基于斜率关联度的模式识别方法及滚动轴承故障诊断应用

刘颖慧; 刘树林; 唐友福; 姜锐红

基于斜率关联度的模式识别方法及滚动轴承故障诊断应用

1.
上海大学机电工程与自动化学院, 上海 200072

基金项目:

国家自然科学基金项目(51175316)

教育部博士点基金项目(20103108110006)

上海市人才发展资金项目(047)资助

详细信息

作者简介:
刘颖慧(1984-)，博士研究生，研究方向为人工免疫和故障诊断，liuyinghui.-112@163.com;刘树林(联系人)，教授，博士，lsl346@126.com

刘颖慧(1984-)，博士研究生，研究方向为人工免疫和故障诊断，liuyinghui.-112@163.com;刘树林(联系人)，教授，博士，lsl346@126.com

计量
- 文章访问数: 106
- HTML全文浏览量: 11
- PDF下载量: 3
- 被引次数: 0
出版历程
- 收稿日期: 2011-08-07
- 刊出日期: 2015-06-10

A Method of Pattern Recognition with Slope Relational Degree and Its Application to Rolling Bearing Fault Diagnosis

1.
School of Mechatronics Engineering and Automation, Shanghai University, Shanghai 200072

摘要

摘要: 模式识别的首要问题是特征提取,在特征提取过程中,是否可以找到有效区分不同模式的特征,对模式识别的准确率有至关重要的影响。特征向量在高维可视化过程中,每一类都有自己固有的几何形态,在原有特征的基础上,可以进一步从斜率的角度反映每一类的形状,为此提出一种基于斜率关联度的模式识别方法,利用UCI机器学习数据库中的Iris数据集进行了模式识别效果分析,得到了较高的识别准确率。将基于斜率关联度的模式识别方法应用于滚动轴承故障诊断,同样得到了较理想的故障诊断效果。
- 斜率关联度 /
- 模式识别 /
- 滚动轴承 /
- 故障诊断
Abstract: Pattern recognition is key to feature extraction and the effective extraction of features of different patterns is vitally important for the accuracy of pattern recognition. In the high-dimension visualization process, each class of feature vectors has its inherent geometric shape. Therefore, we propose our pattern recognition method that uses the slope relational degree. We use the Iris data set in the UCI machine learning database to analyze the pattern recognition effectiveness, thus obtaining a highly accurate pattern recognition rate. Finally, we apply our pattern recognition method to the fault diagnosis of a rolling bearing and also obtain ideal fault diagnosis results.
- slope relational degree /
- pattern recognition /
- rolling bearing /
- fault diagnosis

HTML全文

参考文献(12)

[1]	Heng A,Zhang S,Tan A C C,et al.Rotating machinery prognos-tics State of the art,challenges and opportunities[J].MechanicalSystems and Signal Processing,2009,23(3):724～739
[2]	Andrew K S J,Daming L,Dragan B.A review on machinery diag-nostics and prognostics implementing condition-based maintenance[J].Mechanical Systems and Signal Processing,2006,20
[3]	流畅,周川,伍星等.基于广义形态滤波和相关系数的Hilbert-Huang变换方法[J].机械科学与技术,2011,30(1):71～75
[4]	鞠萍华,秦树人,赵玲.基于LMD的能量算子解调方法及其在故障特征信号提取中的应用[J].振动与冲击,2011,30(2)
[5]	章立军,杨德斌,徐金梧等.基于数学形态滤波的齿轮故障特征提取方法[J].机械工程学报,2007,43(2):72～75
[6]	沈路,周晓军,张文斌等.基于形态滤波与灰色关联度的滚动轴承故障诊断[J].机械工程学报,2009,28(11):17～20
[7]	孟辉,洪文学,宋家霖等.基于多元图形特征融合原理的降维方法研究[J].燕山大学学报,2008,32(5):445～450
[8]	Plaza A.Dimensionality reduction and classification of hyperspec-tral image data using sequences of extended morphological transfor-mations[J].IEEE Transactions on Geoscience and RemoteSensing,2005,43(3):466～479
[9]	李文,叶少珍.多维数据可视化技术及分类器的研究进展[J].福建电脑,2010,(5):38～39
[10]	Liu H,et al.Quality grade recognition of knitted yarns by supportvector machines[A].2010 International Conference on Com-puting,Control and Industrial Engineering[C],2010:49～51
[11]	Tomovic R,et al.Vibration response of rigid rotor in unloadedrolling element bearing[J].International Journal of Mechani-cal Sciences,2010,52(9):1176～1185
[12]	窦东阳,赵英凯.基于分类器组的轴承故障识别方法研究[J].振动与冲击,2010,29(10):221～224