近邻概率距离在旋转机械故障集分类中的应用方法

摘要
图/表
参考文献(16)
相关文章 (4)

全文: PDF (945 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要针对多种故障类型的特征属性相互交叉导致故障难以辨识的问题，提出一种考虑相邻点之间成为近邻点概率的新度量函数。将新提出的近邻概率距离（Nearby Probability Distance）应用于局部保持投影算法（Locality Preserving Projection，LPP）与K-近邻（K-Nearest Neighbor, KNN）分类器中，提出基于近邻概率距离的局部保持投影算法（Nearby Probability Distance Locality Preserving Projection，NPDLPP）与基于近邻概率距离的K-近邻（Nearby Probability Distance K-Nearest Neighbor，NPDKNN）分类器。首先通过时域、频域特征提取方法，将振动信号转化为高维特征数据集，然后通过NPDLPP将高维数据集降维到低维空间，最后将降维得到的低维敏感特征集输入到NPDKNN中进行模式识别。用一个双跨度转子系统的振动信号集合进行验证，证明了本文提出的降维算法效果明显，它能够达到各个故障类型更好分离。研究表明，本研究新提出的近邻概率距离较传统的欧式距离测度更能最小化类内散度，最大化类间分离度。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	李霁蒲
	赵荣珍

关键词 ：局部保持投影, 近邻概率距离, K近邻分类器, 距离度量

Abstract：Aiming at the problem of faults’ being difficult to identify due to their characteristics intersecting, a new measure function called the neighbor probability distance was proposed considering the probability for adjacent points to become neighbor ones. The neighbor probability distance was applied into the locality preserving projection (LPP) algorithm and K-nearest neighbor (KNN) classifier, then the neighbor probability distance-based locality preserving projection (NPDLPP) algorithm and the neighbor probability distance-based K-nearest neighbor (NPDKNN) classifier were proposed. Firstly, vibration signals were converted into high-dimensional data sets using feature-extracting methods in time domain and frequency domain. Then high-dimensional data sets were projected into a lower-dimensional space with NPDLPP. Finally, lower-dimensional sensitive feature sets obtained with dimension reduction were input into NPDKNN for pattern recognition. The vibration signal sets of a double-span rotor system were used to verify the proposed method. It was shown that the proposed method has an obvious effect to better separate various fault types; compared with the traditional Euclidean distance measure, the neighbor probability distance can minimize the divergence within a class and maximize the separation between classes.

Key words： locality preserving projection (LPP) neighbor probability distance (NPD) K-nearest neighbor (KNN) classifier distance measure

收稿日期: 2017-01-17 出版日期: 2018-05-28

引用本文:

李霁蒲，赵荣珍. 近邻概率距离在旋转机械故障集分类中的应用方法[J]. 振动与冲击, 2018, 37(11): 8-54.
LI Jipu, ZHAO Rongzhen. Application of neighbor probability distance in classification of rotating machinery fault sets. JOURNAL OF VIBRATION AND SHOCK, 2018, 37(11): 8-54.

链接本文:

http://jvs.sjtu.edu.cn/CN/ 或 http://jvs.sjtu.edu.cn/CN/Y2018/V37/I11/8

[1]Turk M,Pentland A. Eigenfaces for recognition[J]. Journal of Cognitive Neuroscience,1991,3(1):71-86.

[2]Belhumeur P N,Hespanha J P,Kriegman D J. Eigenfaces vs. Fisherfaces: recognition using class specific linear projection[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence,1997,19(7):711-720.

[3]Xiaofei H,Partha N.Locality Preserving Projections[C]//Proceedings of the 17th Annual Conference on Neural Information Processing Systems,Vancouver,2003:153-160.

[4]Sam T R,Lawrence K S. Nonlinear Dimensionality Reduction by Locally Linear Embedding[J].Science,2000,290(5500):2323-2326.

[5]Belkin M,Niyogi P. Laplacian eigenmaps for dimensionality reduction and data representation[J].Neural Computation, 2003,15(6):1373-1396.

[6]Tenenbaum J B,Silva V, Langford J C.A global geometric framework for nonlinear dimensionality reduction [J].Science,2000,290(5500):2319-2323.

[7]Hinton G,Roweis S.Stochastic neighbor embedding[J].Advances in Neural Information Processing Systems,2003,15(3):833-840.

[8]王雪冬，赵荣珍，邓林锋.基于KSLPP与RWKNN的旋转机械故障诊断[J].振动与冲击，2016，35(8)：219-223.
（Wang Xuedong，Zhao Rongzhen，Deng Linfeng.Rotating machinery fault diagnosis based on KSLPP and RWKNN[J].Journal of Vibration and Shock,2016,35(8):219-223).

[9]王微.融合全局和局部信息的度量学习方法研究[D].北京：中国科学技术大学，2014.
（Wang Wei.Globality and Locality Incorporation in Distance Metric Learning[D].Beijing:University of Science and Technology of China,2014）.

[10]杨望灿，张培林，张云强.基于邻域自适应局部保持投影的轴承故障诊断模型[J].振动与冲击，2014,33(1):39-44.
(Yang Wangcan，zhang Peilin，Zhang Yunqiang.Bearing fault diagnosis model based on neighborhood adaptive locality preserving projections[J].Journal of Vibration and Shock, 2014,33(1):39-44).

[11]杨庆，陈桂明，何庆飞，刘鲭洁.局部切空间排列算法用于轴承早期故障诊断[J].诊断、测试与诊断，2012，32(5)：831-835.
（Yang Qing，Chen Guiming，He Qingfei，Liu Qingjie.Vibration Suppression of Pipe System with Tuned Mass Damper[J].Journal of Vibration, Measurement & Diagnosis,2012,32(5):831-835).

[12]赵荣珍，李超，张优云.中值与小波消噪集成的转子振动信号滤波方法研究[J].振动与冲击，2005,24(4):74-77.
（Zhao Rongzhen，Li Zhao，Zhang Youyun.Filter design synthesizing median filtering and wavelet algorithm to de-nose vibration signal polluted by violent pulse noises[J].Journal of Vibration and Shock, 2005,24(4):74-77）.

[13]王雪冬，赵荣珍，邓林锋.基于PCA-KLFDA的小样本故障数据集降维方法[J].华中科技大学学报(自然科学版),2015,43(12)：12-16.
（Wang Xuedong，Zhao Rongzhen，Deng Linfeng.Small sample size fault feature data recognition based on the PCA – KLFDA[J].Journal of Huazhong University of Science and Technology(Natural Science Edition),2015,43(12):12-16）.

[14]马婧华.基于流形学习的旋转机械早期故障融合诊断方法研究[D].重庆：重庆大学，2015.
（Ma Jinghua .Research on Incipient Fault Fusion Diagnosis Methods for Rotating Machinery Based on Manifold Learning[D].Chongqing:Chongqing University,2015）.

[15]吴剑.基于特征选择的无监督入侵检测方法[J].华计算机工程与应用[J],2011,47(26)：79-82.
（Wu Jian.Unsupervised intrusion detection based on feature selection[J],2011,47(26)：79-82）.

[16] Chen F, Tang B, Chen R. A novel fault diagnosis model for gearbox based on wavelet support vector machine with immune genetic algorithm[J]. Measurement, 2013, 46(1): 220-232.