基于频域信号的稀疏编码在机械故障诊断中的应用

摘要
图/表
参考文献(18)
相关文章 (15)

全文: PDF (2213 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要提出了一种使用稀疏编码对机械频谱信号自学习并识别故障的方法。首先分别对每类频谱信号进行字典学习得到每类信号的字典，然后依次计算测试样本在各个类别的字典上的稀疏重构系数,利用稀疏重构系数与对应类别的字典重构测试样本。最后将重构残差作为识别依据，对机器状态进行判断。通过将振动信号从时域转化到频域，将复杂的移不变稀疏编码问题转化为普通的稀疏编码，并且得益于高效的K-SVD字典学习算法，计算效率得到了大幅提高。本文所提方案直接使用原始频谱信号作为训练集，不仅省去了特征提取过程，而且保留了更丰富的信息。经实验验证，本方案较基于时域的移不变稀疏编码具有更高的计算效率、准确率和稳定性。相对于常规诊断算法，除了有准确率的优势外，不易受负载变化的影响，所需人工干预较少。

	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

关键词 ：故障诊断, 特征提取, 稀疏编码, K-SVD, 字典学习

Abstract：An automatic learning and recognition scheme using sparse coding based on spectra was proposed in this paper. Firstly, each dictionary per class was trained by dictionary learning algorithm. Later, the test sample was sparsely represented respectively using the dictionaries of each class to calculated corresponding sparse coefficients. Afterwards the dictionary with corresponding coefficients of the same class were applied to reconstruct the test sample. Finally, the reconstructed residual was employed as the criterion to determine machine state. Due to the conversion of vibration signals in time domain into frequency domain, the complex shift-invariant sparse coding problem was simplified as sparse coding problem, and with the help of efficient K-SVD algorithm, the whole efficiency was further significantly improved. The original spectra were directly used as training samples in proposed scheme, so that the complicated feature extraction was not needed, and more information was reserved. Verified by experiments, the proposed technique enhanced the efficiency and robustness compared to shift invariant sparse coding in time-domain. Unlike traditional algorithm, in addition to the advantage of accuracy, this proposed scheme needed less manual work and was less affected by load variation.

Key words： fault diagnosis feature extraction sparse coding K-SVD dictionary learning

收稿日期: 2014-06-11 出版日期: 2015-11-15

引用本文:

朱会杰 1,2，王新晴 1，芮挺 1，李艳峰 1，李立平3. 基于频域信号的稀疏编码在机械故障诊断中的应用[J]. 振动与冲击, 2015, 34(21): 59-64.
ZHU Hui-jie1，2， WANG Xin-qing1 RUI Ting1 LI Yan-feng1 LI Li-pin,3. The application of sparse coding based on spectra in machinery diagnosis. JOURNAL OF VIBRATION AND SHOCK, 2015, 34(21): 59-64.

链接本文:

http://jvs.sjtu.edu.cn/CN/ 或 http://jvs.sjtu.edu.cn/CN/Y2015/V34/I21/59

[1] Olshausen B A. Emergence of simple-cell receptive field properties by learning a sparse code for natural images[J]. Nature, 1996, 381(6583): 607-609.
[2] Candès E J, Wakin M B. An introduction to compressive sampling[J]. Signal Processing Magazine, IEEE, 2008, 25(2): 21-30.
[3] 宋长新,马克,秦川, 等. 结合稀疏编码和空间约束的红外图像聚类分割研究[J]. 物理学报, 2013, 62 (4): 40702-040702.
Song Chang-Xin, Ma Ke, Qin Chuan, et al. Infrared image segmentation based on clustering combined with sparse coding and spatial constraints[J]. Acta Physica Sinica, 2013, 62(4): 40702-040702.
[4] Wright J, Yang A Y, Ganesh A, et al. Robust face recognition via sparse representation[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 2009, 31(2): 210-227.
[5] Yang M, Zhang L, Yang J, et al. (2010). Metaface learning for sparse representation based face recognition[C]// Image Processing, IEEE International Conference on, IEEE, 2010. 1601-1604.
[6] 孙俊,王文渊,卓晴. 基于稀疏编码的提取人脸整体特征算法[J]. 清华大学学报: 自然科学版, 2002, 42 (3): 411-413.
SUN Jun, WANG Wen-yuan, ZHUO Qing. Sparse coding-based global face feature extraction algorithm[J]. Journal of Tsinghua University(Science and Technology), 2002, 42 (3): 411-413.
[7] 肖玲,李仁发,曾凡仔, 等. 基于自学习稀疏表示的动态手势识别方法[J]. 通信学报, 2013, 34 (6): 128-135.
XIAO Ling, LI Ren-fa, ZENG Fan-zai, et al. Gesture recognition approach based on learning sparse representation[J]. Journal on Communications, 2013, 34 (6): 128-135.
[8] Grosse R, Raina R, Kwong H, et al. Shift-invariance sparse coding for audio classification[C]// Ron Parr, Linda van der Gaag. Conference on Uncertainty in AI, Vancouver: AUAI Press, 2007.149-158.
[9] Liu H, Liu C, Huang Y. Adaptive feature extraction using sparse coding for machinery fault diagnosis[J]. Mechanical Systems and Signal Processing, 2011, 25(2): 558-574.
[10] Smith E C, Lewicki M S. Efficient auditory coding[J]. Nature, 2006, 439(7079): 978-982.
[11] 苗中华,周广兴,刘海宁, 等. 基于稀疏编码的振动信号特征提取算法与实验研究[J]. 振动与冲击, 2014, (15).
MIAO Zhong-hua, ZHOU Guang-xing, LIU Hai-ning, et al. Tests and feature extraction algorithm of vibration signals based on sparse coding[J]. Journal of vibration and shock, 2014, (15).
[12] Aharon M, Elad M, Bruckstein A. K-SVD: An algorithm for designing overcomplete dictionaries for sparse representation[J]. Signal Processing, IEEE Transactions on, 2006, 54(11): 4311-4322.
[13] Xu H, Chen G. An intelligent fault identification method of rolling bearings based on LSSVM optimized by improved PSO[J]. Mechanical Systems and Signal Processing, 2013, 35(1): 167-175.
[14] Bin G, Gao J, Li X, et al. Early fault diagnosis of rotating machinery based on wavelet packets—empirical mode decomposition feature extraction and neural network[J]. Mechanical Systems and Signal Processing, 2012, 27: 696-711.
[15] Randall R B, Antoni J. Rolling element bearing diagnostics—a tutorial[J]. Mechanical Systems and Signal Processing, 2011, 25(2): 485-520.
[16] Lei Y, He Z, Zi Y. A new approach to intelligent fault diagnosis of rotating machinery[J]. Expert Systems with Applications, 2008, 35(4): 1593-1600.
[17] Tropp J A, Gilbert A C. Signal recovery from random measurements via orthogonal matching pursuit[J]. Information Theory, IEEE Transactions on, 2007, 53(12): 4655-4666.
[18] Shen C, Wang D, Kong F, et al. Fault diagnosis of rotating machinery based on the statistical parameters of wavelet packet paving and a generic support vector regressive classifier[J]. Measurement, 2013, 46(4): 1551-1564.