基于半监督邻域自适应LLTSA算法的故障诊断

PDF(952 KB)

振动与冲击 ›› 2017, Vol. 36 ›› Issue (13) : 189-194.

论文

吕岩，房立清，张前图，齐子元

作者信息 +

Fault diagnosis based on semi-supervised neighborhood adaptive Linear local tangent space alignment

LV Yan FANG Li-qing ZHANG Qian-tu QI Zi-yuan

Author information +

文章历史 +

摘要

为了有效利用振动信号进行故障诊断，提出了一种基于半监督邻域自适应线性局部切空间排列（SSNA-LLTSA）算法的故障诊断方法。首先，从多域提取振动信号的混合特征，构建原始高维特征集。然后，利用半监督邻域自适应线性局部切空间排列算法对原始特征集进行维数约简，提取出辨识性较高的敏感特征子集。最后，将得到的低维特征输入SVM分类器进行识别，判断故障类型。液压泵故障诊断实验结果表明，该算法克服了LLTSA无监督和使用全局统一邻域参数的不足，可更有效地寻找数据的低维本质流形，提高了识别准确率，具有一定优势。

Abstract

In order to diagnose fault effectively by using vibration signals, a fault diagnosis method based on semi-supervised neighborhood adaptive linear local tangent space alignment was proposed. Firstly, the mixed feature of the vibration signal was extracted from multi domains, and the original high-dimensional feature could be constructed. Then, the algorithm of semi-supervised neighborhood adaptive linear local tangent space alignment was used to reduce the dimension of the original feature and to extract the sensitive feature subset. Finally, low-dimensional feature was put into SVM classifier for recognizing the fault types. The experiment results of hydraulic pump indicate that the algorithm overcame the drawbacks that LLTSA has no supervision and use the globally unified neighborhood parameter, and it was more efficient to find the low-dimensional manifold of the data for improving the recognition accuracy and has certain superiority.

导出引用

吕岩，房立清，张前图，齐子元. 基于半监督邻域自适应LLTSA算法的故障诊断[J]. 振动与冲击, 2017, 36(13): 189-194

LV Yan FANG Li-qing ZHANG Qian-tu QI Zi-yuan. Fault diagnosis based on semi-supervised neighborhood adaptive Linear local tangent space alignment[J]. Journal of Vibration and Shock, 2017, 36(13): 189-194

参考文献

[1] 张淑清, 孙国秀, 李亮, 等. 基于LMD近似熵和FCM聚类的机械故障诊断研究 [J]. 仪器仪表学报, 2013, 34(03): 714-720.
ZHANG Shu-Qing, SUN Guo-Xiu, LI Liang, etal. Study on mechanical fault diagnosis method based on LMD approximate entropy and fuzzy C-means clustering[J]. Chinese Journal of Scientific Instrument, 2013, 34(03): 714-720.
[2] 苏祖强，汤宝平，姚金宝，等.基于敏感特征选择与流形学习维数约简的故障诊断[J].振动与冲击，2014,33(3):70-75.
SU Zu-qiang, TANG Bao-ping, YAO Jin-bao, et al. Fault diagnosis method based on sensitive feature selection and manifold learning dimension reduction[J].Journal of Vibration and Shock,2014,33(3):70-75.
[3] Tenenbaum J B, Silva V, Langford J C. A global geometric framework for nonlinear dimensionality reduction [J]. Science, 2000, 290:2319-2323.
[4] Roweis S T, Saul L K. Nonlinear dimensionality reduction by locally linear embedding [J]. Science, 2000, 290:2323-2326.
[5] JIE G, WEI J, LING Z, et al. Locality preserving discriminant projections for face and palm print recognition [J]. Neurocomputing, 2010, 73: 2696-2707.
[6] 杨庆，陈桂明，何庆飞，等.局部切空间排列算法用于轴承早期故障诊断[J].振动、测试与诊断，2012,32(5): 831-835.
YANG Qing, CHEN Gui-ming, HE Qing-fei, et al. Inchoate fault diagnosis of rolling bearing based on local tangent space alignment algorithm[J]. Journal of Vibration, Measurement & Diagnosis, 2012, 32(5): 831-835.
[7] Zhang T H, Yang J, Zhao D L, et al. Linear local tangent space alignment and application to face recognition [J]. Neurocomputing, 2007, 70: 1547-1553.
[8] He X F, Yan S C, Hu Y X, et al. Face recognition using laplacianfaces [J]. IEEE Trans. Pattern Analysis and Machine Intelligence, 2005, 27 (3) :328-340.
[9] 李锋, 汤宝平, 陈法法. 基于线性局部切空间排列维数化简的故障诊断 [J]. 振动与冲击, 2012, 31(13): 36-40.
LI Feng, TANG Bao-ping, CHEN Fa-fa. Fault diagnosis model based on dimension reduction using linear local tangent space alignment[J]. Journal of Vibration and Shock, 2012, 31(13): 36-40.
[10] 苏祖强, 汤宝平, 邓蕾,等. 有监督LLTSA特征约简旋转机械故障诊断[J]. 仪器仪表学报, 2014, 35(8): 1766-1771.
SU Zu-qiang, TANG Bao-ping, DENG Lei, et al. Rotating machinery fault diagnosis with supervised-linear local tangent space alignment for dimension reduction[J]. Chinese Journal of Scientific Instrument, 2014, 35(8): 1766-1771.
[11] 刘志勇，袁媛. 基于测地距离的半监督增强[J].计算机工程与应用,2011,47(21):202-204.
LIU Zhi-yong, YUAN Yuan. Semi-supervised boosting based on geodesic distance[J]. Computer Engineering and Applications, 2011,47(21):202-204.
[12] Cao Q, Ying Y M, Li P. Similarity metric learning for face recognition[C]. In: Proceedings of the 2013 International Conference on Computer Vision. Sydney: IEEE, 2013.2408-2415.
[13] 李文博，王大轶，刘成瑞. 一类非线性系统的故障可诊断性量化评价方法[J].宇航学报，2015,36(4):455-462.
LI Wen-bo, WANG Da-yi, LIU Cheng-rui. An Approach to Fault Diagnosability Quantitative Evaluation for a Class of Nonlinear Systems [J]. Journal of Astronautics, 2015, 36(4):455-462.
[14] 董冀媛，穆志纯，欧阳定恒. 基于改进的局部切空间排列算法的多姿态人耳识别[J].北京科技大学学报,2010,32(12):1637-1642.
DONG Ji-yuan, MU Zhi-chun, OUYANG Ding-heng. Multi-pose ear recognition base on a local tangent space aliment algorithm [J]. Journal of University of Science and Technology Beijing, 2010,32 (12):1637-1642.
[15] 杨望灿，张培林，吴定海，等. 基于改进半监督局部保持投影算法的故障诊断[J]. 中南大学学报(自然科学版),2015，46(6):2059-2064.
YANG Wang-can, ZHANG Pei-lin, WU Ding-hai, et al. Fault diagnosis based on improved semi-supervised locality preserving projections [J]. Journal of Central South University (Science and Technology), 2015,46(6):2059-2064.
[16] 刘晗，张庆，孟理华，等. 基于Parzen窗估计的设备状态综合报警方法[J].振动与冲击，2013,32(3):110-114.
LIU Han, ZHANG Qing, MENG Li-hua, et al. Comprehensive alarm method for equipment conditions based on parzen window estimation [J]. Journal of Vibration and Shock, 2013,32 (3):110-114.
[17] 曾鸣，杨宇，郑近德，等. 基于LCD和KNNCH分类算法的齿轮故障诊断方法[J].中国机械工程，2014，25(15):2049-2054.
ZENG Ming, YANG Yu, ZHENG Jin-de, et al. Fault Diagnosis Approach for Gears Based on LCD and KNNCH Classification Algorithm [J]. China Mechanical Engineering, 2014，25(15):2049-2054.