]. 计算机研究与发展,2019,56(10):2071−2096.

JI Shouling,LI Jinfeng,DU Tianyu,et al. Survey on techniques,applications and security of machine learning interpretability[J]. Journal of Computer Research and Development,2019,56(10):2071−2096.

[21] LINARDATOS P,PAPASTEFANOPOULOS V,KOTSIANTIS S. Explainable AI:A review of machine learning interpretability methods[J]. Entropy (Basel,Switzerland),2020,23(1):18.

[22] CASALICCHIO G,MOLNAR C,BISCHL B. Visualizing the feature importance for black box models[J]. 2018.

[23] NOHARA Y,MATSUMOTO K,SOEJIMA H,et al. Explanation of machine learning models using shapely additive explanation and application for real data in hospital[J]. Computer Methods and Programs in Biomedicine,2022,214:106584.

[24] 杨川. 长水平段水平井钻柱摩阻测量与分析技术[D]. 成都:西南石油大学,2014.

YANG Chuan. Measurement and analysis of drag in long horizontal wells[D]. Chengdu:Southwest Petroleum University,2014.



To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.