用户名: 密码: 验证码:
基于铁谱的磨损模式识别方法研究
详细信息    本馆镜像全文|  推荐本文 |  |   获取CNKI官网全文
摘要
铁谱分析技术是以磨损磨粒识别为基础的诊断技术,它是机械设备磨损监测与故障诊断最为有效的方法之一。磨粒识别是铁谱分析的核心环节,识别的正确与否,直接关系机器磨损状态诊断的正确性。由于磨粒的多样性和复杂性,这种识别过程尚无成熟的理论方法来指导。磨粒识别日前主要由领域专家来完成,识别的准确性很大程度上取决于人的经验和领域知识水平。这使得铁谱技术难以得到更进一步的推广和应用。计算机图像处理技术以及人工智能特别是神经网络技术不断发展,为实现综合定量铁谱诊断及其智能化创造了有力的条件。将智能化技术应用到铁谱分析,提高铁谱分析的准确度和智能化程度,是摩擦学故障诊断领域中的热点问题。磨损磨粒的模式识别是实现铁谱分析数字化和智能化的最为核心的内容。本文提出了基于BP神经网络的磨粒识别模型的实现方法。主要内容包括:
     1.综合国内、外有关文献,对机械设备状态监测方法的现状进行评述;结合本课题研究的要求,阐述了本文的主要研究内容。
     2.分析论述了磨损的分类以及相应磨粒的生成机理和磨粒的形态特征;提出了用摩擦学系统分析的观点研究磨粒分析,磨粒的形态与磨损状态、磨损机理有密切关系,系统磨粒的数字特征包括摩擦学系统的状态特征、结构特征。论述了磨粒分析智能化的研究方法。
     3.论述了目前磨粒识别特征提取的进展,研究分析了当前几种磨粒特征提取方法的优缺点,这对进一步研究铁谱磨粒识别有一定的理论和实用意义。本文提出以傅立叶级数展开式为基础的磨粒特征提取方法。
     4.论述了前馈神经网络的基本理论,着重探讨了BP神经网络的基本原理、分类机理和学习方法;提出了适用于磨损磨粒识别的BP算法;并通过仿真实验检验了改进模型的可行性和有效性。
     5.将神经网络应用于磨粒识别,设计磨粒分类器,在网络学习中运用改进的BP模型,识别严重滑动磨损磨粒、切削磨粒、正常磨损磨粒和疲劳点蚀磨粒,随机选取50个样本对分类器进行训练。
     6.对神经网络隐含层的作用进行分析,在此基础上,借鉴有关文献提出的经验公式,提出了确定隐含层节点数的新方法。构造了一个自动磨粒识别模型。
     7.随机选取50个未参与训练的样本对分类器的推广能力进行考察;提出以推广能力来衡量分类器的优劣;提出了增强分类器推广能力的两种方法:(1)增加训练样本数量;<2)增加隐含层节点数。以仿真实验考察了第二种方法的可行
    
     晰 江 大 《 硕 士 《 仪 佑式
     性。
The ferrography is a wear diagnosis technology based on the analysis of wear particle. The practice has proved that the ferrography is the most effective method for wear condition monitoring and wear fault diagnosis. The recognition of the wear particle is the core step of the ferrography, the result of the recognition has direct relation to the correctness of the wear condition monitoring for the equipments. Because of the diversity and complicacy of the wear particle, the recognition procedure is carried out without guidance of mature theory. Currently, the recognition of the wear particle is carried out by the experts, the recognition process is very complicated, time-consumed and high cost. Those shortcomings limit the application of the ferrography. With the development of computer image processing and artificial intelligence, especially, with the development of neural network, it provides condition for the realization of automatic quantitative ferrographic analysis. The introduction of intelligence technologies will be helpful for the improvement of accuracy and automatization of ferrographic analysis. The recognition of wear particle is the core step to realize the automate ferrographic analysis. The thesis introduces a new method to ferrographic analysis based on the BP neural network. The main contents of the thesis are as follows:
    1. The monitoring technology for machines and equipments at home and abroad are evaluated synthetically. The significance aims of the project are presented.
    2. The thesis discusses and analyses the sorting of wear, the way the wear particle formed and the characteristics of the wear particles. The thesis proposes that the method of tribology system analysis should be used in the research on the wear particle, the characteristics of wear particle have relation to the condition and process of wear, the characteristics of wear particle include the condition characteristics and construction characteristics of the tribology system.
    3. The development of morphology characteristics extraction of wear particle is introduced. The advantages and disadvantages of some methods are pointed out. All those are available for further research of identification of ferrography wear particle in theory and practice.
    4. The principle of Artificial Neural Network (ANN) is discussed. The principle of BP neural network is emphasized. A new arithmetic adapt to the identification of wear particle is proposed based on the BP arithmetic, the possibility and validity of the improvement is examined by experiment.
    5. The BP neural network is applied to the recognition of wear particles, and a BP neural network sorting system expected to recognize severe wear particle, cutting wear particle, normal wear particle and fatigue wear particle is designed and trained.
    6. The function of the neural network's hidden layer is analyzed. A new way used to decide the neuron's number of the hidden layer is proposed based on the analysis and on the experiential way proposed by others. Construct a automate wear particle
    
    
    
    recognition model.
    7. The Generalization Capability of the sorting system is tested. The thesis suggested that the standard for weighing the sorting system should be the generalization capability. Two ways to improve the generalization capability are proposed: (1) increasing the number of the training swatch, (2) increasing the hidden layer's neuron number of the neural network, and the second one is examined by experiment.
引文
[1] 金锡志.机器磨损及其对策.北京:机械工业出版社.1996
    [2] 萧汉梁.铁谱技术及其在机械监测诊断中的应用.北京:人民交通出版社,1993
    [3] 屈梁生,孟建.机械故障诊断动技术与当代前沿科学(一).设备管理与维修,1995,(12):18-19.
    [4] Xie Y. B. On the Systems Engineering of Tribo-Systems. Proc. of IST93, Oct 19-23, 1993, (1):9-19
    [5] 郑庆林.摩擦学原理.北京:高等教育出版社,1994
    [6] 顾大强.蜗杆传动磨损状态监测方法研究:[博士学位论文].杭州:浙江大学,1996
    [7] 杨其明,曹松荫.测试磨损的新方法:铁谱技术.铁道知识,1993,(5):16-17
    [8] 崔屹.基于黑板的铁谱图像解释系统研究:[博士学位论文].北京:北京科技大学,1992
    [9] 金锡志,陈德金,铁谱技术的若干新发展.润滑与密封,1990,(6):4-9
    [10] 李令军,夏本春,夏林稳,斐立端,铁谱技术在采煤机状态监测与故障诊断中的应用与研究,煤矿机电,2000,(1):17-20
    [11] 巩志德.摩擦学及状态监测技术应用的发展.润滑与密封,1999,(1):70-71
    [12] Z. Peng, T.B. Kirk. Wear partical classification in a fuzzy grey system. Wear, 1999, 225-229:1238-1247
    [13] T.B. Kirk, D. Panzera, R.V. Anamalay, Z.L. Xu. Computer image analysis of wear debris for machine condition monitoring and fault diagnosis. Wear, 1995,181-183:712-722
    [14] Roylance B.J and Raadnui S. The Morphological Attributes of Wear Particle-Their Role in Identifying Wear Mechanisms. Wear, 1994,175:115-121
    [15] 吴振锋,左洪福,刘红星,杨忠.因子模糊化BP神经网络在磨粒识别中的应用.摩擦学学报,2000,20(2):143-146
    [16] 冼亮,陈大融,铁谱磨粒数字特征分析系统.清华大学学报(自科版),1992,32(5):60-64
    [17] 攀建春,杨明忠,一种基于Windows调色板和知识聚类的彩色磨粒图像分割方法,武汉汽车工业大学学报,1997,19(1):9-12
    
    
    [18] 李忠,曾昭翔,陈大融,基于BP神经网络的磨损微粒智能识别,北方交通大学学报,1998,22(1):86-91
    [19] G.W. Stachowiak, P. Podsiadlo. Surface characterization of wear particles. WEAR, 1999, 225-229:1171-1185
    [20] P. Podsiadlo, G.W. Stachowiak. Scale-invariant analysis of wear particle surface morphology Ⅰ: Theoretical backgroud, computer implementation and technique testing. WEAR, 2000,242:160-179
    [21] P. Podsiadlo, G.W. Stachowiak. Scale-invariant analysis of wear particle surface morphology Ⅱ: Fractal dimension. WEAR,2000,242:180-188
    [22] P. Podsiadlo, G.W. Stachowiak. Scale-invariant analysis of wear particle surface morphology Ⅲ: Pattern recognition. WEAR, 2000,242: 189-201
    [23] P. Podsiadlo, G.W. Stachowiak. 3-D imaging of surface topography of wear particles found in synovial joints. WEAR, 1999, 230:184-193
    [24] V. Hudnik and J. Vizintin. Key parameters for the reliable prediction of machine failure using wear particle analysis.TRIBOLOGY INTERNATIONAL, 1991, 24(2):95-98
    [25] M.S. Laghari, I.A. Albidewi, et al, Wear partical texture classification using artificial neural networks, Proc. 3rd Nordic Transputer Conf Denmark, 1993
    [26] 卜英勇,张怀亮,秦雅琴.铁谱磨粒形态特征提取的新进展与适用范围.中国有色金属学报.1998,8(3):547-550
    [27] T.B. Kirk, G.W. Stachowiak and A.W. Batchelor. Fractal parameters and computer image analysis applied to wear particles isolated by ferrography. Wear, 1991,1145:347-365
    [28] P. Podsiadlo, G. W. Stachowiak. Evaluation of boundary fractal methods for the characterization of wear particles. WEAR, 1998,217:24—34
    [29] Shirong. Ge; Guoan. Chen;Xiaoyun. Zhang. Fractal characterization of wear particle accumulation in the wear process. Wear, 2001,251(1-12):1227-1233
    [30] 方亮,高义民,周庆德.磨粒磨损中磨粒几何外形参数的分析方法.摩擦学学报,1995,15(4):348-354
    [31] Akihiko Umeda, Joichi Sugimura, Yuji Yamamoto. Characterization of wear particles and their relations with sliding conditions. Wear, 1998,216:220-228
    
    
    [32] B.J. Roylance, I.A. Albirdewi, M.S. Laghari. Computer-Aided Vision Engineering(CAVE)-Quantification of Wear Particle Morphology. Lubrication Engineering, 1994,50(2):111-116
    [33] 梁华,杨明忠,机械设备磨损故障的分类与铁谱诊断的探讨。润滑与密封,1995,(1):20-24
    [34] 梁华,杨明忠.机械设备磨损故障分析与智能化铁谱诊断.武汉工学院学报.1995,17(3):36-42
    [35] 程相君,王春宁,陈生潭.神经网络原理及其应用.北京:国防工业出版社.1995
    [36] 徐勇,荆涛译.神经网络模式识别及其实现.北京:电子工业出版社.1999
    [37] 边肇祺.张学工.模式识别.北京:清华大学出版社.2000
    [38] 戴葵.神经网络实现技术.长沙:国防科技大学出版社.1998
    [39] 胡守仁.神经网络应用技术.长沙:国防科技大学出版社.1993
    [40] 张智星,孙春在,(日)水谷英二著.张平安,高春华译.神经—模糊和软计算.西安:西安交通大学出版社.2000
    [41] 虞和济,陈水征,张省,周健男.基于神经网络的智能诊断.北京:冶金工业出版社.2000
    [42] 刘增良,刘有才.模糊逻辑与神经网络.北京:北京航空航天大学出版社.1996
    [43] 赵林明,胡浩云,魏德华,王树谦编.多层前向人工神经网络.郑州:黄河水利出版社.1999
    [44] 黄德双.神经网络模式识别系统理论.北京:电子工业出版社.1996
    [45] 陈明.大型BP网络学习算法.大连理工大学学报,1996,36(4):499-503
    [46] 梁曼君,石竹.提高BP神经网络学习速度以算法研究.合肥工业大学学报(自然科学版),1995,18(1):75-79
    [47] 杨建刚,戴德成,曹祖庆.改进BP网络在旋转机械故障诊断中的应用.振动工程学报,1995,8(4):342-350
    [48] 刘伟,费仁元.智能监控中改进BP神经网络模型的应用研究.北京工业大学学报,1995,21(4):61-67
    [49] 吴焱明,王纯贤,五治森.改进的BP算法及其应用研究.合肥工业大学学报(自然科学版),1998,21(4):17-21
    [50] 刘春林,何建敏.神经网络用于模式识别分类的改进算法.东南大学学报,1999,29(1):20-24
    [51] 吴江浩,胡志华,周芳德.改进BP神经网络在流型智能识别中的应用.西安交通大学学报,2000,34(1):22—25
    
    
    [52] 彭天好,范龙振,BP神经网络的一种稳健改进算法.计算机应用研究,1996,13(6):29-30
    [53] 高洪深,陶有德,BP神经网络模型的改进.系统工程理论与实践,1996,16(1):67-71
    [54] 肖宇光,刘惠光.基于改进的BP神经网络的FMS故障诊断系统.黑龙江自动化技术与应用,1996,15(2):12-14
    [55] 薛家祥,黄石生,BP神经网络优化训练技术的研究,华南理工大学学报(自然科学版),1998,26(7):21-24
    [56] 张明德,冯闻铮,董敏,刘福祯,乔长阁.改进的BP神经网络收敛性的实验研究.计算机工程,1998,24(5):27-29
    [57] 尚钢,钟珞,陈立耀.神经网络结构与训练参数选取.武汉工业大学学报,1997,19(2):108-110
    [58] 陆阳,韩江洪,高隽.二进神经网络隐元数目最小上界研究.模式识别与人工智能,2000,13(3):254-257
    [59] 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
    [60] 姚德宏.基于神经网络的汽车牌照提取研究.计算机应用,2001,21(6):40-41,44
    [61] 戚德虎,康继昌.BP神经网络的设计.计算机工程与设计,1998,19(2):48-50
    [62] Y.L.Su and J.S.Lin,S.K.Hsieh.The tribological failure diagnosis of spur gear by an expert system.Wear,1993,166:187-196
    [63] 朱新河,严新平,萧汉梁.铁谱分析专家系统开发的探讨.润滑与密封.1995(4):2-5
    [64] 李艳军,左洪福,吴振锋,基于磨粒分析方法的发动机磨损故障智能诊断技术.南京航空航天大学学报,2001,33(3):
    [65] 严志军,朱新河,贾珊中.基于广义贴近度的船用柴油机磨损模式识别方法.润滑与密封,2000(1):5-8
    [66] 汪家道,孔宪梅.磨粒轮廓特征变换研究.润滑与密封,1997,(3):8-10
    [67] 严新平,胡正仪.图象分析技术在磨粒识别中的应用.武汉交通科技大学学报,1996,20(4):367-371
    [68] 凌玲,陈大融,铁谱磨粒图像的计算机处理,机械设计与研究,1994,(1):41-43
    [69] 王延平,严新平等,小波分析在磨粒特征提取中的应用,武汉交通科技大学学报,1994,18:209-213
    
    
    [70] 潘汉玉,陈大融.铁谱图像分析技术的应用研究.摩擦学学报,1992,12(4):362-368
    [71] [美]罗纳德N.布拉斯维尔著,杨燕昌译.傅立叶变换及其应用.北京:人民出版社,1986
    [72] 游兆永,龚怀云,徐宗本著.非线性分析.西安:西安交通大学出版社,1991

© 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