基于支持向量机的潜油柱塞泵沉没度预测

doi:10.7623/syxb201103027

石油学报 ›› 2011, Vol. 32 ›› Issue (3): 534-538.DOI: 10.7623/syxb201103027

基于支持向量机的潜油柱塞泵沉没度预测

于德亮 1 齐维贵 1 邓盛川 1 张永明 1 张凤武 2 王新民 2

1哈尔滨工业大学电气工程及自动化学院黑龙江哈尔滨 150001； 2中国石油大庆油田采油工程研究院黑龙江大庆 163453

收稿日期:2010-09-25 修回日期:2010-12-19 出版日期:2011-05-25 发布日期:2011-07-19
通讯作者: 于德亮
作者简介:于德亮，男，1982年8月生，2005年毕业于哈尔滨工业大学电气工程专业，现为哈尔滨工业大学在读博士研究生，主要从事抽油机节能控制、信息处理、预测控制等方面的研究。
基金资助:
黑龙江省工业和信息化委员会发展信息产业专项资金项目（08020017）资助。

Submergence forecasting of a submersible plunger pump based on the support vector machine

YU Deliang 1 QI Weigui 1 DENG Shengchuan 1 ZHANG Yongming 1 ZHANG Fengwu 2 WANG Xinmin 2

Received:2010-09-25 Revised:2010-12-19 Online:2011-05-25 Published:2011-07-19

摘要/Abstract

摘要：

潜油柱塞泵抽油系统可以及时、合理地调节直线电机的运行状态，使抽油机的抽汲能力与井下沉没度的变化相匹配，以达到可靠、稳产和节能的目的。针对潜油柱塞泵抽油系统沉没度时间序列非平稳、非线性的特点，提出基于支持向量机(SVM)的沉没度预测方法。对实测现场沉没度序列预处理和归一化，构成沉没度时间序列，并进行输入样本空间重构。用沉没度时间序列样本对SVM预测模型进行训练，选择测试样本对训练得到的预测模型进行测试，并将该方法与自回归滑动平均模型（ARMA）预测结果进行比较。最后，引入直线电机冲数信息作为预测模型的输入，形成改进的沉没度预测方法。对三种预测方法在相同的训练和测试条件下进行误差分析，证明改进的SVM方法具有更高的预测精度。研究结果可作为潜油柱塞泵在线监控系统控制直线电机运行状态的依据。

关键词: 潜油柱塞泵, 沉没度预测, 支持向量机, 非平稳时间序列, 直线电机

Abstract:

The submersible plunger pumping system can adjust the operating condition of linear motor reasonably and promptly according to the downhole submergence variation in order to effect the purpose of reliability service, stable production and energy-saving. Aiming at non-stationary and nonlinear characteristics of the submergence time series of the submersible plunger pumping system, the present paper proposed a novel intelligent forecasting approach based on the support vector machine(SVM). The submergence sequence measured in situ were pretreated and normalized to form a submergence time series, and a phase space of input specimens was reconstructed. Subsequently, the SVM-based forecasting model was trained by using specimens of the submergence time series, and specimens were chosen to test the forecasting model established by training, and then some forecasting results obtained from this SVM-based models were compared with those derived from an auto-regressive and moving average(ARMA) model. Finally, the stroke information of linear motor was inputted into the forecasting model to establish an improved submergence forecasting method. The error analysis for these three forecasting methods was made under the same training and testing conditions, and the results showed that the forecasting accuracy offered by the improved SVM-based method was higher than those of the other two methods. Thus, the results of this study were expected to provide a theoretical basis for the on-line monitoring system of the submersible plunger pump to control the running-state of linear motor.

Key words: submersible plunger pump, submergence forecasting, support vector machine(SVM), non-stationary time series, linear motor

于德亮齐维贵邓盛川张永明张凤武王新民. 基于支持向量机的潜油柱塞泵沉没度预测[J]. 石油学报, 2011, 32(3): 534-538.

YU Deliang QI Weigui DENG Shengchuan ZHANG Yongming ZHANG Fengwu. Submergence forecasting of a submersible plunger pump based on the support vector machine[J]. Editorial office of ACTA PETROLEI SINICA, 2011, 32(3): 534-538.

参考文献

[1]马文忠,李耀华,孔力.潜油电泵变频驱动负面问题研究[J].石油学报,2006,27(2):133-136.

Ma Wenzhong,Li Yaohua,Kong Li.Negative problems of electrical submersible pump driven by converter[J].Acta Petrolei Sinica, 2006,27(2):133-136.

[2]关晓晶,王志国,王忠东.抽油机系统效率测试的不确定度分析模型及应用[J].石油学报,2005,26(1):113-120.

Guan Xiaojing,Wang Zhiguo,Wang Zhongdong.Application of mathematical model for uncertainty analysis of efficiency evaluation for pumping system[J].Acta Petrolei Sinica,2005,26(1):113-120.

[3]齐光峰,闫敬东,周亮.螺杆泵最佳沉没度闭环控制系统[J].油气田地面工程,2010,29(3):5-6.

Qi Guangfeng,Yan Jingdong,Zhou Liang.Closed-loop control system with optimal submergence depth of screw pump[J].Oil-Gasfield Surface Engineering,2010,29(3):5-6.

[4]关成尧,赵国春,张翼翼,等.套管放气井环空流动与电泵井合理沉没度计算方法[J].石油学报,2010,31(1):152-156.

Guan Chengyao,Zhao Guochun,Zhang Yiyi,et al.Calculation method of multi-phase flow and optimization submergence depth of electric pump in casing annulus gas-venting wells[J].Acta Petrolei Sinica,2010,31(1):152-156.

[5]赵辉,李阳,高达,等.基于系统分析方法的油藏井间动态连通性研究[J].石油学报,2010,31(4):633-636.

Zhao Hui,Li Yang,Gao Da,et al.Research on reservoir interwell dynamic connectivity using systematic analysis method[J].Acta Petrolei Sinica,2010,31(4):633-636.

[6]Huang S J,Shih K R.Short-term load forecasting via ARMA model identification including nongaussian process considerations[J].IEEE Trans on Power Systems,2003,18(2):673-679.

[7]Infield D G,Hill D C.Optimal smoothing for trend removal in short term electricity demand forecasting[J].IEEE Trans on Power Systems,1998,13(3):1115-1120.

[8]Box G E P,Jenkins G M.Time series analysis-forecasting and control[M].Francisco,CA:Holden-daySan,1976:34-37．

[9]王宽敬,葛家理,刘月田,等.多模型自适应原油产量精确预测方法[J].石油学报,1996,17(2):70-75.

Wang Kuanjing,Ge Jiali,Liu Yuetian,et al.An accurate method to predict oil production with adaptive multi-model[J].Acta Petrolei Sinica,1996,17(2):70-75.

[10]毛志强,李进福.油气层产能预测方法及模型[J].石油学报,2000,21(5):58-61.

Mao Zhiqiang,Li Jinfu.Method and models for productivity prediction of hydrocarbon reservoirs[J].Acta Petrolei Sinica,2000,21(5):58-61.

[11]Czernichow T,Piras A,Imhof K,et al.Short term electrical load forecasting with artificial neural networks[J].Engineering Intelligent Systems,1996,4 (2):85-99.

[12]Rahman S,Bhatnagar R.Expert system based algorithm for short term load forecast[J].IEEE Trans on Power Systems,1988,3(2):392-399．

[13]Mori H,Kobayashi H.Optimal fuzzy inference for short-term load forecasting[J].IEEE Trans on Power Systems,1996, 11(1): 390-396.

[14]张辉,高德利.钻头下部未钻开地层的可钻性预测新方法[J].石油学报,2006,27(1):97-100.

Zhang Hui,Gao Deli.A new method for predicting drillability of un-drilled formation[J].Acta Petrolei Sinica,2006,27(1): 97-100.

[15]张广杰,刘明新,武若霞.神经网络在油田动态预测方面的应用[J].石油学报,1997,18(4):70-75.

Zhang Guangjie,Liu Mingxin,Wu Ruoxia.The application of an artificial neural networks to predict performance parameters of reservoir[J].Acta Petrolei Sinica,1997,18(4):70-75.

[16]张永明，齐维贵，王军栋,等.基于支持向量机的时间序列交叉负荷预报方法[J].电网技术,2007,31(2):207-210.

Zhang Yongming,Qi Weigui,Wang Jundong,et al.Time series crossover load forecasting approach based on support vector machines[J].Power System Technology,2007,31(2):207-210.

[17]王延江,杨培杰,史清江,等.一种基于支撑向量机学习预测井眼轨迹的新方法[J].石油学报,2005,26(5)：98-101.

Wang Yanjiang,Yang Peijie,Shi Qingjiang,et al.A novel method for predicting wellbore trajectory based on support vector machine[J].Acta Petrolei Sinica,2005,26(5)：98-101.

[18]潘勇,蒋军成,曹洪印，等.基于支持向量机方法的烃类物质自燃点预测[J].石油学报(石油加工),2009,25(2)：222-227.

Pan Yong,Jiang Juncheng,Cao Hongyin,et al.Prediction of auto-ignition temperatures of hydrocarbons based on support vector machine[J].Acta Petrolei Sinica(Petroleum Processing Section),2009,25(2):222-227.

[19]王军栋,齐维贵.基于EMD-SVM的江水浊度预测方法研究[J].电子学报,2009,37 (10):2130-2133.

Wang Jundong,Qi Weigui.Prediction of river water turbidity based on EMD-SVM[J].Acta Electronica Sinica,2009,37 (10):2130-2133.

[20]石广仁.支持向量机在多地质因素分析中的应用[J].石油学报,2008,29(2):195-198.

Shi Guangren.Application of support vector machine to multi-geological-factor analysis[J].Acta Petrolei Sinica,2008,29(2):195-198.

[21]Kim H S,Eykholt R,Salas J D.Nonlinear dynamics,delay times,and embedding windows[J].Physica D:Nonlinear Phenomena,1999, 127(1/2): 48-60.

[22]Grassberger P,Procaccia I.Measuring the strangeness of strange attractors[J].Physica D:Nonlinear Phenomena,1983,9 (1):189-208.

[23]Kugiurmtzis D.State space reconstruction parameters in the analysis of chaotic time series-the role of the time window length[J].Physica D:Nonlinear Phenomena,1996,95(1):13-28.

基于支持向量机的潜油柱塞泵沉没度预测

Submergence forecasting of a submersible plunger pump based on the support vector machine

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 13

编辑推荐

Metrics

本文评价

[1]	周斌, 王延江, 刘伟锋, 刘宝弟. 基于Hessian正则化支持向量机的多视角协同识别抽油机井工况方法[J]. 石油学报, 2018, 39(12): 1429-1436.
[2]	邢海燕, 党永斌, 王犇, 葛桦, 王尊策. 基于K-近邻隶属度模糊支持向量机的再造抽油杆损伤等级磁记忆定量识别[J]. 石油学报, 2015, 36(11): 1427-1432,1456.
[3]	朱怡翔石广仁. 火山岩岩性的支持向量机识别[J]. 石油学报, 2013, 34(2): 312-322.
[4]	易方李著信吕宏庆马维平. 基于模糊核支持向量机的管道磁记忆检测缺陷识别[J]. 石油学报, 2010, 31(5): 863-866.
[5]	王明达张来斌梁伟陈志刚. 基于独立分量分析和支持向量机的管道泄漏识别方法[J]. 石油学报, 2010, 31(4): 659-663.
[6]	李洪奇, 郭海峰, 郭海敏, 孟照旭, 谭锋奇, 张军. 复杂储层测井评价数据挖掘方法研究[J]. 石油学报, 2009, 30(4): 542-549.
[7]	马海, 王延江, 魏茂安, 胡睿. 地层可钻性级值预测新方法[J]. 石油学报, 2008, 29(5): 761-765.
[8]	石广仁. 支持向量机在多地质因素分析中的应用[J]. 石油学报, 2008, 29(2): 195-198.
[9]	闫铁, 毕雪亮, 王长江. 基于支持向量机和聚类分析理论的钻具失效分析方法[J]. 石油学报, 2007, 28(3): 135-140.
[10]	肖文生, 周小稀, 谷玉洪, 张世昌. 直线电机抽油机研制[J]. 石油学报, 2006, 27(5): 112-114.
[11]	付国太, 张柏, 任怀丰, 安喜德, 葛激扬, 鲁河清. 往复式磁力驱动柱塞泵举升工艺技术研究[J]. 石油学报, 2006, 27(4): 122-124,129.
[12]	张辉, 高德利. 钻头下部未钻开地层的可钻性预测新方法[J]. 石油学报, 2006, 27(1): 97-100.
[13]	李立毅, 吴红星, 寇宝泉, 邹积岩. 直接驱动直线电磁抽油机系统的研究及试验[J]. 石油学报, 2003, 24(5): 88-92.