往复泵故障示功图灰度矩阵法特征量研究

钟功祥; 邹明铭

doi:10.13433/j.cnki.1003-8728.2016.0221

往复泵故障示功图灰度矩阵法特征量研究

doi: 10.13433/j.cnki.1003-8728.2016.0221

1.
西南石油大学石油天然气装备教育部重点实验室, 成都 610500

基金项目:

省部共建"石油天然气装备"教育部重点实验室(西南石油大学)项目(2013sts03)资助

详细信息

作者简介:
钟功祥(1962-),教授,硕士,研究方向为石油机械工程科研和教学,zhonggx3170@163.com

计量
- 文章访问数: 204
- HTML全文浏览量: 34
- PDF下载量: 9
- 被引次数: 0
出版历程
- 收稿日期: 2014-04-04
- 刊出日期: 2016-02-05

Exploring Failure Characteristics of Indicator Diagram of Reciprocating Pump Based on Gray Matrix

1.
MOE Key Laboratory of Oil & Gas Equipment, Southwest Petroleum University, Chengdu 610500, China

摘要

摘要: 为了准确获取往复泵故障规律和特征量用以监控和诊断往复泵工作状态。本文通过人为实验模拟往复泵液力端泵阀漏失、弹簧断裂、柱塞磨损等6种典型故障,得到了往复泵在典型故障状态下的示功图并分析其产生原因和规律;利用MATLAB编程分别对6种故障状态下的示功图提取6组灰度矩阵特征向量,所得特征量样本数据通过支持向量机训练。结果表明,其故障自动识别率能达到95%以上,具有较高的诊断准确性,可作为往复泵在线监控和故障自动诊断的数据基础。
- 往复泵 /
- 示功图 /
- 特征量 /
- 故障规律 /
- 诊断 /
- MATLAB
Abstract: In order to accurately obtain the failure characteristics of a reciprocating pump so as to monitor and diagnose its working conditions, this article artificially simulated 6 kinds of typical failure at its hydraulic end such as the leakage of pump valve, spring break, plunger wear, obtaining the indicator diagram and law of the reciprocating pump under typical fault conditions. It extracted the feature of its gray matrix based on the indicator diagram and then pretreated them to extract 6 groups of characteristics with the MATLAB. The results obtained with support vector machine trained sample data show that the automatic fault recognition rate of the method reaches more than 95%, having a higher diagnostic accuracy. Therefore the method can be used to establish the automatic online monitoring and fault diagnosis data base of a reciprocating pump.
- data acquisition /
- design of experiments /
- eigenvalues and eigenfunctions /
- failure analysis /
- fault detection /
- feature extraction

HTML全文

参考文献(15)

[1]	毋文峰,陈小虎,苏勋家,等.基于峭度的ICA特征提取和齿轮泵故障诊断[J].机械科学与技术,2011,30(9):1583-1587 Wu W F, Chen X H, Su X J, et al. ICA feature extraction and fault diagnosis based on kurtosis for a gear pump[J]. Mechanical Science and Technology for Aerospace Engineering, 2011,30(9):1583-1587(in Chinese)
[2]	罗红梅,齐明侠,裴峻峰,等.三缸单作用往复泵泵阀冲击信号的实用提取新方法[J].振动与冲击,2008,27(8):158-160,168 Luo H M, Qi M X, Pei J F, et al. Practical method for extracting inpact signals of valve in triplex single role reciprocating pump[J]. Journal of Vibration and Shock, 2008,27(8):158-160,168(in Chinese)
[3]	Xu W H, Fu K. An intelligence diagnostic system for reciprocating machine[C]//Proceedings of IEEE International Conference on Intelligent Processing Systems, Beijing:IEEE, 1997:1520-1522
[4]	徐长航,刘吉飞,陈国明,等.经验模态分解和魏格纳-维利分布在往复泵泵阀振动信号特征提取中的应用[J].中国石油大学学报(自然科学版),2010,34(3):99-103 Xu C H, Liu J F, Chen G M, et al. Application of EMD and WVD to feature extraction from vibration signal of reciprocating pump valves[J]. Journal of China University of Petroleum (Edition of Natural Science), 2010,34(3):99-103(in Chinese)
[5]	赵玉明,冯子明,赵卫华.往复泵泵阀故障诊断方法[J].流体机械,2005,33(1):42-44 Zhao Y M, Feng Z M, Zhao W H. Diagnosticate method study of pump valve trouble[J]. Fluid Machinery, 2005,33(1):42-44(in Chinese)
[6]	赵志华,吴力,殷海双.基于紧致型小波神经网络的往复泵故障诊断[J].噪声与振动控制,2013,33(5):150-154 Zhao Z H, Wu L, Yin H S. Fault diagnosis technology of reciprocating pumps based on compact wavelet neural network[J]. Noise and Vibration Control, 2013,33(5):150-154(in Chinese)
[7]	由大伟.往复泵泵阀故障的智能诊断技术与实现[D].大庆:大庆石油学院,2004 You D W. The technology and realization of intelligent fault diagnosis for the pump valves of reciprocating pump[D]. Daqing:Northeast Petroleum University, 2004(in Chinese)
[8]	王国志,吴文海,柯坚,等.电液比例闭环变量柱塞泵的实验研究[J].机械科学与技术,2009,28(1):136-140 Wang G Z, Wu W H, Ke J, et al. An experimental study of closed-loop electro-hydraulic proportional variable piston pump[J]. Mechanical Science and Technology for Aerospace Engineering, 2009,28(1):136-140(in Chinese)
[9]	胡广杰.抽油机井实测示功图泵况诊断分析[M].北京:石油工业出版社,2008 Hu G J. Indicator diagram pump condition diagnosis analysis of pumping unit well[M] Beijing:Petroleum Industry Press, 2008(in Chinese)
[10]	王晓菡.用于工况诊断的示功图特征提取方法研究[D].北京:中国石油大学,2011 Wang X H. Study on indicator card feature extraction method for working condition diagnosis[D]. Beijing:China University of Petroleum, 2011(in Chinese)
[11]	Kong F S, Chen R H. A combined method for triplex pump fault diagnosis based on wavelet transform, fuzzy logic and neuro-networks[J]. Mechanical Systems and Signal Processing, 2004,18(1):161-168
[12]	Bloemen M C T, Boekema B K H L, Vlig M, et al. Digital image analysis versus clinical assessment of wound epithelialization:a validation study[J]. Burns, 2012,38(4):501-505
[13]	张德丰.详解MATLAB数字图像处理[M].北京:电子工业出版社,2010 Zhang D F. MATLAB digital image processing[M]. Beijing:Publishing House of Electronics Industry, 2010(in Chinese)
[14]	秦树人.工程信号处理[M].北京:高等教育出版社,2008 Qin S R. Engineering signal processing[M]. Beijing:Higher Education Press, 2008(in Chinese)
[15]	Feng K, Jiang Z N, He W, et al. A recognition and novelty detection approach based on curvelet transform, nonlinear PCA and SVM with application to indicator diagram diagnosis[J]. Expert Systems with Applications, 2011,38(10):12721-12729