往复泵泵阀故障的智能诊断技术与实现
详细信息    本馆镜像全文|  推荐本文 |  |   获取CNKI官网全文
摘要
市场的迫切需求促进了机械故障珍断技术的迅猛发展,故障诊断技术发展至今,已经提出了大量的诊断方法,但是其实际应用成果显得非常不足,能在工业装置上实际应用的还不多。在故障诊断领域,还有许多问题亟待解决。目前,往复泵泵阀故障诊断需要解决的两个关键问题是有效提取往复泵工作时非平稳时变信号中的故障特征和将故障特征准确分类。
     故障诊断常用的方法是以泵缸体上的振动信号作为系统特征信号来提取故障特征向量。这种振动诊断技术虽然取得了一定的成果,但是在多个泵阀同时发生故障的场合,这种方法遇到了无法解决的难题,使之不得不求助于粗集理论、遗传算法等数据处理方法来分辩故障类型和判断故障具体发生在哪一个泵阀上。
     为此,本文创造性地提出以常见的压力信号(阀箱内的压力)作为系统特征信号来提取故障特征向量的方法。这种方法信号测取简单、处理方便,有着振动信号方法无法比拟的优点。文中利用时域中的相关分析和频域中的功率谱分析、小波包分析技术提取了故障特征向量,且各故障之间的特征区分明显,充分验证了此方法的有效性。此方法的优点在于特征信号取自于阀箱内的压力,不易受到外部环境的干扰,适用于多个泵阀同时发生故障的情形。同时,文中还构造了三层的前向神经网络,以小波包分析提取的故障特征向量作为网络的训练样本数据,采用加惯性因子、共轭梯度法和迭代过程中改变学习率的反向传播算法来对神经网络进行训练,并采用试验的方法调整神经网络的初始值。在确定了神经网络的结构和参数后,经检验数据验证训练后的神经网络所得的网络结构和参数是合理的。
     本文以故障诊断系统为核心开发了往复泵泵阀故障的智能诊断系统。数据采集系统用VC++进行开发,其主要功能是进行现场数据的采集和数据库管理。故障诊断系统以Matlab作为软件平台,用小波包对数据进行处理并提取故障特征向量,并利用神经网络技术实现泵阀的故障诊断功能。
Urgent requirement of market has promoted the improvement of the technology of mechanical fault diagnosis (FD). So far, many methods have been proposed in the field of fault diagnosis. But practical application is insufficient, and less in the application of industrial devices. Two key issues of fault diagnosis for the pump valves of reciprocating pump are extracting the fault feature information of stationary process efficiently from system feature signals and identifying the specific faults correctly with analysis of causes.
    At present, usual method of FD is measuring vibration signal as system feature signals for fault characteristic eigenvectors pickups. Although the technology of vibration diagnosis has acquired some achievement, on the occasion of having several faults , the method has some trouble that cannot be solved . To solve this problem, some methods i.e. rough-set theory and genetic algorithm have to be used to identify specific fault and decide which pump valve has fault.
    The paper creatively proposes the idea ofusing ordinary pressure signals;(pressure in valve boxes) as system feature signal to pickup fault characteristic eigenvectors and verifies the correction of the method through self-correlation analysis in the time-zone and power spectral and wavelet packet analysis in the frequency-zone. What's more, it is not easy to be disturbed by outside environment for requiring the signals from the inside of reciprocating pump cylinder. The method has special obvious advantages to diagnosis the faults when several faults exist simultaneously. The paper constructs a three-layer forward neural network to diagnosis the fault and trains the network with characteristic eigenvectors extracted through the wavelet packet analysis , when training the net using the method of adding inertia item and the BP algorithm of conjugate gradient method, at the same time adapt the initial data of the network through the test. After confirm the construction and parameters of the net, the result is valid and justified through the verification using the test sample data.
    The paper develops the intelligent fault diagnosis system regarded/the fault diagnosis factor as the center of the whole system. The main function of the data collection system developed by VC++ program is collecting field data and managing the data. And the fault diagnosis system on the basis of Matlab software platform pick up the fault characteristic eigenvectors through the method of wavelet packet analysis and realize the fault diagnosis using the technology of neural network.
引文
[1] 白允东,屠良尧,杨纯宝.时域径向基函数网络诊断方法在往复泵故障诊断中的应用[J].振动工程学报,2002,15(2):162~165
    [2] 张萍,王桂增,周东华.动态系统的故障诊断方法[J].控制理论与应用,2000,17(2):153~158
    [3] 周东华,王庆林.基于模型的控制系统故障诊断技术和最新进展[J].自动化学报,1995,21(2):224~227
    [4] 黄文虎,夏松波,刘瑞岩.设备故障诊断原理、技术及应用[M].北京:科学出版社,1997:53~54
    [5] 裴峻峰,杨其俊.机械故障诊断技术[M].东营:石油大学出版社,1997.2~6,89~92
    [6] 周东华,王桂增.故障诊断技术综述[J].化工自动化及仪表,1998,25(1):58~62
    [7] Kumamaru K, Hu J, Inoue K and Soderstrom T. Robust fault detection using index of Kullback discrimination[C]. Proc. of IFAC World Congress, San Francisco, USA, 1996,205~210
    [8] Gertler J. Diagnosis parametric faults: from parameter estimation to parity relations[C], American Control Conference,Seattle,USA, 1995,1615~1620
    [9] Frank P M. Fault Diagnosis in Dynamics System Using Analytical and Knowledge Based Redundency—A Survey and Some New Results[J]. Automatica,1990,(26):459~474.
    [10] Isermann R.Process Fault Detection Based on Modelling and Knowledge Based Redundancy—A Survey[J]. Automatica, 1984,20:387~404.
    [11] 杨其俊,裴峻峰,田佳禾.钻井泵泵阀状态的监测与故障诊断[J].石油大学学报,1998,22(3):60~62
    [12] 雷继尧,何世德.机械故障诊断基础知识[M].西安:西安交通大学出版社,1989:1~8
    [13] 王占山,李平,任正云,李奇安.非线性系统的故障诊断技术[J].自动化与仪器仪表,2001,(5)8~10.
    [14] 杨叔子,丁洪,史铁林,郑小军.基于知识的诊断推理.北京:清华大学出版社,南宁:广西科学技术出版社,1993:2~44
    [15] 时文刚,王日新,黄文虎.基于粗集理论的往复泵泵阀故障诊断方法.中国机械工程,2002,13(16):1389~1391
    [16] 杨其俊,孙辉,裴峻峰.连续小波变换在往复泵泵阀故障识别中的应用.振动、测试与诊断,2000,20(1):47~52
    [17] 杨其俊,徐长航,孙辉,李继志.三缸泵泵阀故障的幅值域多参数诊断法.石油机械,1999,27(1):35~38
    [18] Randall R B. The Relationship between Spectral Correlation and Envelope Analysis in the Diagnosis of Bearing Fault and Other Cyelostationary Machine Signals[J]. Mechanical System and Signal Processing,2001,15(5):945~962
    [19] 王新晴,王耀华,陈六海等.齿轮传动中几种典型故障的振动图谱分析[J].机械传动,1999,(3):34-36
    [20] Willsky A S.Survey of Design Methods for Failure Decision in Dynamics System[J].Automation,1976,(12): 601~611.
    [21] 杨其俊,徐长航.烈谱分析在往复泵故障诊断中的应用研究.振动工程学报,2001,14(4):464~468
    [22] 崔锦泰著,程正兴译.小波分析导论[M].西安:西安交通大学出版社,1995
    [23] 李建平.小波分析与信号处理.理论,应用及软件实现.重庆:重庆出版社,1997
    [24] S.G. Mallat. A Theory for Multiresolution Signal Decomposition: The Wavelet Representation. IEEE Trans. on Pattern Analysis and Machine Intelligence, 1989,11(7),674~693
    [25] L.科恩著,白居宪译.时—频分析:理论与应用[M].西安:西安交通大学出版社,1998
    [26] Satish L. Short-time Fourier and wavelet transforms for fault detection in power transformers during impulse tests. In: IEE Proc. Sci. Meas. Technol., 1998,145(2):77~84
    
    
    [27] 张贤达.现代信号处理[M].北京:清华大学出版社,1995
    [28] 王将萍,王鸿飞,王素英.基于小波多分辨分析的往复机械故障特征提取与识别.西安石油学院学报,1998,13(1):30~32,52
    [29] Mallat S G, Hwang W L, Singularity detection and processing with wavelet. IEEE Trans on Information Theory, 1992,38(2): 617~643
    [30] 秦前清,杨宗凯.实用小波分析[M].西安:西安电子科技大学出版社,1994
    [31] 杨国安,钟秉林,黄仁,贾民平.机械故障信号分析小波包分解的时域特征提取方法研究.振动与冲击,2001,20(2):25~28.31
    [32] 刘树林,张嘉钟,徐敏强,黄文虎.基于小波包与神经网络的往复压缩机故障诊断方法.石油矿场机械,2002,31(4):1~3
    [33] 张佩瑶,马孝江,王吉军,朱泓.小波包信号提取算法及其在故障诊断中的应用。大连理工大学学报,1996,37(1):68~72
    [34] KocCK,Chen G R, Chui C K. Complexity analysis of wavelet signal decomposition and reconstruction.IEEE Trans on Aerospace and Electronic Systems. 1994,30:910~918
    [35] Huang Qun-gu, Ren zhen,et al. Fault signal Analysis in Power System Based on Similar Wavelet Transforms. Journal of South China University of Technology, 2001,29(5),5~9
    [36] 张兵,李唯利,谢国胜.神经网络理论的发展与前沿问题.湖南电力,2001,21(4):9~12
    [37] 虞和济等.基于神经网络的智能诊断[M].北京:冶金工业出版社,2000
    [38] Sorsa T, Heikki N,Koivo. Neural Networks in Process Fault Diagnosis. IEEE Trans. On System,Man, and Cybernetics. 1991,21 (4):815~825
    [39] Naidu S.R., E.Zafiriou, et al. Use of Neural Networks for Sensor Failure Detection in a Control System. IEEE Control Systems Magazine. 1990,49(2):225~231
    [40] James A, Leonard and Mark A, Kramer. Radial Basis Function Networds for Classifying Process Faults. IEEE Control Systems. 1991,2(1):31~38
    [41] 汪维崧,何勇,李恩光.基于知识的汽车发动机故障诊断系统.机械制造,1999(5):39~41
    [42] 蔡卫峰.神经网络技术在分布式系统智能故障诊断中的应用.化工自动化及仪表,2002,29(5):12~17
    [43] 丛爽.面向MATLAB工具箱的神经网络理论与应用.合肥:中国科学技术大学出版社,1998,6~12
    [44] 王永骥,涂健.神经元网络控制[M].北京:机械工业出版社,1998,23~32
    [45] 丛爽,典型人工神经网络的结构、功能及其在智能系统中的应用.信息与控制,2001,30(2):97~103
    [46] B Widrow, M Bilello. Nonlinear Adaptive Signal Processing for Inverse Control. World Conference on Neural Network (WCNN'94), 1994
    [47] 李学桥,马莉.神经网络-工程应用[M].重庆:重庆大学出版社.1996:10~15
    [48] 徐丽娜.神经网络控制[M].哈尔滨:哈尔滨工业大学出版社,1999:12~16
    [49] 焦李成.神经网络系统理论.西安:西安电子科技大学出版社,1999
    [50] 丛爽,向微.BP网络结构、参数及训练方法的设计与选择.计算机工程,2001,27(10):36~38
    [51] 高雪鹏,从爽.BP网络改进算法的性能对比研究。控制与决策,2001,16(2):167~171
    [52] David J.Kruglinski,Scot Wingo,George Shepherd著,希望图书创作室译.Visual C++6.0技术内幕[M]北京:北京希望电子出版社,1999
    [53] 霍志红,张志学,郭江,唐必光.基于神经网络的故障诊断研究.工业控制计算机,2001,14(10):19~21

© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号

地址:北京市海淀区学院路29号 邮编:100083

电话:办公室:(+86 10)66554848;文献借阅、咨询服务、科技查新:66554700