High-Level Feature Extraction based on Correlogram for State Monitoring of Rotating Machinery with Vibration Signals

doi:10.23940/IJPE.19.01.P22.220229

Abstract

Abstract:

Vibration analysis is one of the most popular methods for state monitoring of rotating machines, and feature extraction is of much importance in the design of the monitoring system. In this paper, a new high-level feature extraction method based on correlograms for vibration signal analysis is proposed, and it includes two phases. Firstly, in the learning process, a codebook is created from training data using thek-means algorithm. Next, in the testing process, for a given data stream collected from a monitoring rotating machine, the correlogram in each cycle is obtained by comparing every data point with all codewords in the codebook at first; the entropy is then computed to form final high-level features to measure the state of the machine. A change decision can be made finally based on features extracted from null hypothesis testing. Based on an experimental setup used in our previous work, the proposed method is evaluated with application to the speed change monitoring of a rotating machine. Experimental results demonstrate the excellent performance and the priority of the method compared with ten typical features.

Key words: rotating machinery, vibration analysis, speed monitoring, feature extraction, correlogram

Shaohua Yang, Guoliang Lu, Aiqun Wang, and Peng Yan. High-Level Feature Extraction based on Correlogram for State Monitoring of Rotating Machinery with Vibration Signals [J]. Int J Performability Eng, 2019, 15(1): 220-229.

Add to citation manager EndNote|Reference Manager|ProCite|BibTeX|RefWorks

Figures/Tables 10

Figure 1

Figure 2

Figure 3

Figure 4

Table 1

Figure 5

Figure 6

Table 2

Figure 7

Figure 8

References 24

[1]	D. Goyal and S. B. Pabla , “The Vibration Monitoring Methods and Signal Processing Techniques for Structural Health Monitoring: A Review,” Archives of Computational Methods in Engineering, Vol. 23, No. 4, pp. 585-594, 2016 doi: 10.1007/s11831-015-9145-0
[2]	G. Lu, Y. Zhou, C. Lu, X. Li , “A Novel Framework of Change-Point Detection for Machine Monitoring,” Mechanical Systems & Signal Processing, Vol. 83, pp. 533-548, 2017 doi: 10.1016/j.ymssp.2016.06.030
[3]	F. Pozo, I. Arruga, L. E. Mujica, M. Ruiz, E. Podivilova , “Detection of Structural Changes through Principal Component Analysis and Multivariate Statistical Inference,” Structural Health Monitoring, Vol. 15, No. 2, pp. 127-142, 2016 doi: 10.1177/1475921715624504
[4]	Y. Ding, W. He, B. Chen, Y. Zi, I. W. Selesnick , “Detection of Faults in Rotating Machinery using Periodic Time-Frequency Sparsity,” Journal of Sound and Vibration, Vol. 382, pp. 357-378, 2016 doi: 10.1016/j.jsv.2016.07.004
[5]	M. Cerrada, R. V. Sánchez, D. Cabrera, G. Zurita, C. Li , “Multi-Stage Feature Selection by using Genetic Algorithms for Fault Diagnosis in Gearboxes based on Vibration Signal,” Sensors, Vol. 15, No. 9, pp. 23903-23926, 2015 doi: 10.3390/s150923903 pmid: 4610427
[6]	J. Dybała and R. Zimroz,“Rolling Bearing Diagnosing Method based on Empirical Mode Decomposition of Machine Vibration Signal,” Applied Acoustics,Vol. 77, No. 3, pp. 195-203, 2014 doi: 10.1016/j.apacoust.2013.09.001
[7]	G. Lu, J. Liu, P. Yan , “Graph-based Structural Change Detection for Rotating Machinery Monitoring,” Mechanical Systems and Signal Processing, Vol. 99, pp. 73-82, 2018 doi: 10.1016/j.ymssp.2017.06.003
[8]	A. Ghods and H. H. Lee, “Probabilistic Frequency-Domain Discrete Wavelet Transform for Better Detection of Bearing Faults in Induction Motors,” Neurocomputing, Vol. 188, pp. 206-216, 2016 doi: 10.1016/j.neucom.2015.06.100
[9]	Y. Yang, X. J. Dong, Z. K. Peng, W. M. Zhang, G. Meng , “Vibration Signal Analysis using Parameterized Time-Frequency Method for Features Extraction of Varying-Speed Rotary Machinery,” Journal of Sound and Vibration, Vol. 335, pp. 350-366, 2015 doi: 10.1016/j.jsv.2014.09.025
[10]	W. Li, S. Zhang, S. Rakheja , “Feature Denoising and Nearest-Farthest Distance Preserving Projection for Machine Fault Diagnosis,” IEEE Transactions on Industrial Informatics, Vol. 12, No. 1, pp. 393-404, 2016 doi: 10.1109/TII.2015.2475219
[11]	C. Wang, M. D. Prieto, L. Romeral, Z. Chen, F. Blaabjerg, X. Liu , “Detection of Partial Demagnetization Fault in PMSMs Operating under Nonstationary Conditions,” IEEE Transactions on Magnetics, Vol. 52, No. 7, pp. 1-4, 2016 doi: 10.1109/TMAG.2015.2511003
[12]	X. Zhang, Y. Liang, J. Zhou , “A Novel Bearing Fault Diagnosis Model Integrated Permutation Entropy, Ensemble Empirical Mode Decomposition and Optimized SVM,” Measurement, Vol. 69, pp. 164-179, 2015 doi: 10.1016/j.measurement.2015.03.017
[13]	G. He, K. Ding, H. Lin , “Fault Feature Extraction of Rolling Element Bearings using Sparse Representation,” Journal of Sound and Vibration, Vol. 366, pp. 514-527, 2016 doi: 10.1016/j.jsv.2015.12.020
[14]	W. He, Y. Zi, B. Chen, F. Wu, Z. He , “Automatic Fault Feature Extraction of Mechanical Anomaly on Induction Motor Bearing using Ensemble Super-Wavelet Transform,” Mechanical Systems and Signal Processing, Vol. 54, pp. 457-480, 2015 doi: 10.1016/j.ymssp.2014.09.007
[15]	N. Lu, Z. Xiao, O. P. Malik , “Feature Extraction using Adaptive Multiwavelets and Synthetic Detection Index for Rotor Fault Diagnosis of Rotating Machinery,” Mechanical Systems and Signal Processing, Vol. 52, pp. 393-415, 2015 doi: 10.1016/j.ymssp.2014.07.024
[16]	W. Li, Z. Zhu, F. Jiang, G. Zhou, G. Chen , “Fault Diagnosis of Rotating Machinery with a Novel Statistical Feature Extraction and Evaluation Method,” Mechanical Systems and Signal Processing, Vol. 50, pp. 414-426, 2015 doi: 10.1016/j.ymssp.2014.05.034
[17]	A. S. Rathore, M. Pathak, R. Jain, G. P. Jadaun . “Monitoring Quality of Biotherapeutic Products using Multivariate Data Analysis,” Aaps Journal, Vol. 18, No. 4, pp. 1-8, 2016 doi: 10.1208/s12248-016-9908-z pmid: 27044370
[18]	A. Nigam and R. C. Tripathi, “Trademark Image Retrieval using Weighted Combination of Sift and HSV Correlogram,” International Journal of Computer Applications in Technology, Vol. 54, No. 1, pp. 61-67, 2016 doi: 10.1504/IJCAT.2016.077797
[19]	K. Yildiz , “Dimensionality Reduction-based Feature Extraction and Classification on Fleece Fabric Images,” Signal, Image and Video Processing, Vol. 11, No. 2, pp. 317-323, 2017
[20]	H. H. Bafroui and A. Ohadi, “Application of Wavelet Energy and Shannon Entropy for Feature Extraction in Gearbox Fault Detection under Varying Speed Conditions,” Neurocomputing, Vol. 133, pp. 437-445, 2014 doi: 10.1016/j.neucom.2013.12.018
[21]	E. Mooi and M. Sarstedt, “Cluster Analysis,” A Concise Guide to Market Research, pp. 273-324, Springer, Berlin, Heidelberg, 2014
[22]	V. Shahsavari, L. Chouinard, J. Bastien , “Wavelet-based Analysis of Mode Shapes for Statistical Detection and Localization of Damage in Beams using Likelihood Ratio Test,” Engineering Structures, Vol. 132, pp. 494-507, 2017 doi: 10.1016/j.engstruct.2016.11.056
[23]	R. Lourenzutti and R. A. Krohling, “The Hellinger Distance in Multicriteria Decision Making: An Illustration to the TOPSIS and TODIM Methods,” Expert Systems with Applications, Vol. 41, No. 9, pp. 4414-4421, 2014
[24]	C. D. Fuh and Y. Mei, “Quickest Change Detection and Kullback-Leibler Divergence for Two-State Hidden Markov Models,” IEEE Transactions on Signal Processing, Vol. 63, No. 18, pp. 4866-4878, 2015 doi: 10.1109/ISIT.2015.7282433

$\Delta v\backslash v$	250	300	350
50	250→250+50	300→300+50	350→350+50
100	250→250+100	300→300+100	350→350+100
150	250→250+150	300→300+150	350→350+150
200	250→250+200	300→300+200	350→350+200
250	250→250+250	300→300+250	350→350+250

Features	Formulations
RMS	${{X}_{RMS}}=\sqrt{\frac{\sum\limits_{z=1}^{Z}{{{x}_{z}}^{2}}}{Z}}$
Crest factor	${{X}_{C}}=\frac{\left\| {{x}_{z}} \right\|}{{{X}_{RMS}}}$
Kurtosis	${{X}_{K}}=\frac{1}{Z}\sum\limits_{z=1}^{Z}{{{(\frac{{{x}_{z}}-\overline{x}}{{{X}_{SD}}})}^{4}}}$
Waveform	${{X}_{W}}=\frac{{{X}_{RMS}}}{\frac{1}{Z}\sum\limits_{z=1}^{Z}{\left\| {{x}_{z}} \right\|}}$
Skewness	${{X}_{SK}}=\frac{Z\sum\limits_{z=1}^{Z}{{{({{x}_{z}}-\overline{x})}^{3}}}}{(Z-1)(Z-2){{X}_{SD}}^{3}}$
Mean	$\overline{x}=\frac{1}{Z}\sum\limits_{z=1}^{Z}{{{x}_{z}}}$
SD	${{X}_{SD}}=\sqrt{\frac{1}{Z}\sum\limits_{z=1}^{Z}{{{({{x}_{z}}-\overline{x})}^{2}}}}$
MSE	$MSE=\frac{1}{Z}\sum\limits_{z=1}^{Z}{{{\varepsilon }_{z}}^{2}},{{\varepsilon }_{z}}=observe{{d}_{z}}-predicte{{d}_{z}}$
Variance	${{X}_{V}}=\frac{1}{Z}\sum\limits_{z=1}^{Z}{{{({{x}_{z}}-\overline{x})}^{2}}}$
MP	${{X}_{MP}}=\max ({{x}_{z}})$