有杆抽油系统故障递阶诊断的故障分辨研究

doi:10.11885/j.issn.1674-5086.2012.11.19.09

摘要/Abstract

摘要：

有杆抽油系统工况极其恶劣，发生故障的概率较高。针对有杆抽油系统的特点及其故障诊断目前存在的问
题，提出基于示功图的有杆抽油系统故障递阶诊断法，该方法分为故障分辨和故障识别两个阶段，即首先在故障分辨
阶段根据正常（或平稳状态）样本的统计规律把示功图分为故障类和非故障类；然后采用基于示功图的有杆抽油系统
故障识别的搜索树方法，对故障样本进行故障类型的识别。它提高了故障诊断系统的故障诊断性能，且不需要建立和
求解有杆抽油系统力学模型，也不存在训练集问题，并能反映出有杆抽油系统自身的基本特征。故障分辨过程包括：
在训练阶段，t 检验剔除异常数据后，通过X2拟合优度检验确定样本的随机分布形式及其参数，进而计算出正常区域
和故障区域；在分辨阶段，根据测试样本是否有特征量落入故障区域来判断其分类。实例表明故障分辨过程能从大量
的数据中筛选出故障样本，分辨的正确率比较高；训练样本的统计规律能反映油井实时的生产状况。

关键词: 有杆抽油系统, 故障递阶诊断, 故障分辨, 示功图, X2 拟合优度检验, 正常区域

Abstract:

There is higher fault probability under the bad work conditions of rod pumping system. Because of the large amount
of sample and the long-time steady status，this paper proposes hierarchical fault diagnosis method. Fault distinguishing and
fault identification are two phases in this method. In fault distinguishing，fault phase and normal phase are classified according
to statistical rule of normal sample in dynamometer card. Combining statistical theory and search-tree，fault identification is
processed in fault sample. Using this method，mechanical model of rod pumping system is not to be established and training
set of fault sample is not necessary. Fault distinguishing process includes：fault taring phase and fault distinguishing phase.
In fault training phase，stochastic distribution rule and parameters of samples are determined by X2 goodness-of-fit test after
abnormal samples are rejected，then normal area and fault area is calculated. In fault distinguishing phase，classification of
fault is estimated according to whether or not feature value of test sample is in fault area. Examples indicate fault samples can
be selected from large number of samples in distinguish fault and correct rate of fault distinguishing is high. Statistical rule of
training samples can reflect the actual production of oil well.

Key words: rod pumping system, fault hierarchical diagnosis, fault distinguish, surface dynamometer card, X2 Goodness-offit
test, normal area

梁华. 有杆抽油系统故障递阶诊断的故障分辨研究[J]. 西南石油大学学报(自然科学版), DOI: 10.11885/j.issn.1674-5086.2012.11.19.09.

Liang Hua. Hierarchical Fault Diagnosis of Rod Pumping System Based on
Fault Distinguishing[J]. 西南石油大学学报(自然科学版), DOI: 10.11885/j.issn.1674-5086.2012.11.19.09.

0
/ / 推荐

导出引用管理器 EndNote|Ris|BibTeX

链接本文: http://journal15.magtechjournal.com/Jwk_xnzk/CN/10.11885/j.issn.1674-5086.2012.11.19.09

http://journal15.magtechjournal.com/Jwk_xnzk/CN/Y2014/V36/I5/169

参考文献

[1] Abello J，Houang A，Russell J. A hierarchy of pattern

recognition algorithms for the diagnosis of sucker rod

pumped wells[C]. 5th International Conference on Computing

and Information，1993：359–364.

[2] Gibbs S G，Neely A B. Computer diagnosis of down-hole

conditions in sucker rod pumping wells[C]. SPE 1165，

1965.

[3] 张宏，刘海浪，孙应民. 定向井有杆泵抽油系统的有限

元分析[J]. 石油学报，2000，21（6）：102–106

Zhang Hong，Liu Hailang，Sun Yingmin. Fem analysis of

sucker-rod pumping system for directional well[J]. Acta

Petrolem Sinica，2000，21（6）：102–106.

[4] 刘清友，何玉发. 有杆抽油系统诊断方法研究与应

用[J]. 西南石油大学学报：自然科学版，2008，30（1）：

1–4.

Liu Qingyou，He Yufa. Study of the method to diagnose

sucker rod pumping system and its application[J]. Journal

of Southwest Petroleum University：Science & Technology

Edition，2008，30（1）：1–4.

[5] 彭勇，余国安. 识别泵工况的分类器设计[J]. 西安石油

学院学报，1995，10（3）：35–37.

Peng Yong，Yu Guo′an. Design of the separator used to

recognize the working condition of the sucker rod pump in

a pumping well[J]. Journal of Xi′an Petroleum Insistute，

1995，10（3）：35–37.

[6] Cerqueira J F，Correa J F，Bittencourt A C. Development

of an intelligent distributed management system for automated

wells[J]. SPE 77609，2002.

[7] Zhang Shirong，Tang Yuling. Indirect measurement of

dynamometer card of pumping unit[C]. The 7th World

Congress on Intelligent Control and Automation，2008：

4952–4955.

[8] Rowlan O L，Lea J F，Mccoy J N. Overview of beam pump

operations[C]. SPE 110234，2007.

[9] Xu Peng，Xu Shijin，Yin Hongwei. Application of selforganizing

competitive neural network in fault diagnosis

of sucker rod pumping system[J]. Journal of Petroleum

Science and Engineering，2007，58（1–2）：43–48.

[10] 张强，许少华. 智能动态诊断模型及在示功图识别中

的应用[J]. 计算机工程与应用，2009，45（4）：215–217.

Zhang Qiang，Xu Shaohua. Interlligent dynamic diagnosis

method and its application in identification of indicator diagram[

J]. Computer Engineering and Applications，2009，

45（4）：215–217.

[11] De Lima，Guedes，Sliva. Application of fourier descriptors

and pearson correlation for fault detection in sucker

rod pumping system[C]. IEEE Conference on Emerging

Technologies and Factory Automatio，2009：1–4.

[12] Liang Hua，Li Xunming. Accurate extraction of valve

opening and closing points based on the physical meaning

of surface dynamometercard[J]. Petroleum Exploration

and Development，2011，38（1）：109–115.

[13] 陈魁. 应用概率统计[M]. 北京：清华大学出版社，2000.

[14] 张玉斌，齐卫红. 有杆泵抽油系统可靠性数字仿真研

究[J]. 系统仿真学报，2003，15（2）：242–246.

Zhang Yubin，Qi Weihong. Research on the reliability digital

simulation of rod pumping system[J]. Journal of System

Simulation，2003，15（2）：242–246.

[15] Scott W L，Elton J S，Albert S G. Total downstroke

friction from downhole dynamometer analysis[C]. SPE

67274，2001.

[16] Mccoy J N，Jennings J W，Capps K S，et al. Simplified

computer-aided analysis of electrical current in motors

used for beam pumping systems[C]. SPE 25447，1993.

[17] Doty D R. Performance of electric submersible pumps in

gassy wells[C]. SPE 22767，1994.

[18] Cerqueira J F，Correa J F，Bittencourt A C. Development

of an intelligent distributed management system for automated

wells[C]. SPE 77609，2002.

[19] Li Hongsheng，Wang Yu，Ding Yongzhong，et al. Implemention

of network-computing and NN based remote

real-time oil well monitoring system[C]. 2005 International

Conference on Neural Networks and Brain，2005.