基于支持向量机的潜油往复式油田抽油机工况诊断方法

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (1124 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract The submersible plunger pump is a new device for lifting in onshore oil wells. Its level of working condition diagnosis has important influence on production of oilfield. This paper proposes a working condition diagnosis method of submersible plunger pump. Based on analyzing the potential oil reciprocating pumping works, combining with the pump structure, it occurs different characters in loading and offloading process of submersible linear motor in different working conditions. By defining correlation parameter, the characteristic quantity can be extracted from operation data of submersible linear motor. The support vector machines take these characteristic quantities as input. the working condition diagnosis model based on support vector machines(SVM) of submersible plunger pump is proposed. In this condition, effectiveness and misjudgment rate of working condition diagnosis method can be analysed and validated on simulation platform.

Key words： Submersible plunger pump working condition diagnosis linear motor characteristic quantity SVM misjudgment rate

Received: 22 February 2012 Published: 25 March 2014

PACS:

TM85

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Yu Deliang
	Deng Shengchuan
	Zhang Yongming
	Qi Weigui

Cite this article:

Yu Deliang,Deng Shengchuan,Zhang Yongming等. Working Condition Diagnosis Method Based on SVM of Submersible Plunger Pump[J]. Transactions of China Electrotechnical Society, 2013, 28(4): 248-254.

URL:

http://dgjsxb.ces-transaction.com/EN/ OR http://dgjsxb.ces-transaction.com/EN/Y2013/V28/I4/248

[1] Wagner M R, Bernardo A, Ivan E C, et al. New concept for lifting in onshore oil wells[J]. IEEE Trans. on Industry Applications, 2008, 44(4): 951-961.
[2] 于德亮, 齐维贵, 邓盛川. 基于支持向量机的潜油柱塞泵沉没度[J]. 石油学报, 2011, 32(3): 534-538.
Yu Deliang, Qi Weigui, Deng Shengchuan, et al. Submergence forecasting of a submersible plunger pump based on the support vector machine[J]. Acta Petrolei Sinica, 2011, 32(3): 534-538.
[3] 付国太, 张柏, 任怀丰. 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.
Fu Guotai, Zhang Bai, Ren Huaifeng, et al. Lifting technology for reciprocating magnetic drive plunger pump[J]. Acta Petrolei Sinica, 2006, 27(4): 122-124.
[4] 于德亮, 齐维贵, 邓盛川. 基于支持向量机沉没度预测的潜油泵冲次优化研究[J]. 中国电机工程学报, 2011, 31(27): 138-144.
Yu Deliang, Qi Weigui, Deng Shengchuan, et al. Optimization frequency of stroke based on submergence depth SVM forecasting of submersible pump[J]. Proceedings of the CSEE, 2011, 31(27): 138-144.
[5] Muller K, Mika S, Ratsch G, et al. An introduction to kernel based learning algorithms[J]. IEEE Trans. on Neural Net works, 2001, 12 (2): 181- 201.
[6] 张学工. 关于统计学习理论与支持向量机[J]. 自动化学报, 2000, 26(1): 32-44.
Zhang Xuegong. Introduction to statistical learning theory and support vectormachines[J]. Acta Automatica Sinica, 2000, 26 (1) : 32-44.
[7] 杜京义, 侯媛彬. 基于核的多故障分类器及其应用[J]. 煤炭学报, 2007, 32(1): 103-106.
Du Jingyi, Hou Yuanbin. Multi-fault classifier with kernels and its applications[J]. Journal of China Coal Society, 2007, 32(1): 103-106.
[8] Vapnik V N. An overview of statistical learning theory[J]. IEEE Trans. on Neural Net Works, 1999, 10(5): 988-999.
[9] Schölkopf B, Mika S, Burges C J C. Input space versus feature space in kernel-based methods[J]. IEEE Trans. on Neural Net-works, 1999, 10(5): 1000-1017.
[10] Luts J, Ojeda F, Van de Plas. A tutorial on support vector machine-based methods for classification problems in chemometrics[J]. Analytica Chimica Acta, 2010, 665(2): 129-145.
[11] 陈理渊, 黄进. 基于支持向量机的电机转子断条故障诊断[J]. 电工技术学报, 2006, 21(8): 48-52.
Chen Liyuan, Huang Jin. Motor broken rotor bar fault diagnosis with support vector machine[J]. Transactions of China Electrotechnical Society, 2006, 21(8): 48-52.
[12] 罗慧, 王友仁, 崔江. 基于分数阶Hilbert变换的模拟电路双层故障特征提取方法[J]. 电工技术学报, 2010, 25(6): 150-154.
Luo Hui, Wang Youren, Cui Jiang. A method of analog circuit two-layer fault feature extraction based on fractional hilbert transform[J]. Transactions of China Electrotechnical Society, 2010, 25(6): 150-154.
[13] Bottou L, Cortes C, Denker J, et al. Comparison of classifier methods: a case study in handwritten digit recognition[C]. Proc of the Int Conf on Pattern Recognition, Jerusalem, 1994: 77-82.
[14] Krebel U. Pairwise classification and support vector machines[C]. Advances in Kernel Methods-Support Vector Learning, Cambridge, MA, 1999: 255-268.
[15] 杜京义, 侯媛彬. 基于核方法的故障诊断理论及其方法的研究[M]. 北京: 北京大学出版社, 2010.
[16] 卢锦玲, 朱永利, 赵洪山, 等. 提升型贝叶斯分类器在电力系统暂态稳定评估中的应用[J]. 电工技术学报, 2009, 24(5): 179-181.
Lu Jinling, Zhu Yongli, Zhao Hongshan, et al. Power system transient stability assessment based on boosting bayesian classifier[J]. Transactions of China Electrotechnical Society, 2009, 24(5): 179-181.
[17] 吴立增, 朱永利, 苑津莎. 基于贝叶斯网络分类器的变压器综合故障诊断方法[J]. 电工技术学报, 2005, 20(4): 45-51.
Wu Lizeng, Zhu Yongli, Yuan Jinsha. Novel method for transformer faults integrated diagnosis based on bayesian network classifier[J]. Transactions of China Electrotechnical Society, 2005, 20(4): 45-51.
[18] Cherkassky V, Ma Y. Practical selection of SVM parameters and noise estimation for SVM regression[J]. Neural Networks, 2004, 17(1): 113-126.
[19] Chua K S. Efficient computations for large least square support vector machine classifiers[J]. Pattern Recognition Letters, 2003, 24(3): 75-80.