用户名: 密码: 验证码:
基于模糊神经网络的旋转机械故障诊断方法研究
详细信息    本馆镜像全文|  推荐本文 |  |   获取CNKI官网全文
摘要
近年来国内外的机械故障诊断技术发展迅速,研究的手段和方法日新月异,其应用已遍及各个工业领域。由于旋转机械结构复杂,故障特征及原因普遍存在模糊性和复杂性,对其实施故障诊断比较困难,尽管人们对其开展了不少研究并取得了一些研究成果,但总的诊断水平还不是很高,这与其在生产中广泛应用的现状极不相符。因此,对旋转机械开展故障诊断研究具有十分重要的意义。本文研究工作就是在这个技术背景下展开的。
     研究了旋转机械振动信号的消噪方法和特征提取方法。针对旋转机械振动信号的非平稳性及特征难以提取的特点,通过对小波变换技术的进一步研究,提出旋转机械振动信号处理的小波基函数选择原则及小波包消噪的软阀值原则。利用小波包变换对旋转机械振动信号进行消噪处理和特征提取。并以“能量”为元素,构造旋转机械振动信号的特征向量,从而为旋转机械振动信号的故障特征提取以及后续的故障智能诊断提供了一种便捷的处理方法。旋转机械质量不平衡和油膜涡动故障的振动信号分析结果进一步验证了这种方法的可行性和有效性。
     研究了神经网络和模糊系统的故障诊断方法。模糊系统缺乏自学习能力,隶属度函数和模糊规则的选取带有一定的主观性且依赖于专家;神经网络所获得的输入/输出关系无法用容易被人接受的方式表示出来,存在非此即彼的绝对性,使诊断结果与实际情况不符。针对以上缺点,通过对神经网络和模糊系统的结合方式的研究,提出了一种基于模糊神经网络(ANFIS)的旋转机械故障诊断方法,并将其用于旋转机械的故障诊断。实验结果表明,与常用的神经网络和模糊系统诊断方法相比,该方法能够弥补模糊和神经网络单独应用时所存在的不足,具有更高的诊断准确率。在旋转机械故障诊断领域具有较好的应用前景。
     在深入分析旋转机械故障诊断过程的基础上,借助功能强大的MATLAB语言系统及其工具箱,在本论文中完成了旋转机械故障诊断原型软件的开发与设计,并用旋转机械常见故障状态的特征向量数据对其诊断结果的正确性进行了测试,效果良好,证明了此系统具有可用性。
In these years, machinery fault diagnosis technology has grown rapidly and research approaches and means are increasingly updated, all of which have been used in nearly every part of industrial field. However, for rotating machinery, it is very difficult to carry out fault diagnosis for its complicated structures and the ubiquitous fuzziness and complexity in character and causation of the fault. Although much research work has been done and some research fruits have been obtained, its diagnostic level is still low and does not match its wide application status. Therefore, the research on rotating machinery fault diagnosis is of great significance. The research work in this dissertation is started just in this technical background.
    Research on the feature extraction method of rotating machinery vibration signals. According to the time variation and feature extraction difficulty of rotating machinery vibration signals, the rule of choosing wavelet basis function and wavelet denoising soft-thresholding value is proposed after making further research on wavelet transform technique, using for denoising rotating machinery vibration signals The conception of "energy" is proposed, based on the theory that signals energy in all frequency can be affected by faults deeply, to construct feature vectors of rotating machinery vibration signals which can give a convenient disposal way to fault feature extraction and fault intellectual diagnosis. The vibration signals analytical result of rotating machinery mass imbalance and oil film turbulence fault verified its feasibility and validity.
    Researched on the fault diagnosis method of neural network and fuzzy system. Fuzzy system lacks self-study ability and its membership functions and fuzzy rule are chosen by experts subjectivity, and input/output relation obtained by neural network can not be expressed in acceptable way and exists the quality of absoluteness, all of which make diagnosis result not live up to the fact. So a rotating mechanical failure diagnosis method base on fuzzy neural network (ANFIS) is put forward and be applied to the fault diagnosis of rotating machinery. The experimental result indicates that this method, compared with the common one, can make up the shortcoming of the single-handed application of fuzzy classification or neural network. Moreover, it owns the better validity and popularity .It has a good application prospects in rotating machinery fault diagnosis.
    Based on the deep analysis of the diagnosis process for rotating machinery fault diagnosis system, the research has accomplished the design and developed system software of rotating machinery fault diagnosis prototype by the MATLAB language, which has strong function and toolboxes. The validity of the fault diagnosis system was well tested by eigenvectors, which are common appeared in rotating machinery fault status.
引文
[1] 裴峻峰,杨其俊.机械故障诊断技术.第1版.北京:石油大学出版社,1997.1~4
    [2] 黄文虎,夏松波,刘瑞岩.设备故障诊断原理技术及应用.第1版.北京:科学出版社,1996.1~5
    [3] 陈长征,白秉三.设备故障诊断技术研究发展.洛阳工业大学学报,2000,4(22):349~352
    [4] John Reason. Expert systems promise to cut critical machine downtime. Power. 1987, 131(3): 17~24
    [5] Doglas J. Smith. Intelligent Computer systems enhance power plant operations. Power Engingeering. 1989, 93(12): 21~26
    [6] Muszynska, A. Vibrational Diagnostics of Rotating Machinery Malfunctions. Vki, Vibration and Rotor Dynamics. C1992, p40
    [7] Joussellin, A. Ricard, B: Morel, J; et. al . PSAD: an integrated architecture for intelligent monitoring and diagnosis of EDF power plants. International Journal of Engineering Intelligent systems for Electrical Engineering and Com munications, 3 1 Mar 1995 CRL publishing Ltd p25~31
    [8] 刘峻华,黄树红,陆继东.汽轮机故障诊断技术的发展与展望.汽轮机技术,2000,42(1):1~6
    [9] 李平,刘长生.运用振动诊断技术进行机械设备的维修.木工机床,1998,(3):19~22
    [10] 张安华,张洪才.设备故障诊断中的信息融合技术.机械科学与技术,1997,4(16):612~616
    [11] 张建华,张俊华,侯国莲.神经网络在故障诊断中的应用.电力学报,1998,13(3):162~167
    [12] 张建文,许允之.模糊数学在故障诊断中的应用研究.煤矿设计,1998,(11):33~36
    [13] 王江萍.神经网络信息融合技术在故障诊断中的应用.石油机械,2001,29(8):27~30
    [14] 段志善,闻邦椿著.灰色理论在设备故障诊断中的应用.东工学报,1990,(8):231~238
    [15] 鞠万群,韩秋实.基于神经网络与规则库的故障诊断专家系统.北京机械工业学院学报,2001,16(1):6~10
    [16] 王琳.机械设备故障诊断与监测的常用方法及发展趋势.武汉工业大学学报,2000,6(22):62~64
    [17] 夏松波,张嘉钟,徐世昌,张礼勇.旋转机械故障诊断技术的现状与展望.振动与冲击,1997,16(2):1~5
    [18] 林克正,李殿璞.基于小波变换的去噪方法.哈尔滨工程大学学报,2000,21(4):21~23
    [19] 胡昌华,张军波,夏军,张伟.基于MATLAB的系统分析与设计—小波分析.第1版.西安:西安电子科技大学出版社,1999.20~23
    [20] R. P. Duhamel. Fast Algorithms for Discrete and Continuous Wavelet Transforms. IEEE Trans. On IT. 1992, 38(2): 569~586
    [21] 胡昌华,张军波.夏军,张伟.基于MATLAB的系统分析与设计—小波分析.第1版.西安:西安电子科技大学出版社,1999.6~12
    [22] 时文刚.往复机械的振动信号处理与故障诊断方法研究.工学博士学位论文.哈尔滨:哈尔滨工业大学,2003.38~39
    [23] 潭善文,秦树人,汤宝平.小波基时频特性及其在分析突变信号中的应用.重庆大学学报,2001,24(2):12~17
    [24] 汪新凡.小波基选择及其优化.株州工学院学报,2003,17(5):33~35
    [25] 曾凡永.谷尔兵,宋正勋.基于小波变换的图像压缩方法中小波基的选取问题探讨.长春光学精密机械学院学报,2000,23(2):73~74
    [26] 李爱萍,段利国.小波分析在信号降噪处理中的应用.太原理工大学学报,2001,32(1):69~71
    [27] 董小刚,秦喜文.信号消噪的小波处理方法及MATLAB实现.长春工业大学学报,2003.24(2):
    
    1~4
    [28] 刘刚,屈梁生.自适应阀值选择和小波消噪方法研究.信号处理,2002,18(6):509~512
    [29] D. L. Donoho. De-noising by soft-thresholding, IEEE Tans. On Information Theory, Vol. 41, No. 3, pp713-627, 1995. 5
    [30] Bin Liu, Yuanyuan wang, Weiqi Wang. Spectrogram Enhancement Algorithm: a Soft Thresholding based Approach, Uitrasound in Med. &.Biol., Vol. 25, No. 5, pp. 839~846, 1999
    [31] David L. Donoho: Wavelet Shrinkage and W. V. D..A 10-minute tour, ftp://playfair. Stanford. edu, 2001
    [32] L. K. Shark and C. Yu. Denoising by optimal fuzzy thresholding in wavelet domain, IEEE Electronics Letters, Vol. 36, No. 6, 16th, pp581-582, march2000
    [33] Pasti, L., Walczak, B., Massart, D. L., Reschiglian, P.. Optimization of signal denoising in discrete wavelet transform, Chemometrics and Intelligent Laboratory Systems, Vol. 48, IssueⅠ, June 14, pp21-34, 1999
    [34] Donoho D. L.. Johnstone I. M., Ideal spatial adaptation by wavelet shrink-age. Biometrika 81, pp425-455, 1992
    [35] 刘树林,张嘉钟,徐敏强.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(5):1~3
    [36] 许东,吴铮.基于MATLAB6.X的系统分析与设计—神经网络.第2版.西安:西安电子科技大学出版社,2002.1~2
    [37] 李占锋,韩芳芳,郑德忠.基于BP神经网络的电机转子故障诊断的研究.河北科技大学学报,2001,22(3):23~26
    [38] 钟秉林.黄仁著.机械故障诊断学.第1版.北京:机械工业出版社,1997:7~8
    [39] 张国良,曾静,柯熙政,邓方林.模糊控制及其MATLAB应用.第1版.西安:西安交通大学出版社,2002.61~62
    [40] 陈继光.基于自适应模糊网络系统的径流序列预测.山东工业大学学报,2002,32(1):13~15
    [41] 吕锋,谢妍,石敏等.基于ANFIS的模糊神经推理机在故障诊断中应用.水泥工程,2002,(2):39~41
    [42] 张韧.王继光,蒋国荣.基于小波分解和ANFIS模型的赤道东太平洋海温集成预测.热带海洋学报.2002,21(3):77~79
    [43] 张智星,孙春在,水谷英二.神经—模糊和软计算 张平安,高春.第1版.西安:西安交通大学出版社,2000.238~239
    [44] 邵栋,周志华,陈兆乾.模糊神经网络研究.计算机应用研究,1999,7(1):1~3
    [45] 谢维信,钱纭涛.模糊神经网络研究.深圳大学学报,1999,16(2~3):22~28
    [46] 罗远秋.朱威同,刘洪松.模糊神经网络的研究现状及发展前景.山东电子.1999,(2):25~28
    [47] 张浩炯,余岳峰,王强.应用自适应神经模糊推理系统进行建模与仿真.计算机仿真,2001,19(4):47~49
    [48] 周佩玲,邢根柳.股市价格趋势预测研究.计算机工程,2002,28(1):136~138

© 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