基于图像形状特征和LLTSA的故障诊断方法

张前图1,2,房立,2

振动与冲击 ›› 2016, Vol. 35 ›› Issue (9) : 172-177.

PDF(1805 KB)
PDF(1805 KB)
振动与冲击 ›› 2016, Vol. 35 ›› Issue (9) : 172-177.
论文

 基于图像形状特征和LLTSA的故障诊断方法

  • 张前图1,2,房立,2
作者信息 +

Fault diagnosis method based on image shape feature and LLTSA

  • ZHANG Qian-tu1,2,FANG Li-qin,2
Author information +
文章历史 +

摘要

针对滚动轴承故障诊断问题,提出了一种基于图像形状特征和线性局部切空间排列(LLTSA)的故障诊断方法。首先采用SDP(Symmetrized Dot Pattern)方法对时域信号进行变换,得到极坐标空间下的雪花图像,在分析图像特点的基础上,从图像处理的角度初步提取出图像的形状特征;然后利用LLTSA对初步提取的特征进行维数约简以提取低维特征;最后采用支持向量机(SVM)对低维特征进行分类评估。滚动轴承的故障诊断实验表明图像形状特征能够表征轴承的状态,经LLTSA约简后特征数据的复杂度得到降低,且具有更好的聚类效果,而SVM对轴承4种状态的识别率也达到了100%,验证了该方法的有效性。

Abstract

Aiming at the fault diagnosis problem of rolling bearing, a fault diagnosis method based on image shape feature and liner local tangent space alignment (LLTSA) was proposed. Firstly, the time waveform was transformed to snowflake image in polar coordinate space by symmetrized dot pattern (SDP) method, and image shape feature was initially extracted on the basis of analyzing the characteristic of the image. Secondly, the LLTSA was introduced to compress the initial high-dimension feature into the low-dimension which has better discrimination. Finally, the support vector machine (SVM) was employed to classify and evaluate the low-dimension feature. The experiment results of rolling bearing fault diagnosis shown that the image shape feature can represent the bearing state, and the LLTSA decreases the complexity of the feature data and enhance its clustering effect. Furthermore, a relatively high identification rate of four bearing states, namely, 100% was obtained by SVM, validated the effectiveness of the proposed method.

关键词

SDP / 形状特征 / 线性局部切空间排列 / 支持向量机 / 故障诊断

Key words

symmetrized dot pattern / shape feature / liner local tangent space alignment / support vector machine / fault diagnosis

引用本文

导出引用
张前图1,2,房立,2.  基于图像形状特征和LLTSA的故障诊断方法[J]. 振动与冲击, 2016, 35(9): 172-177
ZHANG Qian-tu1,2,FANG Li-qin,2. Fault diagnosis method based on image shape feature and LLTSA[J]. Journal of Vibration and Shock, 2016, 35(9): 172-177

参考文献

[1] Xu Li, A’nan Zheng, Xunan Zhang, etal. Rolling element bearing fault detection using support vector machine with improved ant colony optimization[J]. Measurement, 2013, 46: 2726-2734.
[2] 唐贵基, 邓飞跃, 何玉灵, 等. 基于时间-小波能谱熵的滚动轴承故障诊断研究[J]. 振动与冲击, 2014, 33(7): 68-72,91.
TANG Gui-ji, DENG Fei-yue, HE Yu-ling, etal. Rolling element bearing fault diagnosis based on time-wavelat energy spectrum entropy[J]. Journal of Vibration and Shock, 2014, 33(7): 68-72,91.
[3] 程利军, 张英堂, 李志宁, 等. 基于时频分析及阶比跟踪的曲轴轴承故障诊断研究[J]. 振动与冲击, 2012, 31(19): 73-78.
CHENG Li-jun, ZHANG Ying-tang, LI Zhi-ning, etal. Fault diagnosis of an engine's main bearing based on time-frequency analysis and order tracking[J]. Journal of Vibration and Shock, 2012, 31(19): 73-78.
[4] 窦唯, 刘占生. 旋转机械故障诊断的图形识别方法研究[J]. 振动与冲击, 2012, 31(17): 171-175.
DOU Wei, LIU Zhan-sheng. A fault diagnosis method based on graphic recognition for rotating machine[J]. Journal of Vibration and Shock, 2012, 31(17): 171-175.
[5] 张立国, 杨瑾, 李晶, 等. 基于小波包和数学形态学结合的图像特征提取方法[J]. 仪器仪表学报, 2010, 31(10): 2285-2290.
ZHANG Liguo, YANG Jin, LI Jing, etal. Image characteristic extraction method based on wavelat packet and mathematicalm orphology[J]. Chinese Journal of Scientific Instrument, 2010, 31(10): 2285-2290.
[6] Shibata K, Takahashi A, Shirai T. Fault diagnosis of rotating machinery through visualization of sound signals[J]. Mechanical Systems and Signal Processing, 2000, 14(2): 229-241.
[7] Wu Jian da, Chuang Chao qin. Fault diagnosis of internal combustion engines using visual dot patterns of acoustic and vibration signals[J]. NDT Int., 2005, 38(8): 605-614.
[8] Delvecchio S, D'Elia G, Mucchi E, etal. Advanced signal processing tools for the vibratory surveillance of assembly faults in diesel engine cold tests[J]. ASME Journal of Vibration and Acoustics, 2010, 132: 1-10.
[9] Kouropteva O, Okun O, Pietikainen M. Supervised locally linear embedding algorithm for pattern recognition[J]. Pattern Recognition and Image Analysis, 2003, 2652(9): 386-394.
[10] He X F, Yan S C, Hu Y X, etal. Face recognition using laplacianfaces[J]. IEEE Trans.Pattern Analysis and Machine Intelligence, 2005, 27(3): 328-340.
[11] Zhang T H, Yang J, Zhao D L, etal. Linear local tangent space alignment and application to face recognition [J]. Neurocomputing, 2007, 70: 1547-1553.
[12] 杨成, 冯焘, 王中方, 等. 基于SDP法诊断发动机的异响[J]. 声学技术, 2010, 29(5): 523-527.
YANG Cheng, FENG Tao, WANG Fang-zhong, etal. Abnormal noise diagnosis of motorcycle engines based on Symmetrized Dot Pattern method[J]. Technical Acoustics, 2010, 29(5): 523-527.
[13] 任玲辉, 刘凯, 张海燕. 基于图像处理技术的机械故障诊断研究进展[J]. 机械设计与研究, 2011, 27(05): 21-24.
REN Ling-hui, LIU Kai, ZHANG Hai-yan. Progress on mechanical fault diagnosis based on image processing[J]. Machine Design and Research, 2011, 27(05): 21-24.
[14] 秦襄培, 郑贤中. Matlab数字图像处理宝典[M]. 北京:电子工业出版社. 2011.
[15] 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.
[16] 向丹, 葛爽. 一种基于小波包样本熵和流行学习的故障特征提取模型[J]. 振动与冲击, 2014, 33(11): 1-5.
 XIANG Dan, GE Shuang. A model of fault feature extraction based on wavelet packet sample entropy and manifold learning[J]. Journal of Vibration and Shock, 2014, 33(11): 1-5.

PDF(1805 KB)

Accesses

Citation

Detail

段落导航
相关文章

/