Wavelet time–frequency analysis has been widely used for machinery fault diagnosis. Mechanical vibration signals can be converted to time–frequency images using wavelet transform, so machinery fault diagnosis can be transformed to the problem of image classification. Label consistent K-SVD algorithm has been proven to be effective in image classification, which incorporates a label consistent term namely discriminative sparse code error into the objective function. Therefore, in this paper, a novel bearing fault diagnosis method based on wavelet time–frequency image and label consistent K-SVD is proposed. Firstly, continuous wavelet transform is utilized to generate wavelet time–frequency images that can fully reflect bearing fault characteristics. Then texture feature extraction based on gray level co-occurrence matrix is implemented on the wavelet time–frequency images. Finally, label consistent K-SVD is conducted for classification of the time–frequency images, and thus bearing fault diagnosis is realized. The experiment results show that the texture features based on gray level co-occurrence matrix of wavelet time–frequency images can effectively extract the fault characteristics of rolling bearings, and label consistent K-SVD performs better than other classification methods based on dictionary learning under the same parameters.
FengZPLiangMChuFL. Recent advances in time-frequency analysis methods for machinery fault diagnosis: a review with application examples. Mech Syst Signal Process2013; 38: 165–205.
2.
Cocconcelli M, Zimroz R, Rubini R, et al. STFT based approach for ball bearing fault detection in a varying speed motor. In: Proceedings of the Second International Conference “Condition Monitoring of Machinery in Non-Stationnary Operations”, CMMNO, Springer, 2012, pp.41–50.
3.
ZiajaAAntoniadouIBarszczTet al.Fault detection in rolling element bearings using wavelet-based variance analysis and novelty detection. J Vib Control2016; 22: 396–411.
4.
BaydarNBallA. A comparative study of acoustic and vibration signals in detection of gear failures using Wigner-Ville distribution. Mech Syst Signal Process2001; 15: 1091–1107.
5.
LiangBIwnickiSDZhaoY. Application of power spectrum, cepstrum, higher order spectrum and neural network analyses for induction motor fault diagnosis. Mech Syst Signal Process2013; 39: 342–360.
6.
OsmanSWangW. A normalized Hilbert-Huang transform technique for bearing fault detection. J Vib Control2016; 22: 2771–2787.
7.
KankarPKSharmaSCHarshaSP. Rolling element bearing fault diagnosis using autocorrelation and continuous wavelet transform. J Vib Control2011; 17: 2081–2094.
8.
ZhaoLYWangLYanRQ. Rolling bearing fault diagnosis based on wavelet packet decomposition and multi-scale permutation entropy. Entropy-Switz2015; 17: 6447–6461.
9.
GanMWangCZhuCA. Construction of hierarchical diagnosis network based on deep learning and its application in the fault pattern recognition of rolling element bearings. Mech Syst Signal Process201672–7392–104.
10.
WangWGLiuZS. Classification of time-frequency images based on locality-constrained linear coding optimization model for rotating machinery fault diagnosis. P I Mech Eng C-J Mec2015; 229: 3350–3360.
11.
ZhaoMHTangBPTanQ. Fault diagnosis of rolling element bearing based on S transform and gray level co-occurrence matrix. Measur Sci Technol2015; 26. .
12.
HuaLQiangYJGuJPet al.Mechanical fault diagnosis using color image recognition of vibration spectrogram based on quaternion invariable moment. Math Probl Eng2015. .
13.
LuCWangYRagulskisMet al.Fault diagnosis for rotating machinery: a method based on image processing. Plos One2016; 11: e0164111.
14.
KhanSAKimJM. Rotational speed invariant fault diagnosis in bearings using vibration signal imaging and local binary patterns. J Acoust Soc Am2016; 139: El100–El104.
15.
WangKC. the feature extraction based on texture image information for emotion sensing in speech. Sensors-Basel2014; 14: 16692–16714.
16.
RamamoorthySKirubakaranRSubramanianRS. Texture feature extraction Using MGRLBP method for medical image classification. Adv Intell Syst2015; 324: 747–753.
17.
HaralickRMShanmugamKDinsteinI. Textural features for image classification. IEEE Trans Syst Man Cybernet1973; SMC-3: 610–621.
18.
Ojala T, Pietikainen M and Harwood D. Performance evaluation of texture measures with classification based on Kullback discrimination of distributions. In: IAPR international conference on pattern recognition, Conference A: computer vision & image processing, vol.1, Jerusalem, Israel, 9–13 October 1994, pp.582–585. IEEE.
19.
LoweDG. Distinctive image features from scale-invariant keypoints. Int J Comput Vision2004; 60: 91–110.
20.
Eleyan A and Demirel H. Co-Occurrence based statistical approach for face recognition. In: 2009 24th international symposium on computer and information sciences, Guzelyurt, Cyprus, 14–16 September 2009, pp.609–613. IEEE.
21.
EleyanADemirelH. Co-occurrence matrix and its statistical features as a new approach for face recognition. Turk J Electr Eng Co2011; 19: 97–107.
22.
WrightJYangAYGaneshAet al.Robust face recognition via sparse representation. IEEE T Pattern Anal2009; 31: 210–227.
23.
QiaoLSChenSCTanXY. Sparsity preserving projections with applications to face recognition. Pattern Recogn2010; 43: 331–341.
24.
Yang M, Zhang L, Yang J, et al. Robust sparse coding for face recognition. In: CVPRIEEE, Milan, Italy, 20–25 June 2011, 625–632.
25.
Liu W, Song C and Wang Y. Efficient discriminative K-SVD for facial expression recognition. In: Proceedings of 2013 Chinese intelligent automation conference, Springer, Yangzhou, China, 23–25 August 2013, pp.11–19.
26.
ZhengCXZhangFHouHRet al.Active discriminative dictionary learning for weather recognition. Math Probl Eng2016. .
27.
XieWJiaoLCZhaoJ. PolSAR image classification via D-KSVD and NSCT-domain features extraction. IEEE Geosci Remote S2016; 13: 227–231.
28.
FangLYLiSTKangXDet al.Spectral-spatial classification of hyperspectral images with a superpixel-based discriminative sparse model. IEEE T Geosci Remote2015; 53: 4186–4201.
29.
LiQXuDAnL. Discriminative reference-based scene image categorization. IEICE T Inf Syst2014; E97d: 2823–2826.
30.
DaiDXYangW. Satellite image classification via two-layer sparse coding with biased image representation. IEEE Geosci Remote S2011; 8: 173–176.
31.
AharonMEladMBrucksteinA. K-SVD: an algorithm for designing overcomplete dictionaries for sparse representation. IEEE T Signal Proces2006; 54: 4311–4322.
32.
EnganKAaseSOHusoyJH. Multi-frame compression: theory and design. Signal Process2000; 80: 2121–2140.
33.
Grosse R, Raina R, Kwong H, et al. Shift-invariant sparse coding for audio classification. In: Proceedings of the twenty-third conference on uncertainty in AI, Vancouver, BC, 19–22 July 2007, p.8. Canada: AUAI Press.
34.
EladMAharonM. Image denoising via sparse and redundant representations over learned dictionaries. IEEE T Image Process2006; 15: 3736–3745.
35.
BrytOEladM. Compression of facial images using the K-SVD algorithm. J Vis Commun Image R2008; 19: 270–282.
36.
ZhuHJWangXQZhaoYet al.Sparse representation based on adaptive multiscale features for robust machinery fault diagnosis. P I Mech Eng C-J Mec2015; 229: 2303–2313.
37.
Pham DS and Venkatesh S. Joint learning and dictionary construction for pattern recognition. In: Proc CVPR IEEE, 23–28 June 2008, pp.517–524. IEEE.
38.
Zhang QA and Li BX. Discriminative K-SVD for dictionary learning in face recognition. In: Proc CVPR IEEE, 13–18 June 2010, pp.2691–2698. IEEE.
39.
JiangZLLinZDavisLS. Label consistent K-SVD: Learning a discriminative dictionary for recognition. IEEE T Pattern Anal2013; 35: 2651–2664.
40.
JiangWMZhangZLiFZet al.Joint label consistent dictionary learning and adaptive label prediction for semisupervised machine fault classification. IEEE T Ind Inform2016; 12: 248–256.
41.
Kalaji I, Balasundaram K and Umapathy K. Discriminative sparse coding of ECG during ventricular arrhythmias using LC-K-SVD approach. In: The Proceedings of the Twenty-Third Conference on Uncertainty in AI, Milan, Italy, 25–29 August 2015, pp.5211–5214.
42.
TroppJAGilbertAC. Signal recovery from random measurements via orthogonal matching pursuit. IEEE T Inform Theory2007; 53: 4655–4666.
