1.中国石油大学(北京)人工智能学院
2.中国石油大学(北京)石油工程学院
3.中国石油大学(北京)机械与储运工程学院
叶山林,生于1998年,现为在读博士研究生,研究方向为人工智能技术的钻井提速方法。地址:(102249)北京市昌平区。email:779975965@qq.com。
宋先知,教授。email:songxz@cup.edu.cn。
收稿:2025-05-14,
修回:2026-03-25,
录用:2025-09-22,
纸质出版:2026-09-25
移动端阅览
叶山林,宋先知,祝兆鹏,等.基于大数据分析和智能技术的PDC钻头选型与参数优化[J].石油机械,2026,54(9):10-18.
Ye Shanlin,Song Xianzhi,Zhu Zhaopeng,et al.PDC bit selection and parameter optimization based on big data analysis and intelligent technology[J].China Petroleum Machinery,2026,54(9):10-18.
叶山林,宋先知,祝兆鹏,等.基于大数据分析和智能技术的PDC钻头选型与参数优化[J].石油机械,2026,54(9):10-18. DOI: 10.12473/CPM.202505039.
Ye Shanlin,Song Xianzhi,Zhu Zhaopeng,et al.PDC bit selection and parameter optimization based on big data analysis and intelligent technology[J].China Petroleum Machinery,2026,54(9):10-18. DOI: 10.12473/CPM.202505039.
随着油田技术聚焦于数字化与智能化转型,钻头选型和参数优选方法也亟须升级和创新,以发挥大数据和智能算法优势,让钻头和参数优选更合理高效。然而现有钻头选型智能模型大多建立在地层抗钻属性与钻头型号的对应关系上,缺乏对更深层原因(如钻头设计特征)的探索。为此,提出一种基于大数据分析和智能技术的钻头选型与参数优选框架。具体作法如下:融合地层岩石力学数据、钻头历史性能表现数据及关键特征数据,构建钻头特征-地层信息与平均进尺-机械钻速间的智能预测模型,评价不同钻头特征组合在测试地层的性能表现,为最优表现的钻头组合匹配已有的钻头型号;基于优选钻头的历史数据,建立钻压-转速与机械钻速的分布热力图,优化钻井参数;利用西南某油田区块实测数据对模型进行验证。研究结果表明:模型在训练集和测试集上的
R
²分别达到了0.9及0.8以上,平均绝对百分比误差均小于20%;井深、岩性、地层密度及抗压强度等地层属性对钻头机械钻速和进尺具有显著影响,钻头自身的刀翼数量、主切削齿倾角与齿高等关键参数也对钻头性能发挥着至关重要的作用;在同一井段内,经过参数优选后的钻头可将趟钻次数由原来的5次减少到3次,机械钻速由0~10 m/h提升至10~20 m/h,整体钻井效率明显提高。研究成果可为智能钻井中钻头选型与参数调控提供数据驱动解决方案。
As oil-gas field development engineering technology focuses on digital and intelligent transformation, the methods for bit selection and parameter optimization need to be upgraded and innovated urgently. By leveraging the advantages of big data and intelligent algorithms, bit and parameter selection can become more reasonable and efficient. However, most existing intelligent models for bit selection are established based on the correspondence between formation drillability properties and bit models, lacking exploration of deeper causes such as bit design characteristics. To address this issue, a framework for bit selection and parameter optimization based on big data analysis and intelligent technology is proposed. Firstly, an intelligent prediction model for bit features-formation information vs. average footage-rate of penetration (ROP) was constructed by integrating formation rock mechanical data, historical bit performance data, and key feature data, to evaluate the performance of different bit feature combinations in the tested formation and match the optimal bit combination with available bit models. Then, based on historical data of the optimized bit, a distribution heat map of weig
ht on bit (WOB)-rotary speed and ROP was established to optimize drilling parameters. Finally, field data from a block of an oilfield in southwest China were used to verify the model. The results show that the
R
² values of the model on the training set and test set reach above 0.9 and 0.8, respectively, both with the mean absolute percentage error (MAPE) less than 20%. Formation properties including well depth, lithology, formation density and compressive strength have significant effects on bit ROP and footage. Key bit parameters such as the number of blades, main cutting tooth inclination angle and tooth height also play a vital role in bit performance. In the same well section, after parameter optimization, the number of bit runs is reduced from 5 to 3, and the ROP is increased from 0-10 m/h to 10-20 m/h, resulting in a significant improvement in overall drilling efficiency. This study provides a data-driven solution for bit selection and parameter regulation in intelligent drilling.
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 ( 4 ): 35 - 47 .
Li Gensheng , Song Xianzhi , Zhu Zhaopeng , et al . Research progress and the prospect of intelligent drilling and completion technologies [J]. Petroleum Drilling Techniques , 2023 , 51 ( 4 ): 35 - 47 .
毕开原 . 我国页岩气钻完井关键技术现状及发展趋势 [J]. 石油机械 , 2024 , 52 ( 11 ): 12 - 20, 28 .
Bi Kaiyuan . Current status and trend of key technologies for shale gas well drilling and completion in China [J]. China Petroleum Machinery , 2024 , 52 ( 11 ): 12 - 20, 28 .
Al-Dujaili A N , Asad M S , Saeed N , et al . Optimizing polycrystalline diamond compact bit selection and drilling parameters for deviated wells in the Majnoon Field, Iraq [J]. Scientific Reports , 2025 , 15 ( 1 ): 3178 .
段鸿杰 , 马承杰 , 董琰 , 等 . 胜利油田数字化转型实践与成效 [J]. 石油科技论坛 , 2023 , 42 ( 3 ): 48 - 55, 64 .
Duan Hongjie , Ma Chengjie , Dong Yan , et al . Practice and achievements from digital transformation in shengli oilfield [J]. Petroleum Science and Technology Forum , 2023 , 42 ( 3 ): 48 - 55, 64 .
李金蔓 , 周守为 , 孙金声 , 等 . 数字技术赋能海上油田开发: 渤海智能油田建设探索 [J]. 石油钻采工艺 , 2022 , 44 ( 3 ): 376 - 382 .
Li Jinman , Zhou Shouwei , Sun Jinsheng , et al . Digital technology energizes offshore oilfield development: an attempt to build the Bohai smart oilfield [J]. Oil Drilling & Production Technology , 2022 , 44 ( 3 ): 376 - 382 .
潘起峰 , 高德利 , 孙书贞 , 等 . PDC钻头选型新方法 [J]. 石油学报 , 2005 , 26 ( 3 ): 123 - 126 .
Pan Qifeng , Gao Deli , Sun Shuzhen , et al . A new method for PDC bit selection [J]. Acta Petrolei Sinica , 2005 , 26 ( 3 ): 123 - 126 .
赵军 , 蔡亚西 , 林元华 . 声波测井资料在岩石可钻性及钻头选型中的应用 [J]. 测井技术 , 2001 , 25 ( 4 ): 305 - 307 .
Zhao Jun , Cai Yaxi , Lin Yuanhua . Application of sonic logs to rock drillability and bit selection [J]. Well Logging Technology , 2001 , 25 ( 4 ): 305 - 307 .
苏强 , 何世明 , 胡锡辉 , 等 . 川西双鱼石构造难钻地层岩石可钻性及钻头选型研究与应用 [J]. 钻采工艺 , 2019 , 42 ( 2 ): 124 - 127 .
Su Qiang , He Shiming , Hu Xihui , et al . Research and application on rock drillability and bit selection of difficult drilling formations in Shuangyushi structure of western Sichuan basin [J]. Drilling & Production Technology , 2019 , 42 ( 2 ): 124 - 127 .
张武昌 , 李忠慧 , 寿翔 , 等 . 玛湖凹陷砂砾岩地层抗钻特性预测及钻头优选 [J]. 石油机械 , 2023 , 51 ( 3 ): 9 - 15 .
Zhang Wuchang , Li Zhonghui , Shou Xiang , et al . Prediction of anti-drilling properties and bit selection for glutenite formations in Mahu sag [J]. China Petroleum Machinery , 2023 , 51 ( 3 ): 9 - 15 .
田云英 , 夏宏泉 , 张晶晶 . 川西深井钻头选型的测井参数灰色关联研究 [J]. 钻采工艺 , 2007 , 30 ( 3 ): 30 - 32, 48 .
Tian Yunying , Xia Hongquan , Zhang Jingjing . Research on grey relation method of logging parameter about bit selection in deep wells of west Sichuan [J]. Drilling & Production Technology , 2007 , 30 ( 3 ): 30 - 32, 48 .
闫铁 , 许瑞 , 孙文峰 , 等 . 地层抗钻能力相似性评价及钻头选型新方法 [J]. 石油勘探与开发 , 2021 , 48 ( 2 ): 386 - 393, 420 .
Yan Tie , Xu Rui , Sun Wenfeng , et al . Similarity evaluation of stratum anti-drilling ability and a new method of drill bit selection [J]. Petroleum Exploration and Development , 2021 , 48 ( 2 ): 386 - 393, 420 .
冯定 . 神经网络在钻头选型中的应用研究 [J]. 石油钻探技术 , 1998 ( 1 ): 45 - 47,64 .
Feng Ding . Application research of neural network in bit selection [J]. Petroleum Drilling Techniques , 1998 ( 1 ): 45 - 47, 64 .
张辉 , 王昊 , 姜敞 , 等 . 基于岩石抗钻特性的BP神经网络钻头选型方法 [J]. 钻采工艺 , 2019 , 42 ( 4 ): 24 - 27 .
Zhang Hui , Wang Hao , Jiang Chang , et al . Bit type selection by BP neural network method based on rock's anti-drilling property [J]. Drilling & Production Technology , 2019 , 42 ( 4 ): 24 - 27 .
赵廷峰 , 周启成 , 赵春艳 , 等 . 基于PCA-BP的钻头优选方法与应用 [J]. 断块油气田 , 2016 , 23 ( 2 ): 243 - 247 .
Zhao Tingfeng , Zhou Qicheng , Zhao Chunyan , et al . Selection and application of bit type based on PCA-BP [J]. Fault-Block Oil and Gas Field , 2016 , 23 ( 2 ): 243 - 247 .
邓嵘 , 丰波 , 敖建章 , 等 . 牙轮钻头牙齿破岩效率的模糊综合评判方法 [J]. 石油机械 , 2016 , 44 ( 3 ): 6 - 11 .
Deng Rong , Feng Bo , Ao Jianzhang , et al . Fuzzy comprehensive evaluation method of cone bit teeth rock-breaking efficiency [J]. China Petroleum Machinery , 2016 , 44 ( 3 ): 6 - 11 .
邹德永 , 孟祥雨 , 袁军 , 等 . 基于模式识别的钻头选型新方法 [J]. 石油钻探技术 , 2016 , 44 ( 2 ): 40 - 45 .
Zou Deyong , Meng Xiangyu , Yuan Jun , et al . A new method for bit selection based on pattern recognition [J]. Petroleum Drilling Techniques , 2016 , 44 ( 2 ): 40 - 45 .
Tewari S , Dwivedi U D , Biswas S . A novel application of ensemble methods with data resampling techniques for drill bit selection in the oil and gas industry [J]. Energies , 2021 , 14 ( 2 ): 432 .
樊永东 , 金衍 , 林伯韬 , 等 . 地质-工程驱动的邻井辅助同井钻速预测与优化方法 [J]. 石油钻探技术 , 2025 , 53 ( 1 ): 31 - 40 .
Fan Yongdong , Jin Yan , Lin Baitao , et al . Prediction and optimization of ROP assisted by adjacent well data based on geological and engineering driving [J]. Petroleum Drilling Techniques , 2025 , 53 ( 1 ): 31 - 40 .
0
浏览量
11
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621