基于混沌相空间重构的轧机故障诊断预测研究
详细信息    本馆镜像全文|  推荐本文 |  |   获取CNKI官网全文
摘要
当前,工矿企业大型设备的数目越来越多,关键设备的检测与诊断技术所带来的社会效益和经济效益,也不断为人们所认识。因此,预防维修到预知维修的转变也成为必然,顺应了机械设备故障诊断的趋势。
     对于时间序列,利用时间序列的相空间重构可以保存系统的某些性质,在此基础上可以建立动力系统的非线性模型并进行预测。对于机械系统状态的预测,就是根据已知的某时刻以前机械系统的状态运动轨迹,预测该时刻以后最大可预测尺度内轨迹的运动状态。
     论文首先分析了混沌的复杂特性以及其他混沌识别方法的利弊。针对所作分析,提出了一种混沌相空间重构的方法:即运用互信息函数方法确定有效延迟时间;CAO方法确定最佳嵌入维数。
     然后根据相空间重构所确定的混沌时间序列的延迟时间以及嵌入维数,运用Volterra级数算法推算出未来一定时间内的时间序列,以达到对设备未来故障状态预测分析的目的。
     为解决强噪声环境中的大型机械故障的早期信号微弱的问题,运用了Duffing振子的间歇混沌现象对强噪声背景中的微弱信号进行检测,并将其应用在轧机设备的齿轮和转子的故障检测中,同时对实验数据及结果进行分析。
     最后,将整套理论方法应用到减速机的故障状态预测中:将所预测的时间序列运用Duffing振子来提取特征信号,并通过RBF神经网络进行推理决策,给出故障诊断结果,从而实现了对机械故障状态的预测分析。
At present, more and more industry and mine corporations are constructed, the social and economic benefit bright out by the detection and diagnosis of the key equipment are more considered gradually. The change from prevention maintenance to prescient maintenance will be inevitable, it conforms the trend of machine fault’s diagnosis.
     For time series, the phase reconstruction can recover some of the system’s characteristics. Basing on it, nonlinear model of the power system can be created in order to do some prediction. Relying on the state of machine system before the moment that have been slected, the movement state after the moment can be predicted in the bound of the max prediction.
     First, chaos’s complex characteristic and the method of identifying them are analysed. Depending on these analysis, a new method on the phase reconstruction of chaos is proposed: the appropriate delay time is determined using the mutual information function; the best embedding dimension is determined using CAO method.
     Second, the time series are calculated in an allowable bound using the Volterra progression, relying on the delay time and the embedding dimension through the method of phase reconstruction, so the prediction on the fault of equipment will be completed.
     Third, in order to solute the question on the weak fault signal of large machine, intermittent chaos of the Duffing oscillator is used to detect the weak fault signal buried in the strong noise surroundings. The method is applied to detect the fault of the rolling mill’s rotors and gears and analysing the experiment result.
     At last, all theories are applied to predict the fault of speed-down machine: the characteristic signal contained in the predicted time series is detected by Duffing oscillator and the dignosis result is given using RBF nerve network. The prediction and analysis to machine fault state are completed.
引文
1石博强,申焱华.机械故障诊断的分形方法--理论与实践.北京:冶金工业出版社,2002:170.179 288-302
    2张淑清.基于小波变化和混沌理论的机械故障诊断理论及应用研究.[燕山大学博士论文]2006:3-5 47-64
    3 Bennet J Etal.DART:An Expert System for Computer Fault Diagnosis.Proc.7th UCAI.198l:843-845
    4黄文虎,夏松波,刘瑞岩.设备故障诊断原理、技术及应用.北京:科学出版社.1996:16-20
    5韩敏.混沌时间序列预测理论与方法.北京:中国水利水电出版社,2007:10-12168-172
    6姜万录,张淑清,王益群.基于混沌和小波的故障信息诊断.北京:国防工业出版社,2005:22-28 33-60
    7姜万录,张淑清,王益群.混沌运动特征的数值实验分析.机械工程学报,2000,36(10):13-18
    8刘宗华.混沌动力学基础及其应用.北京:高等教育出版社,2006:71-80
    9李月,杨宝俊.混沌振子系统(L-Y)与检测.北京:科学出版社,2007:112-130
    10刘树勇,朱石坚,俞翔.确定相空间重构嵌入维数的研究.哈尔滨工程大学学报,2008.29(4):374-381
    11王军,石炎福,余华瑞.相空间重构中最优时滞的确定.四川大学学报(工程科学版),2001,33(2):47-51
    12黄国如,芮孝芳.流域降雨径流时间序列的混沌识别及其预测研究进展.水科学进展,2004,15(2):255-260
    13李春贵,裴留庆.一种识别混沌时间序列动力学异同性的方法.物理学报,2003,52(09):2114-2119
    14王沙,杨志安,任中京.动态光散射检测电机转速的互信息函数分析.光学学报,2005.31(5)758-763
    15肖方红,阎桂荣,韩宇航.混沌时序相空间重构参数确定的信息论方法.物理学报,2005,54(2):550-556
    16储军峰.中国股市的混沌性质研究.[北京大学硕士论文],2006:16-18
    17 Liangyue Cao.Practical method for determining the minimum embedding dimension of a scalar time series.Physica D.1997 110:43-50
    18许小可.海杂波的非线性分析与建模.[大连海事大学博士论文],2007:9.11
    19于万波.混沌的计算实验与分析.北京:科学出版社,2008:33-50
    20 Paulo S.R.Diniz.Adaptive Filtering:Algorithms and Practical Implementation Second Edition.Publishing House of Electronics Industry.2004:268-270
    21李崇晟,屈梁生.齿轮早期疲劳裂纹的混沌检测方法.机械工程学报,2005,41(8):195-198
    22谢涛,魏学业.混沌振子在为弱信号检测中的可靠性研究.仪器仪表学报,2008,29(6):1265-1269
    23 M J OGORZALEK.H DEDIEU.Chaotic Signal Processing via Unstable Cycle Extraction.Proceedings ICASSP IEEE International Conference on Acoustics.Speech and Signal Processing,Vo13,1994(31):521-524
    24 WENBO LIU.SHENGLIN YU.Application of chaos in measurement.Transactions of Nanj ing University of Aeronautics&Astronautics,2002,(12):1113-117
    25 L LIN.J P DARRYLL.Static Effects of Tooth Crack on a Spur Gear Pair.Proc.Of the Inter.Conf on Mechanical Transmission.Beijing.2001(10):683-686
    26韩逸飞,何琳.RBF神经网络在传感器故障诊断中的应用研究.舰船电子工程,2008,9(16):16-18
    27宋宏儒,丁常富,冯玉朝.RBF神经网络在凝汽器故障诊断中的应用.发电设备,2008,6:529-533
    28葛强,徐俩俩,仇宝云,谈磊,唐建军.基于RBF人工神经网络的电动机振动故障诊断.河海大学学报(自然科学版),2008,36(6):842-845
    29赵艳军,李永刚.基于RBF神经网络的发电机转子匝问短路故障诊断.电力科学与工程,2008,24(10):5-8
    30李勇,李春明,李秀娟.基于RBF神经网络的模拟电路故障诊断方法的研究.机械工程与自动化,2009,2(1):115-12
    31李力,蒋宇,李志雄.基于时序RBF神经网络的齿轮故障诊断方法.机械传动,2008,32(4)63-67
    32飞思科技产品研发中心.神经网络理论与MATLAB7实现.北京:电子工业出版社.2005:116-127
    33王光研,许宝杰.RBF神经网络在旋转机械故障诊断中的应用.机械设计与制造,2008,9(9):57-58
    34龙仙爱,杨顺,夏利民.基于Boosting RBF神经网络的滚动轴承故障诊断.计算机与数字工程,2006,34(9):15-18
    35周鹏,秦树人.基于切片谱RBF神经网络的旋转机械故障诊断.中国机械工程,2008,19(12):1488-1491
    36付强.一种基于RBF神经网络的转台分系统故障诊断方法.传感器与微系统,2007,26(6):26-32
    37岳晓娜,徐启,李建新.改进的RBF在水轮发电机组故障诊断中的应用.水电能源科学,2008,26(5):169-172
    38王璐,潘紫微,叶金杰.基于EKF训练的RBF神经网络及其故障诊断应用.振动、测试与诊断,2008,28(4):358-361
    39 Liu Zeng Rong.Advanced Series in Nonlinear Science Perturbation Criteria For Chaos.Shanghai:Shanghai Scientific and Technological Eduction Publishing House,1994:12-100
    40王海燕,卢山.非线性时间序列分析及其应用.北京:科学出版社,2006:70-87102-132
    41马军海.复杂非线性系统的重构技术.天津:天津大学出版社,2005:46-73117-121
    42冯明库,薛迎霄.混沌吸引子随机性的一种判别方法.计算机工程与应用,2007,43(15):56-58
    43姜万录.一种基于正交小波包分析的混沌识别方法.学燕山大学报,2004,28(1):7-13
    44任辉,顾家柳,贺尔铭,张志禹.含噪声的转子碰摩混沌信号分类识别.航空动力学报,2002,17(4):442-446
    45李香莲.汽车微弱振动信号的混沌振子识别.应用力学学报,2005,22(4):628-632
    46丁康,李巍华,朱小勇.齿轮及齿轮箱故障诊断应用技术.北京:机械工业出版社,2005:10-26
    47张鑫,陈伟斌,姚明海.Duffing振子检测微弱正弦信号的普遍性研究.计算机与数字工程,2005,33(12):71-73
    48陈敏,胡茑庆,温熙森.混沌振子在转子系统早期碰摩故障检测中的应用.国防科技大学学报,2001,23(1):36-39
    49李香莲.机械振动微弱慢频变信号的混沌振子检测.中国机械工程,2006,17(1):12-16
    50周华,基于混沌理论的滚动轴承故障诊断研究.诊断与检测,2006,3:144-146
    51朱志宇,姜长生,张冰,刘维亭.基于混沌理论的微弱信号检测方法.传感器技术,2005,24(5):65-68
    52姜万录,吴胜强.基于混沌振子的微弱信号检测方法及应用.机床与液压.2002.4:194-202
    53 Wu jun,Lu jian,Wang jiaquan.Application of chaos and fractal models to water quality time series prediction.Environmental Modelling and Software,2009,5(24):632-636
    54 Pontes Jr,Oliveira.VA..Balthazar.J.M.Note on the use of Melnikov’S chaos prediction criterion:Results of a friction-driven self-excited vibrating system.International Conference on Control of Oscillations and Chaos Proceedings,2000,1:171-172
    55 Lu ZhenBo.Cai ZhiMing.Jiang KeYu.Nonlinear adaptive prediction of chaotic time series based on sparse Volterra filter~Systems Engineering and Electronics,2007,9(29):1428-1431
    56 Kumar,Uijwal,Prakash,Arnit,Jain,VK.Characterization of chaos in air pollutants:A Volterra-Wiener-Korenberg series and numerical titration approach.Atmospheric Environment,2008,7(42):1537-1551
    57 Wijeratne.A.W,Yi,Fengqi,Wei,Jinjie.Bifurcation analysis in the diffusive Lotka-Volterra system:An application to market economy.Chaos Solitons Fractals,2009.2(40):902-911
    58 Dehghan,Mehdi,Shakourifar,Mohammad,Hamidi,Asgar.The solution of linear and nonlinear systems of Volterra functional equations using Adomian-Pade technique.Chaos,Solitons and Fractals,2009,5(39):2509-2521
    59 Aliyev,T.L,Stamps,A.T,Gatzke,E.P.Improved crude oil processing using second-order Volterra models and nonlinear model predictive contr01.Proceedings of the American Control Conference,2008:2215-2220
    60 Peng,Z.K,Lang,Z.Q.On the convergence of the Volterra-series representation of the Duffing’S oscillators subjected to harmonic excitations.Journal of Sound and Vibration,2007,2(305):322-332
    61吕伟才,徐绍铨.Kalman滤波在似单差方法中的应用.测绘通报,2006(3):14-17
    62冯永青,刘映尚,吴文传,张伯明.电力系统状态估计调试方法研究.南方电网技术,2007,1(1):46-50
    63姚桂艳,孙丽媛,程秀芳,薛全会.机械故障诊断技术的研究现状及发展趋势.河北理工学院学报,2005,27(3):35-37
    64罗邦劫.旋转机械故障诊断技术的研究现状及发展趋势.机电产品开发与创新,2008,21(3):85-86
    65简小刚,张艳伟,冯跃.工程机械故障诊断技术的研究现状与发展趋势.中国工程机械学报,2005,3(4):445-448
    66崔彦平,傅其凤,葛杏卫,刘玉秋.机械设备故障诊断发展历程及展望.河北工业科技,2004,21(4):59-62

© 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