基于支持向量机的钻柱黏滑振动等级评估方法
|
摘要
为评估钻柱黏滑振动的严重程度,提出了一种基于因子分析(FA)与支持向量机(SVM)的黏滑振动风险评估方法。对仿真得到的扭矩数据进行时域与频域分析,提取信号的特征值,然后应用因子分析方法减少高维特征的冗余信息,获取特征向量,最后通过SVM对降维处理后的数据进行黏滑振动等级分类。研究结果表明:基于井口扭矩信号的SVM黏滑振动等级预测方法的整体预测精度超过80%,能够较准确地对黏滑振动强度等级进行预测。因此该方法是一个有效的黏滑振动等级分类方法,应用该方法能够有效地对钻柱黏滑振动等级进行识别,有助于司钻根据钻柱黏滑振动剧烈程度实时调整钻井参数,减轻黏滑振动产生的危害,提高钻井作业效率和安全性。
To evaluate the severity of stick-slip vibration of drill string,a risk assessment method based on factor analysis( FA) and support vector machine( SVM) is proposed. By performing time domain and frequency domain analysis on the simulated torque data,the signal feature values are extracted. The factor analysis method is used to reduce the redundant information of high-dimensional features to obtain the feature vector. The SVM is used to classify stick-slip vibration levels based on the dimensionality-reduced data. The results show that the overall prediction accuracy of the SVM stick-slip vibration level prediction method based on the wellhead torque signal is more than 80%,which can accurately predict the stick-slip vibration level,presenting an effective method for classifying the stick-slip vibration level. The method can effectively identify the stick-slip vibration level of the drill string,which could help the driller to adjust the drilling parameters in real time according to the severity of the stick-sliding vibration of the drill string,so as to minimize stick-slip vibration hazard and improve drilling efficiency and safety.
To evaluate the severity of stick-slip vibration of drill string,a risk assessment method based on factor analysis( FA) and support vector machine( SVM) is proposed. By performing time domain and frequency domain analysis on the simulated torque data,the signal feature values are extracted. The factor analysis method is used to reduce the redundant information of high-dimensional features to obtain the feature vector. The SVM is used to classify stick-slip vibration levels based on the dimensionality-reduced data. The results show that the overall prediction accuracy of the SVM stick-slip vibration level prediction method based on the wellhead torque signal is more than 80%,which can accurately predict the stick-slip vibration level,presenting an effective method for classifying the stick-slip vibration level. The method can effectively identify the stick-slip vibration level of the drill string,which could help the driller to adjust the drilling parameters in real time according to the severity of the stick-sliding vibration of the drill string,so as to minimize stick-slip vibration hazard and improve drilling efficiency and safety.
引文
[1]吕苗荣,沈诗刚.钻柱黏滑振动动力学研究[J].西南石油大学学报(自然科学版),2014(6):150-159.LM R,SHEN S G. The simulation and analysis ofdrilling stick-slip vibration[J]. Journal of SouthwestPetroleum University(Science&Technology Edition),2014(6):150-159.
[2]韩春杰,阎铁.大位移井钻柱“粘滞-滑动”规律研究[J].天然气工业,2004,24(11):58-60.HAN C J,YAN T. Research on the “sticky-slip”ruleof drilling string in large displacement well[J]. NaturalGas Industry,2004,24(11):58-60.
[3]汤历平,祝效华,石昌帅,等.钻柱系统黏滑振动的自激振动特性研究[J].西南石油大学学报(自然科学版),2017,39(4):168-175.TANG L P,ZHU X H,SHI C S,et al. Characteristicsof self-excited oscillations in the stick-slip vibrations ofdrill string systems[J]. Journal of Southwest PetroleumUniversity(Science&Technology Edition),2017,39(4):168-175.
[4]付蒙,李江红,吴亚锋,等.钻柱黏滑振动特性仿真与产生机理分析[J].西北工业大学学报,2016,34(3):467-472.FU M,LI J H,WU Y F,et al. Simulation of stick-slipvibration of drill string and analysis of its mechanism[J]. Journal of Northwestern Polytechnical University,2016,34(3):467-472.
[5]黄根炉,韩志勇.大位移井钻柱扭转振动顶部扭矩负反馈减振研究[J].石油大学学报(自然科学版),2001,25(5):32-35.HUANG G L,HAN Z Y. Research on torsional vibra-tion top torque negative feedback damping in drill stringwith large displacement[J]. Journal of the University ofPetroleum,2001,25(5):32-35.
[6] BESAISOW A A,PAYNE M L. A study of excitationmechanisms and resonances inducing bottomhole-assem-bly vibrations[J]. SPE Drilling Engineering,1988,3(1):93-101.
[7] LIN Y Q,WANG Y H. Stick-slip vibration of drillstrings[J]. Journal of Manufacturing Science&Engi-neering,1991,113(1):38.
[8] BRETT J F. The genesis of torsional drillstring vibra-tions[J]. SPE Drilling Engineering,1992,7(3):168-174.
[9] CHALLAMEL N,SELLAMI H,CHENEVEZ E,et al.A stick-slip analysis based on rock/bit interaction:theo-retical and experimental contribution[C]∥IADC/SPE Drilling Conference. 2000.
[10] RICHARD T,GERMAY C,DETOURNAY E. Self-ex-cited stick-slip oscillations of drill bits[J]. ComptesRendus Mécanique,2004,332(8):619-626.
[11] BRESCH-PIETRI D,KRSTIC M. Adaptive outputfeedback for oil drilling stick-slip instability modeledby wave PDE with anti-damped dynamic boundary[C]∥American Control Conference,2014.
[12] HALSEY G W,KYLLINGSTAD A,KYLLING A.Torque feedback used to cure slip-stick motion[C]∥SPE Technical Conference and Exhibition,1988.
[13] ROBNETT E W,HOOD J A,HEISIG G,et al. Anal-ysis of the stick-slip phenomenon using downhole drill-string rotation data[R]. SPE 52821-MS,1999.
[14]金在温,米勒查尔斯·W.因子分析[M].上海:格致出版社,2016.JIN Z W,MILLER C W. Factor analysis[M]. Shang-hai:Gezhi Press,2016.
[15]谢中华. MATLAB统计分析与应用[M].北京:北京航空航天大学出版社,2010.XIE Z H. Statistical analysis and application of MAT-LAB[M]. Beijing:Beijing University of Aeronauticsand Astronautics Press,2010.
[16]韩力群.人工神经网络教程[M].北京:北京邮电大学出版社,2006.HAN L Q. Artificial neural network tutorial[M]. Bei-jing:Beijing University of Posts and Telecommunica-tions Press,2006.
[17]张浩然,韩正之,李昌刚.支持向量机[J].计算机科学,2002,29(12):135-137.ZHANG H R,HAN Z Z,LI C G. Support vector ma-chines[J]. Journal of Computer Science,2002,29(12):135-137.
[18]王小川. MATLAB神经网络43个案例分析[M].北京:北京航空航天大学出版社,2013.WANG X C. 43 cases analysis of matlab neural net-work[M]. Beijing:Beijing University of Aeronauticsand Astronautics Press,2013.
[2]韩春杰,阎铁.大位移井钻柱“粘滞-滑动”规律研究[J].天然气工业,2004,24(11):58-60.HAN C J,YAN T. Research on the “sticky-slip”ruleof drilling string in large displacement well[J]. NaturalGas Industry,2004,24(11):58-60.
[3]汤历平,祝效华,石昌帅,等.钻柱系统黏滑振动的自激振动特性研究[J].西南石油大学学报(自然科学版),2017,39(4):168-175.TANG L P,ZHU X H,SHI C S,et al. Characteristicsof self-excited oscillations in the stick-slip vibrations ofdrill string systems[J]. Journal of Southwest PetroleumUniversity(Science&Technology Edition),2017,39(4):168-175.
[4]付蒙,李江红,吴亚锋,等.钻柱黏滑振动特性仿真与产生机理分析[J].西北工业大学学报,2016,34(3):467-472.FU M,LI J H,WU Y F,et al. Simulation of stick-slipvibration of drill string and analysis of its mechanism[J]. Journal of Northwestern Polytechnical University,2016,34(3):467-472.
[5]黄根炉,韩志勇.大位移井钻柱扭转振动顶部扭矩负反馈减振研究[J].石油大学学报(自然科学版),2001,25(5):32-35.HUANG G L,HAN Z Y. Research on torsional vibra-tion top torque negative feedback damping in drill stringwith large displacement[J]. Journal of the University ofPetroleum,2001,25(5):32-35.
[6] BESAISOW A A,PAYNE M L. A study of excitationmechanisms and resonances inducing bottomhole-assem-bly vibrations[J]. SPE Drilling Engineering,1988,3(1):93-101.
[7] LIN Y Q,WANG Y H. Stick-slip vibration of drillstrings[J]. Journal of Manufacturing Science&Engi-neering,1991,113(1):38.
[8] BRETT J F. The genesis of torsional drillstring vibra-tions[J]. SPE Drilling Engineering,1992,7(3):168-174.
[9] CHALLAMEL N,SELLAMI H,CHENEVEZ E,et al.A stick-slip analysis based on rock/bit interaction:theo-retical and experimental contribution[C]∥IADC/SPE Drilling Conference. 2000.
[10] RICHARD T,GERMAY C,DETOURNAY E. Self-ex-cited stick-slip oscillations of drill bits[J]. ComptesRendus Mécanique,2004,332(8):619-626.
[11] BRESCH-PIETRI D,KRSTIC M. Adaptive outputfeedback for oil drilling stick-slip instability modeledby wave PDE with anti-damped dynamic boundary[C]∥American Control Conference,2014.
[12] HALSEY G W,KYLLINGSTAD A,KYLLING A.Torque feedback used to cure slip-stick motion[C]∥SPE Technical Conference and Exhibition,1988.
[13] ROBNETT E W,HOOD J A,HEISIG G,et al. Anal-ysis of the stick-slip phenomenon using downhole drill-string rotation data[R]. SPE 52821-MS,1999.
[14]金在温,米勒查尔斯·W.因子分析[M].上海:格致出版社,2016.JIN Z W,MILLER C W. Factor analysis[M]. Shang-hai:Gezhi Press,2016.
[15]谢中华. MATLAB统计分析与应用[M].北京:北京航空航天大学出版社,2010.XIE Z H. Statistical analysis and application of MAT-LAB[M]. Beijing:Beijing University of Aeronauticsand Astronautics Press,2010.
[16]韩力群.人工神经网络教程[M].北京:北京邮电大学出版社,2006.HAN L Q. Artificial neural network tutorial[M]. Bei-jing:Beijing University of Posts and Telecommunica-tions Press,2006.
[17]张浩然,韩正之,李昌刚.支持向量机[J].计算机科学,2002,29(12):135-137.ZHANG H R,HAN Z Z,LI C G. Support vector ma-chines[J]. Journal of Computer Science,2002,29(12):135-137.
[18]王小川. MATLAB神经网络43个案例分析[M].北京:北京航空航天大学出版社,2013.WANG X C. 43 cases analysis of matlab neural net-work[M]. Beijing:Beijing University of Aeronauticsand Astronautics Press,2013.