计算机科学 ›› 2021, Vol. 48 ›› Issue (6A): 619-622.doi: 10.11896/jsjkx.201000070
许明泽, 韦明辉, 邓霜, 蔡卫
XU Ming-ze, WEI Ming-hui, DENG Shuang, CAI Wei
摘要: 钻井的机械钻速与钻井操作参数、钻井液性能以及钻具组合等因素有关。准确预测机械钻速可以有效计算钻井成本和钻进时间,从而优化钻进参数、合理安排钻机工作人员,并为钻井设计人员提供依据。结合目前机器学习和大数据处理,利用中国西部吐哈油田历史钻井数据,建立了一种基于集成学习的钻速预测模型。其成员包括KNN(K近邻)、DT(决策树)、SVR(支持向量机)、RF(随机森林),输入7个特征影响因素,包括井深、钻压、泵压、密度、粘度、排量和转速,将拟合优度作为机械钻速预测的评价指标,结果显示集成模型的预测输出优于任何一种单一模型的结果。以7-13井为例,拟合优度R2达到了0.93以上。文中还探讨了不同集成成员的组合,结合时间成本和拟合优度发现最优组合为KNN+SVR+RF,其拟合优度在7-13,8-17,4-10井分别达到了0.937 8,0.918 7,0.912 4。最后,以SVR为例,优化后的单一模型拟合准确性依旧低于任何一组组合模型。进一步的研究表明,有效的集成模型需要集成成员的多样性和较高的精度。这些预测结果表明,该模型为机械钻速预测提供了一种有前途的替代方案。
中图分类号:
[1] HUNT S G.Drilling Forecast Model[C]//SPE Eastern Regional Meeting.Society of Petroleum Engineers,1984. [2] CAICEDO H U,CALHOUN W M,EWYRT.Unique ROP Predictor Using Bit-specific Coefficient of Sliding Friction and Mechanical Efficiency as a Function of Confined Compressive Strength Impacts Drilling Performance[C] //SPE/IADC Drilling Conference. Amsterdam,Netherlands,2005. [3] ABBAS A,ELHAM K.Simulation Study of Drilling Horizontal Wells in One Iranian Oil Field [C] //Latin American & Caribbean Petroleum Engineering Conference.Buenos Aires,Argentina,2007. [4] MOHAN K,ADIL F,SAMUEL R.Tracking Drilling Efficiency Using Hydro-Mechanical Specific Energy[C]//SPE/IADC Drilling Conference and Exhibition.Society of Petroleum Engineers.2009. [5] YUANHUA L,YUYU Z,ZHENG L,et al.The Developments of ROP Prediction for Oil Drilling[J].Petroleum Drilling Techniques,2004,1:10-13. [6] BOURGOYNE A T,YOUNG F S.A Multiple Regression Approach to Optimal Drilling and Abnormal Pressure Detection[J].Society of Petroleum Engineers Journal,1974,14(4):371-384. [7] AMER M M,DAHAB A S,EL-SAYED A A H.An ROP Predictive Model in Nile Delta Area Using Artificial Neural Networks[C] //SPE Kingdom of Saudi Arabia Annual Technical Symposium and Exhibition.Dammam,Saudi Arabia,2017. [8] ELKATATNY S.Rate of Penetration Prediction Using Self-Adaptive Differential Evolution-Artificial Neural Network [C] //SPE Kingdom of Saudi Arabia Annual Technical Symposium and Exhibition.Dammam,Saudi Arabia,2018. [9] ALKINANI H H,AL-HAMEEDI A T,DUNN-NORMAN S,et al.Dynamic Neural Network Model to Predict the Rate of Penetration Prior to Drilling[C] //The 53rd U.S. Rock Mechanics/Geomechanics Symposium.New York City,New York,2019. [10] BING Z,WEINAN L,ZHEN W,et al.Identification Strategy of Driving Style Based on Random Forest[J].Automotive Engineering,2019,41(2):213-218,224. [11] JIANJUN H,SHAOWEI N,JIANPING L,et al.Research onPrediction and Control of Mechanical Ventilation Temperature of Grain Pile Based on Random Forest Algorithm[J].Journal of Henan University of Technology (Natural Science Edition),2019,40(5):107-113. [12] LIU Y,CHENG H,KONG X,et al.Intelligent wind turbineblade icing detection using supervisory control and data acquisition data and ensemble deep learning[J].Energy Science & Engineering,2019,7(6):2633-2645 [13] LIU Z,WEI M,ZHANG P,et al.Drilling Localization and Error Analysis of Radial Horizontal Jet Drilling Based on Magnetic Gradient Tensor[J].Energies,2020,13:4989. [14] NAN L,WENCHUN Z,YING L,et al.Prediction of DeepFoundation Pit Horizontal Displacement Based on Random Forest Model in Seasonal Frozen Region[J].Chinese Journal of Underground Space and Engineering,2018,14(S1):357-362. [15] ARABJAMALOEI R,EDALATKHAH S,JAMSHIDI E.ANew Approach to Well Trajectory Optimization Based on Rate of Penetration and Wellbore Stability[J].Liquid Fuels Technology,2011,29(6):588-600. [16] YUANHUA L,YUYU Z,ZHENG L,et al.The Developments of ROP Prediction for Oil Drilling[J].Petroleum Drilling Techniques,2004,1:10-13. [17] DENG Y,CHEN M,JIN Y,et al.Theoretical and experimental study on the penetration rate for roller cone bits based on the rock dynamic strength and drilling parameters[J].Journal of Natural Gas Science and Engineering,2016,36:117-123. [18] YAN T,JINGLIN D.Temperature prediction using long short term memory network based on random forest[J].Computer Engineering and Design,2019,40(3):737-743. [19] WANG Z,LAI C,CHEN X,et al.Flood hazard risk assessment model based on random forest[J].Journal of Hydrology,2015,527:1130-1141. [20] 刘胜娃,孙俊明,高翔,等.基于人工神经网络的钻井机械钻速预测模型的分析与建立[J].计算机科学,2019(Z6):605-608. |
[1] | 吴兰, 王涵, 李斌全. 基于自监督任务最优选择的无监督域自适应方法 Unsupervised Domain Adaptive Method Based on Optimal Selection of Self-supervised Tasks 计算机科学, 2021, 48(6A): 357-363. https://doi.org/10.11896/jsjkx.201000030 |
[2] | 陈靖邦, 潘俊哲, 沈皓朗, 谷培, 扈明涛. 一种多趋势指标结合与择时引入峰值的投资组合优化系统 Portfolio Optimization System Based on Multiple Trend Indices with Time Picking of Inducing Peak Prices 计算机科学, 2021, 48(11A): 693-698. https://doi.org/10.11896/jsjkx.210300215 |
[3] | 王晓晖, 张亮, 李俊清, 孙玉翠, 田捷, 韩睿毅. 基于遗传算法与随机森林的XGBoost改进方法研究 Study on XGBoost Improved Method Based on Genetic Algorithm and Random Forest 计算机科学, 2020, 47(11A): 454-458. https://doi.org/10.11896/jsjkx.200600002 |
[4] | 张洋, 姬波, 卢红星, 娄铮铮. 基于LSTM神经网络的短期高压负荷电流预测方法 Short-term High Voltage Load Current Prediction Method Based on LSTM Neural Network 计算机科学, 2019, 46(6): 49-54. https://doi.org/10.11896/j.issn.1002-137X.2019.06.006 |
[5] | 张贵军,丁情,王柳静,周晓根. 柔性车间生产排产调度优化方法 Optimization Method of Production Scheduling in Flexible Job 计算机科学, 2018, 45(2): 269-275. https://doi.org/10.11896/j.issn.1002-137X.2018.02.046 |
[6] | 郑巧仙,何国良,李明,唐秋华. 第2类U型装配线平衡问题的双阶段蚁群算法 Two Stage Ant Colony Optimization for Type 2 of U-shaped Assembly Line Balancing Problem 计算机科学, 2017, 44(6): 206-211. https://doi.org/10.11896/j.issn.1002-137X.2017.06.034 |
[7] | 张艳梅,曹怀虎. 基于覆盖网络模型的跨领域组合服务优化问题研究 Research on Routing Problem of Inter-domain Composed Service Based on Overlay Network 计算机科学, 2014, 41(4): 70-74. |
[8] | 范菁,熊丽荣,徐聪. 分布式企业服务总线平台数据集成研究及应用 Research and Application of Data Integration in Distributed Enterprise Service Bus Platform 计算机科学, 2014, 41(2): 206-214. |
[9] | 郭树行,丁娴,王坚. 基于改进微粒群算法的信息化需求组合优选模型研究 Study on Optimal Combination of Model of Information Needs Based on Particle Swarm Optimization Algorithm 计算机科学, 2013, 40(6): 238-241. |
[10] | 夏欣. 批处理机调度问题的蚁群算法求解 Scheduling Single Batch Processing Machine Using Ant Colony Algorithm 计算机科学, 2013, 40(5): 247-250. |
[11] | 陈乙雄,吴中福,李华,冯永. 一种基于Max-Flow的协同学习活动调度算法 Collaborated E-learning Scheduling Algorithm Based on Max-Flow 计算机科学, 2012, 39(9): 43-46. |
[12] | 张庆科,杨 波,王 琳,朱福祥. 基于GPU的现代并行优化算法 Research on Parallel Modern Optimization Algorithms Using GPU 计算机科学, 2012, 39(4): 304-311. |
[13] | 刘超,王文杰. 一个由接口路径求Hamilton回路的算法研究 Research on Hamiltonian Cycle Based on Path with Interface 计算机科学, 2010, 37(9): 252-256. |
[14] | 许昌,常会友,徐俊,衣杨. 一种新的融合分布估计的蚁群优化算法 Novel Ant Colony Optimization Algorithm with Estimation of Distribution 计算机科学, 2010, 37(2): 186-188. |
[15] | 郭文忠 陈国龙. 求解TSP问题的模糊自适应粒子群算法 计算机科学, 2006, 33(6): 161-162. |
|