基于改进局部线性嵌入算法的故障特征提取方法

Abstract
Figure/Table
References (16)
Related Citation (15)

Download: PDF (890 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract Focusing on the performance of local linear embedding (LLE) with respect of fault feature extraction which is influenced by the noise, embedding dimensionality and neighborhood size, it is improved form both the estimation of weight coefficient and the selection of neighborhood sizes and embedding dimensionality. The cross-correntropy is being substituted for the Euclidean distance to measure similarity of vectors. An estimation model of weight coefficient is created based on cross-correntropy. At the same time, it is simplified by the Lagrange method because of computation difficulties. The model of weight coefficient based on cross-correntropy will improve the performance of the local linear embedding and reduce the influence from noise in fault feature extraction. The Ncut criterion is employed to choosing the neighborhood sizes and embedding dimensionality. A model for choosing the parameters in a more automatic way is created. The improved LLE is employed in the fault feature extraction of rolling bearings. The experimental results for fault diagnosis of rolling ball bearings show that the proposed approach, compared with other approaches, is more effective to extract the fault features form vibration signals, and enhance the classification ability of failure pattern.

Received: 04 May 2014 Published: 15 August 2015

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Hu Feng
	Su Xun
	Liu Wei
	Wu Yuchuan
	Fan Liangzhi

Cite this article:

Hu Feng,Su Xun,Liu Wei, et al. Fault Feature Extraction Based on improved Locally Linear Embedding[J]. JOURNAL OF VIBRATION AND SHOCK, 2015, 34(15): 201-204.

URL:

http://jvs.sjtu.edu.cn/EN/ OR http://jvs.sjtu.edu.cn/EN/Y2015/V34/I15/201

[1]栗茂林，王孙安，梁霖. 利用非线性流形学习的轴承早期故障特征提取方法[J].西安交通大学学报，2010，44(5)：45-49.
Li Maolin, Wang Sunan, Liang Lin. Feature Extraction for Incipient Fault Diagnosis of Rolling Bearings Based on Nonlinear Manifold Learnging[J]. Journal of Xian Jiao Tong University, 2010，44(5)：45-49.
[2]张绍辉，李巍华.可变近邻参数的局部线性嵌入算法及其在轴承状态识别中的应用[J].机械工程学报，2013，49(1):81-87.
Zhang Shaohui, Li Weihua. Variable Nearest Neighbor Locally Linear Embedding and Applications in Bearing Condition Recognition[J]. Journal of Mechanical Engineering, 2013, 49(1): 81-87.
[3] 李锋，田大庆，王家序等.基于有监督增量式局部线性嵌入的故障辨识[J].振动与冲击,2013,32(23):82-88.
Li Feng, Tian Daqing, Wang Jiaxu, et al. Fault identification method based on supervised incremental locally linear embedding[J]. Journal of Vibration and Shock,，2013， 32(23)：82-88.
[4]John A. Lee, Michel Verleysen. Quality assessment of dimensionality reduction: Rank-based criteria[J]. Neurocomputing, 2009, 72：1431-1443.
[5]Deyu Meng, Yee Leung, Zongben Xu. A new quality assessment criterion for nonlinear dimensionality reduction[J]. Neurocomputing, 2011, 74：941-948.
[6]Roweis，SaulL. Nonlinear dimensionality reduction by locally linear embedding[J]. Science，2000，290(5500)：2323—2326.
[7]Kouropteva，Okun，PietikSinen. Selection of the optimal parameter value for the locally linear embedding algorithm[J]. In：Fisrt Internat. Conf. on Fuzzy Systems and Knowledge Discovery，2002.
[8]Genaro Daza-Santacoloma, German Castellanoes-Domiguez, Jose C. Principe. Locally Linear embedding based on correntropy measure for visualization and classification[J]. Neurocomputing, 2012, 80: 19-30.
[9]Genaro Daza-Santacoloma, German Castellanoes-Domiguez, Jose C. Principe. Functional Data Representation Using Correntropy Locally LINEAR Embedding[J]. IEEE International Workshop on Machine Learning for Signal Processing, Kittila, Finland, 2010: 7-12.
[10]阎庆，梁栋，张晶晶. 基于Fisher变换的植物叶片图像识别监督LLE算法[J]. 农业机械学报，2012，43(9)：179-183.
Yan Qing, Liang Dong, Zhang Jingjing. Recognition Method of Plant Leaves Based on Fisher Projection-supervised LLE Algorithm [J]. Transactions of the Chinese Society for Agricultural Machinery, 2012，43(9)：179-183.
[11] L. Chen, Local multidimensional scaling for nonlinear dimension reduction graph layout and proximity analysis, Ph.D. Thesis, University of Pennsylvania, 2006.
[12] John A. Lee, Michel Verleysen, Quality assessment of dimensionality reduction: Rank-based criteria, Neurocomputing. 2009,72 : 1431-1443.
[13] Jianbo Shi, Jitendra Malik. Normalized Cuts and Image Segmentation[J]. IEEE Transactions on pattern analysis and machine intelligence, 2000, 22(8): 888-905.
[14] Maria C.V. Nascimento, Andre C.P.L.F. de Carvalho. Spectral methods for graph clustering — A survey[J]. European Journal of Operational Research, 2011, 211: 221-231.
[15]Seyed Salim Tabatabaei, Mark Coates, Michael Rabbat. GANC: Greedy agglomerative normalized cut for graph clustering [J]. Pattern Recognition, 2012, 45: 831-843.
[16]J. M. Nichols，F. Bucholtz，B. Nousain. Automated，rapid classification of signals using locally linear embedding[J]. Expert Systems with Applications, 2011, 38：13472-13474.