摘要
粘滑振动是影响钻井速度、安全以及成本的重要限制因素,建立一套可靠的粘滑振动分级模型对于石油钻井的决策至关重要。提出一种基于贝叶斯优化和极端梯度提升eXtremeGradient Boosting(XGBoost)的新方法来评估近钻头处粘滑振动的严重程度。对近钻头粘滑振动数据进行分级处理;通过时域和频域分析,提取原始数据主要特征向量;建立基于XGBoost的粘滑振动等级识别分类模型,引用贝叶斯算法对XGBoost超参数调优;基于准确率、召回率、F1评分等模型评价指标,利用测试集分别将优化XGBoost模型与分类回归树模型和随机森林模型进行对比。研究结果表明:该方法能有效评估近钻头粘滑振动等级,具有较高的识别精度。
Stick-slip vibration is an important limiting factor affecting drilling speed,safety and cost.The establishment of a reliable stick-slip vibration classification model is very important for oil drilling decision-making.A new method based on Bayesian optimization and eXtreme Gradient Boosting(XGBoost)is proposed to evaluate the severity of stick-slip vibration near the bit.The classification processing of the near-bit stick-slip vibration data is carried out.The main feature vectors of the original data is extracted through time domain and frequency domain analysis.A stick-slip vibration level identification and prediction model based on XGBoost is established,and Bayesian algorithm is uesd to the XGBoost hyperparameter tuning.Based on the model evaluation indicators of accuracy,recall,and F1 score,the test set is used to compare the optimized XGBoost model with the Classification and Regression Tree(CART)model and the Random Forests(RFs)model,respectively.The research results show that the method can effectively evaluate the stick-slip vibration level of the near-bit bit and has a high recognition accuracy.
作者
唐翰文
张涛
李玉梅
李雷
张京华
胡冬良
Tang Hanwen;Zhang Tao;Li Yumei;Li Lei;Zhang Jinghua;Hu Dongliang(Beijing Key Laboratory of High Dynamic Navigation Technology,Beijing Information Science&Technology University,Beijing 100101,China;Drillling&Production Technology Research Institute,CNPC Chuanqing Exploratory Drilling Engineering Co.,Ltd.,Deyang 618300,China;Engineering Technology Research Institute,CNPC Bohai Drilling Engineerinig Co.,Ltd.,Tianjin 300457,China;Directional Well Drilling Company,CNPC Bohai Drilling Engineerinig Co.,Ltd.,Tianjin 300000,China)
出处
《系统仿真学报》
CAS
CSCD
北大核心
2021年第11期2704-2710,共7页
Journal of System Simulation
基金
国家自然科学基金青年项目(41802197)
中国石油天然气集团有限公司-中国石油大学(北京)战略合作科技专项(ZLZX2020-03)
北京信息科技大学重点研究培育项目(2121YJPY220)
北京市教委一般项目(KM202111232004)。
