地质出版社有限公司 中国地质科学院勘探技术研究所主办

基于融合特征选择算法的钻速预测模型研究

周长春, 姜杰, 李谦, 朱海燕, 李之军, 鲁柳利. 2022. 基于融合特征选择算法的钻速预测模型研究. 钻探工程, 49(4): 31-40. doi: 10.12143/j.ztgc.2022.04.005
引用本文: 周长春, 姜杰, 李谦, 朱海燕, 李之军, 鲁柳利. 2022. 基于融合特征选择算法的钻速预测模型研究. 钻探工程, 49(4): 31-40. doi: 10.12143/j.ztgc.2022.04.005
ZHOU Changchun, JIANG Jie, LI Qian, ZHU Haiyan, LI Zhijun and LU Liuli, . 2022. Research on drilling rate prediction model based on fusion feature selection algorithm. DRILLING ENGINEERING, 49(4): 31-40. doi: 10.12143/j.ztgc.2022.04.005
Citation: ZHOU Changchun, JIANG Jie, LI Qian, ZHU Haiyan, LI Zhijun and LU Liuli, . 2022. Research on drilling rate prediction model based on fusion feature selection algorithm. DRILLING ENGINEERING, 49(4): 31-40. doi: 10.12143/j.ztgc.2022.04.005

基于融合特征选择算法的钻速预测模型研究

  • 基金项目:

    中海石油(中国)有限公司项目“南海西部油田上产2000万方钻完井关键技术研究”子课题“乐东10区超高温高压井综合提速技术研究”(编号:CNOOC-KJ135ZDXM38ZJ05ZJ);四川省科技支撑计划应用基础研究项目“四川深层页岩气产能大数据挖掘和智能评估方法研究”(编号:2021YJ0360)

详细信息
    作者简介: 周长春,男,汉族,1995年生,硕士研究生在读,岩土工程专业,从事人工智能在钻探施工中应用的研究工作,四川省成都市成华区二仙桥东三路1号,zcc@stu.cdut.edu.cn.。
    通讯作者: 周长春,男,汉族,1995年生,硕士研究生在读,岩土工程专业,从事人工智能在钻探施工中应用的研究工作,四川省成都市成华区二仙桥东三路1号,zcc@stu.cdut.edu.cn.。
  • 中图分类号: P634

Research on drilling rate prediction model based on fusion feature selection algorithm

More Information
  • 钻速预测是钻井优化的重要组成部分,机器学习算法是当前实现准确钻速预测的重要手段,准确的特征选择是保证机器学习精度的关键途径。基于南海某井眼的实际钻井数据,本文采用一种融合特征选择法从钻井特征参数中选出井径、钻井液出口温度、钻井液入口密度、钻井液出口密度、K值、塑性粘度、滤失量、上覆压力、孔隙压力、和喷嘴等效直径共10种参数。将优选出的参数作为模型输入,引入集成的梯度提升树(Gradient Boosting Decision Tree,GBDT)算法建立机械钻速预测模型。将建立的模型与常规机器学习算法模型进行对比试验。试验结果显示,所提出的融合特征选择算法模型精度较全特征模型高2%,较常用机器学习模型平均高14.5%,该研究为钻井参数的准确、快速寻优提供了有效解决方案,对提高钻进速率具有一定的指导意义和实际应用价值。
  • 加载中
  • [1]

    于洋,黄凯,李卉.基于机器学习和多源数据预处理技术的机械钻速预测方法研究[J].中国石油和化工标准与质量,2021,41(20):133-136.

    YU Yang, HUANG Kai, LI Hui. Research on prediction method of ROP based on machine learning and multi-source data preprocessing technology[J]. China Petroleum and Chemical Standard and Quality, 2021,41(20):133-136.

    [2]

    [2] Barbosa L F F M, Nascimento A, Mathias M H, et al. Machine learning methods applied to drilling rate of penetration prediction and optimization—A review[J]. Journal of Petroleum Science and Engineering, 2019,183:106332.

    [3]

    [3] 张维罡.基于机器学习算法的石油钻速研究[J].化工管理,2021(20):89-90.

    ZHANG Weigang. Research on ROP of petroleum based on machine learning algorithm[J]. Chemical Management, 2020(20):89-90.

    [4]

    [4] 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. OnePetro, 2017.

    [5]

    [5] 赵颖,孙挺,杨进,等.基于极限学习机的海上钻井机械钻速监测及实时优化[J].中国海上油气,2019,31(6):138-142.

    ZHAO Ying, SUN Ting, YANG Jin, et al. Extreme learning machine-based offshore drilling ROP monitoring and real-time optimization[J]. China Offshore Oil and Gas, 2019,31(6):138-142.

    [6]

    [6] 李莉,石可欣,任振康.基于特征选择和TrAdaBoost的跨项目缺陷预测方法[J].计算机应用,2022,42(5):1554-1562.

    LI Li, SHI Kexin, REN Zhenkang. Cross-project defect prediction method based on feature selection and TrAdaboost[J]. Journal of Computer Applications, 2022,42(5):1554-1562.

    [7]

    [7] 周翔,翟俊海,黄雅婕,等.大数据环境下的投票特征选择算法[J/OL].小型微型计算机系统,2022:1-9.

    ZHOU Xiang, ZHAI Junhai, HUANG Yajie, et al. Voting feature selection algorithm in big data environment[J/OL]. Journal of Chinese Computer Systems, 2022:1-9.

    [8]

    [8] 康文豪,徐天奇,王阳光,等.双层特征选择和CatBoost-Bagging集成的短期风电功率预测[J/OL].重庆理工大学学报(自然科学),2022:1-8.

    KANG Wenhao, XU Tianqi, WANG Yangguang, et al. Short-term wind power prediction based on double-layer feature selection and catboost-bagging integration[J/OL]. Journal of Chongqing University of Technology(Natural Science), 2022:1-8.

    [9]

    [9] Dupriest F E, Koederitz W L. Maximizing drill rates with real-time surveillance of mechanical specific energy[C]//SPE/IADC Drilling Conference. OnePetro, 2005.

    [10]

    [10] Shi X, Liu G, Gong X, et al. An efficient approach for real-time prediction of rate of penetration in offshore drilling[J]. Mathematical Problems in Engineering, 2016:20-16.

    [11]

    [11] 李谦,周长春,朱海燕,等.生产数据的整合与初步分析在钴井中的应用实例[J].钻探工程,2021,48(S1):97-107.

    LI Qian, ZHOU Changchun, ZHU Haiyan,et al. Application of integration and preliminary analysis of production data in drilling[J]. Drilling Engineering, 2021,48(S1):97-107.

    [12]

    [12] 李洪烈,夏栋,王倩.基于回归模型的采集数据清洗技术[J].电光与控制,2022,29(4):117-120.

    LI Honglie, XIA Dong, WANG Qian. A sample data clean technology based on regression model[J]. Electronics Optics & Control, 2022,29(4):117-120.

    [13]

    [13] 匡俊搴,赵畅,杨柳,等.一种基于深度学习的异常数据清洗算法[J].电子与信息学报,2022,44(2):507-513.

    KUANG Junqian, ZHAO Chang, YANG Liu, et al. An outlier cleaning algorithm based on deep learning[J]. Journal of Electronics & Information Technology, 2022,44(2):507-513.

    [14]

    [14] 曹凯鑫,汤猛猛,葛建鸿,等.大气污染物PM_(2.5)缺失数据插值方法的比较研究:基于北京市数据[J].环境与职业医学,2020,37(4):299-305.

    CAO Kaixin, TANG Mengmeng, GE Jianhong, et al. Comparison of methods to interpolate missing PM2.5 values: Based on air surveillance data of Beijing[J]. Journal of Environmental and Occupational Medicine, 2020,37(4):229-305.

    [15]

    [15] 王双敬,王玉杰,李旭,等.TBM掘进数据标准化预处理方法研究[J/OL].现代隧道技术,2022:1-8.

    WANG Shuangjing, WANG Yujie, LI Xu, et al. Research on standardized preprocessing method of TBM tunneling data[J/OL]. Modern Tunnelling Technology, 2022:1-8.

    [16]

    [16] 屈峰涛.基于大数据和智能算法的钻井参数优选模型与应用研究[D].西安:西安石油大学,2021.QU Fengtao. Research on establishment and application of drilling parameter optimization model based on big data and intelligent algorithms[D]. Xi’an: Xi’an Shiyou University, 2021.

    [17]

    [17] 李谦,曹彦伟,朱海燕.基于人工智能的钻速预测模型数据有效性下限分析[J].钻探工程,2021,48(3):21-30.

    LI Qian, CAO Yanwei, ZHU Haiyan. Discussion on the lower limit of data validity for ROP prediction based on artificial intelligence[J]. Drilling Engineering, 2021,48(3):21-30.

    [18]

    [18] 殷豪,翟广松,王鹏,等.基于互信息特征选取-变分模态分解和长短时记忆网络的日前耦合市场电价预测[J/OL].电网技术,2022:1-9.

    YIN Hao, ZHAI Guangsong, WANG Peng, et al. Electricity price forecast of day-ahead coupled market based on mutual information feature selection and variational mode decomposition and LSTM[J/OL]. Power System Technology, 2022:1-9.

    [19]

    [19] 陈陆,吴桦.基于GBDT的船舶油耗预测模型设计[J].电子设计工程,2022,30(2):91-95.

    CHEN Lu, WU Ye. Prediction model of ship fuel consumption based on GBDT[J]. Electronic Design Engineering, 2022,30(2):91-95.

    [20]

    [20] 吕晓玲,宋捷.大数据挖掘与统计机器学习[M].北京:中国人民大学出版社,2016.SONG Xiaoling, SONG Jie. Big Data Mining and Statistical Machine Learning[M]. Beijing: China Renmin University Press, 2016.

  • 加载中
计量
  • 文章访问数:  855
  • PDF下载数:  204
  • 施引文献:  0
出版历程
收稿日期:  2022-04-25
修回日期:  2022-06-17

目录