基于贝叶斯网络的发动机故障诊断
详细信息    本馆镜像全文|  推荐本文 |  |   获取CNKI官网全文
摘要
发动机作为典型的往复式机械设备,在整个机械系统中占有重要的地位,然而其结构的复杂性使得发动机的故障呈现出多样性,另外由于工作环境噪声、信息采集系统精度、数据处理和故障诊断方法的影响,使得发动机故障诊断中不确定性尤为突出,因此解决不确定性是目前国内外相关学者的主要研究内容。
     以贝叶斯理论为基础的贝叶斯网络通过实践积累可以随时进行在线学习以改进网络结构和参数,提高故障诊断能力,并且基于网络结构的概率推理算法,可以随时更新网络中的概率信息。可见贝叶斯网络非常适合解决复杂的、不确定性的问题。
     本文首先阐述了本课题国内外的研究现状,以及贝叶斯网络解决发动机故障诊断的可行性,其次重点研究了贝叶斯网络的建立,并将粒子群优化算法应用于贝叶斯网络参数优化上,给出粒子群优化的贝叶斯网络结构。通过对柴油机进行试验得到振动信号,然后用小波能量谱对振动信号进行特征值的提取。用训练样本训练贝叶斯网络,用测试样本对贝叶斯网络的训练结果进行测试。得到贝叶斯网络对柴油机故障诊断的结论,对比结论表明贝叶斯网络能够很好的解决柴油机故障诊断中的不确定性。且发现此方法可以对发动机多故障并存的故障类型进行故障诊断,这也为以后学者研究多故障并存提供了方向。
Engine as a typical reciprocating machinery and equipment, mechanical systems occupyan important position, but the complexity of its structure showing a diversity of the enginefailure, as a result of environmental noise, the accuracy of the information collection system,data processing and fault diagnosiseffects, resulting in engine failure diagnostic uncertainty inparticularly prominent, so to solve the uncertainty is the main contents of the current domesticand foreign scholars.
     Bayesian network based on Bayesian theory practice has accumulated at any time, onlinelearning to improve the network structure and parameters, to improve the fault diagnosiscapability, and probabilistic inference algorithm based on network structure, you can alwaysupdate the probability of information in the network. Be seen, the Bayesian network is verysuitable to solve the problem of complexity and uncertainty.
     This paper first describes the current situation of this subject at home and abroad, as wellas the feasibility of Bayesian networks to solve the engine fault diagnosis, followed by focuson the establishment of the Bayesian network, and particle swarm optimization algorithm isapplied to the Bayesian network parameter optimization, particle swarm optimization of theBayesian network structure.
     . We can get the vibration signal by diesel engine test, extract the eigenvalue of thevibration signal by Wavelet power spectrum. Training samples used to train Bayesiannetworks, and test results of the test samples on the training of the Bayesian network. Theconclusion of the Bayesian network for fault diagnosis of diesel engine, the contrastconcluded that the Bayesian network can be a good diesel engine fault diagnosis ofuncertainty. And found that this method can be diagnosed by the coexistence of multi-faulttype of engine failure, it also provides a direction later scholars of multiple faults coexist.
引文
[1]齐伟.发动机状态监测与诊断方法的研究[期刊论文].郑州铁路职业技术学院学报,2009.
    [2]孙颖楷.内燃机智能故障诊断系统的研究及应用[博士学位论文].重庆:重庆大学,2007.
    [3]张晓丹.汽车发动机故障诊断中不确定性的贝叶斯网络解法[博士学位论文].沈阳:东北大学,2005.
    [4]钱娜.贝叶斯网络在汽车发动机故障诊断中的应用研究[硕士学位论文].沈阳:沈阳工业大学,2009.
    [5]张燕军.发动机故障多级融合诊断研究[期刊论文].计算机测量与控制,2009.
    [6]赵龙庆.基于小波包分析和神经网络柴油机故障诊断研究[J].小型内燃机与摩托车,2009,38(3):9~11.
    [7]杨昌昊.基于不确定性理论的机械故障诊断方法研究[博士学位论文].中国科学技术大学,2009.
    [8]郑善亮.汽车发动机故障诊断研究的理论与方法[硕士学位论文].重庆:重庆交通大学,2009.
    [9]陈凯.复杂系统故障诊断中的模糊聚类方法.上海交通大学学报.Vo.32,No.6,1998:61~64.
    [10]张德利.基于贝叶斯网络的故障智能诊断方法研究[博士学位论文].华北电力大学,2008.
    [11]陈小岗.基于贝叶斯网络的智能诊断技术及系统开发[硕士学位论文].南京理工大学,2005.
    [12]曹龙汉.柴油机智能化故障诊断技术研究[博士学位论文].重庆:重庆大学,2001.
    [13] Tahani,Information fusion in computer vision using the fuzzyintegral,Systems,Man andCybernetics[J].IEEE Transactions on,1990,20(3). 733~741.
    [14]刘思远.信息融合和贝叶斯网络集成的故障诊断理论方法实验研究[博士学位论文].燕山大学,2008.
    [15]罗江华.贝叶斯网络在机械故障诊断中的应用研究[硕士学位论文].重庆:重庆大学,2006.
    [16] Zhang S.Best basis-based intelligent machine fault diagnosis [J].Mechanical Systems andSignal Processing,2005,19(2):357~370.
    [17]李检川.贝叶斯网络故障诊断与维修决策方法及应用研究[博士学位论文].国防科技大学,2002.
    [18]聂岩.基于贝叶斯网络的变压器故障诊断方法研究[硕士学位论文].华北电力大学,2007.
    [19]周曙.基于贝叶斯网的电力系统故障诊断方法研究[博士学位论文].西南交通大学,2010.
    [20]傅军.贝叶斯网络在柴油机动力装置故障诊断中的应用.上海海运学院学报,2001,22(3):68~72.
    [21] Liu Rujie.A D-S based multi-channel information fusion method using classifier'suncertainty measurement [J].Signal Processing Proceedings,2000:1297~1300.
    [22] J W Grzymala-Busse, M Fu.A comparison of several approaches to missing attributevalues in data mining.In:Proc of the 2nd Int’Conf on Rough Sets and Current Trends inComputing. Berlin:Springer-Verlag,2000.378~385.
    [23] Bo Thiesson,Christopher Meek&David Heckerman.Accelerating EM for LargeDatabases. Machine Learning, 2001,279~299.
    [24] Pernkopf.Bayesian network classifier versus selective k-NN classifier [J].PatternRecognition.2005,1-10.
    [25]高丽.汽车发动机故障诊断中不确定性问题的贝叶斯网络解法研究[硕士学位论文].沈阳航空工业学院,2009.
    [26]张高峰.贝叶斯网络于车身故障诊断中的应用研究[硕士学位论文].上海:上海交通大学,2008.
    [27] Cheng J;Learning Bayesian networks from date;An information theory based approach,University of luster U K,1998:53~67
    [28] Radu stefan niculescu,Tom M.Mitchell,R.Bharat Rao;Bayesian network learning withparameter constraints;Journal of machine learning research,2006(7):1357~1383
    [29] Chickering D.M;Learning Bayesian networks is NP-complete;learning from data:AIand Statistics,New York,1996:121~130
    [30] Gregory F.Cooper,Edward Herskovits;A Bayesian method for the induction ofprobabilistic networks from data;Machine Learning(S0885-6125),1992,9(4):309~347
    [31] Angeli c,AtheRon D;A model-based method for an on-line diagnosticknowledge—based system;Expert systems,2001,18(3)
    [32]舒苗淼.基于振动信号的柴油机小波神经网络故障诊断研究[硕士学位论文].太原:中北大学,2009.
    [33] Wolff K E;A conceptual view of knowledge bases in rough set theory;Lecture Notes inComputer Science;Vol.2005,Spring-Berlin,2001:220~228
    [34] Ganter B,Wille R;Formal Concept Analysis,Mathematical Foundations,Berlin:Springer,1999
    [35] Goumas,S.K.Classification of washing machines vibration signals using discrete waveletanalysis for feature extraction [J].IEEE Transactions on Instrumentation andMeasurement,2002,51(3):497~508.
    [36]皮骏.基于粗糙集理论的旋转机械故障诊断技术[博士学位论文].西安:西北工业大学,2006.
    [37] Ruben Villarino,Johann F.Bohme.Misfire Detection in Automotive Engine UsingStructure-Borne Sound [J].SAE Paper,2004.
    [38]张楠.基于贝叶斯网络的汽轮机振动故障诊断研究[硕士学位论文].华北电力大学,2007.
    [39]王志鹏.基于信息融合技术的故障诊断方法的研究及应用[博士学位论文].大连:大连理工大学,2001.
    [40] Gary G,Yen Kuo-Chung;Wavelet Packet Feature Extraction for Vibration Monitoring;IEEE Transactions on Industrial Electronics,2000,47(3):12~14
    [41] A.J.C.Sharkey,G.O.Chandroth,N.E.Sharkey;A Multi-Net System for the Fault Diagnosisof a Diesel Engine.Neural Comput & Applic(2000)9:152~160
    [42] M.K.Stern.Naive Bayes Classifiers for User Modeling [D].Amherst,MA:University ofMassachuestts,1999.
    [43]李凤鸣.基于小波神经网络的柴油机燃油系统故障诊断的设计与实现[硕士学位论文].山东大学,2010.
    [44]田静宜.基于粗糙集和神经网络的柴油机故障诊断研究[硕士学位论文].太原:中北大学,2011.
    [45]陈二强.贝叶斯网络在飞机故障诊断与维修优化中的应用[硕士学位论文].电子科技大学,2006.
    [46]刘亚军.基于小波分析和神经网络的电机故障诊断研究[硕士学位论文].太原:中北大学,2009.
    [47] Castillo,Enrique,Gutiérrez,J.Manuel,A.S.Hadi.Expert Systems andProbabilistic NetworkModels[M].New York:Springer-Verlag.1997:481–528.
    [48]严莉.基于多源信息融合的发动机故障诊断研究[硕士学位论文].太原:中北大学,2010.
    [49]罗江华.贝叶斯网络在机械故障诊断中的应用研究[硕士学位论文].重庆:重庆大学,2006.
    [50]翟光瑞.基于瞬时转速和振动信号的柴油机故障诊断研究[硕士学位论文].太原:中北大学,2009.
    [51]赵慧敏.柴油机非稳态振动信号分析与智能故障诊断研究[博士学位论文].天津:天津大学,2010.
    [52] P.Domingos.On the Optimality of the Simple Bayesian Classifierunder zero-one Loss[J].Machine Learing,1997,29:103-130.
    [53]王玉雷;RBF网络在发动机故障诊断中的应用[J].微计算机信息,2009,24(1):183~185.
    [54]王裕鹏.基于小波分析和神经网络的动力机械故障诊断研究[硕士学位论文].昆明:西南林学院,2007.
    [55]黄友平.贝叶斯网络研究[博士学位论文].中国科学院研究生院,2005.
    [56]毛恒.粒子群优化算法的改进及应用研究[博士学位论文].香港:华侨大学,2007.
    [57]高芳.智能粒子群优化算法研究[博士学位论文].哈尔滨:哈尔滨工业大学,2008.
    [58]董延胜.粒子群算法在神经网络参数优化中的应用[硕士学位论文].洛阳:河南科技大学,2009.
    [59]刘建华.粒子群算法的基本理论及其改进研究[博士学位论文].中南大学,2009.
    [60]李丹.粒子群优化算法及其应用研究[博士学位论文].沈阳:东北大学,2007.
    [61] G.Zhang.Forecasting with artificial neural networks:thestate of the art[J].Int.J ofForecasting 1998,14:35–62.

© 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