Abstract
Machinery condition monitoring is a crucial application to enable condition-based predictive maintenance, realizing smart manufacturing in the context of the Industry 4.0 revolution. Machine learning that is built upon data correlation has recently become mainstream for machinery fault diagnosis. To boost the fault diagnosis performance of the machine learning methods, extracting high-quality fault-related features from raw time-series response signals is the key. In this research, we propose a signal processing-based feature extraction method, the so-called recurrence plot (RP), to evaluate the hidden dynamic characteristics of the vibration signals collected from the machinery system that is subject to fault. To further examine the properties of RP, the recurrence quantification analysis (RQA) is employed to quantitatively measure the patterns in the RP. The main strength of the proposed methodology lies in its excellent capability in handling the nonstationary signals with strong system nonlinearity and ambient noise, thereby yielding high-quality features with a high degree of separation in terms of the fault condition. A novel quantitative metric based on the silhouette is established to thoroughly assess the feature quality, providing systematic guidance for machinery condition monitoring. Comprehensive case studies using publicly accessible gear and bearing fault datasets are carried out to validate the proposed methodology. The enhanced performance of the proposed methodology also is highlighted by comparing it with other benchmark methods.
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00170-022-10392-z/MediaObjects/170_2022_10392_Fig1_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00170-022-10392-z/MediaObjects/170_2022_10392_Fig2_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00170-022-10392-z/MediaObjects/170_2022_10392_Fig3_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00170-022-10392-z/MediaObjects/170_2022_10392_Fig4_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00170-022-10392-z/MediaObjects/170_2022_10392_Fig5_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00170-022-10392-z/MediaObjects/170_2022_10392_Fig6_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00170-022-10392-z/MediaObjects/170_2022_10392_Fig7_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00170-022-10392-z/MediaObjects/170_2022_10392_Fig8_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00170-022-10392-z/MediaObjects/170_2022_10392_Fig9_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00170-022-10392-z/MediaObjects/170_2022_10392_Fig10_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00170-022-10392-z/MediaObjects/170_2022_10392_Fig11_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00170-022-10392-z/MediaObjects/170_2022_10392_Fig12_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00170-022-10392-z/MediaObjects/170_2022_10392_Fig13_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00170-022-10392-z/MediaObjects/170_2022_10392_Fig14_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00170-022-10392-z/MediaObjects/170_2022_10392_Fig15_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00170-022-10392-z/MediaObjects/170_2022_10392_Fig16_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00170-022-10392-z/MediaObjects/170_2022_10392_Fig17_HTML.png)
Similar content being viewed by others
Data availability
Not applicable.
Code availability
Not applicable.
References
Jauregui Correa JCA, Lozano Guzman AA (2020) Condition monitoring, in: Mech. Vib. Cond. Monit., Elsevier, pp 147–168. https://doi.org/10.1016/B978-0-12-819796-7.00008-1
Zhou K, Tang J (2021) Harnessing fuzzy neural network for gear fault diagnosis with limited data labels. Int J Adv Manuf Technol 115:1005–1019. https://doi.org/10.1007/s00170-021-07253-6
Teolis C, Teolis A, Paduano J, Lackner M (2005) Analytic representation of eddy current sensor data for fault diagnostics, in: 2005 IEEE Aerosp Conf, IEEE, 2005: pp 3496–3506.https://doi.org/10.1109/AERO.2005.1559652
Liang M, Zhou K (2022) Probabilistic bearing fault diagnosis using Gaussian process with tailored feature extraction. Int J Adv Manuf Technol 119:2059–2076. https://doi.org/10.1007/s00170-021-08392-6
Pandya DH, Upadhyay SH, Harsha SP (2013) Fault diagnosis of rolling element bearing with intrinsic mode function of acoustic emission data using APF-KNN. Expert Syst Appl 40:4137–4145. https://doi.org/10.1016/j.eswa.2013.01.033
Chen Z, Zhang J, Zhai W, Wang Y, Liu J (2017) Improved analytical methods for calculation of gear tooth fillet-foundation stiffness with tooth root crack. Eng Fail Anal 82:72–81. https://doi.org/10.1016/j.engfailanal.2017.08.028
Pandya Y, Parey A (2013) Failure path based modified gear mesh stiffness for spur gear pair with tooth root crack. Eng Fail Anal 27:286–296. https://doi.org/10.1016/j.engfailanal.2012.08.015
Yu J (2019) A selective deep stacked denoising autoencoders ensemble with negative correlation learning for gearbox fault diagnosis. Comput Ind 108:62–72. https://doi.org/10.1016/j.compind.2019.02.015
Chen X, Zhang B, Gao D (2021) Bearing fault diagnosis base on multi-scale CNN and LSTM model. J Intell Manuf 32:971–987. https://doi.org/10.1007/s10845-020-01600-2
Liang M, Zhou K (2022) A hierarchical deep learning framework for combined rolling bearing fault localization and identification with data fusion. J Vib Control 107754632210916. https://doi.org/10.1177/10775463221091601
Wu X, Zhang Y, Cheng C, Peng Z (2021) A hybrid classification autoencoder for semi-supervised fault diagnosis in rotating machinery. Mech Syst Signal Process 149:107327. https://doi.org/10.1016/j.ymssp.2020.107327
Wang D, Chen Y, Shen C, Zhong J, Peng Z, Li C (2022) Fully interpretable neural network for locating resonance frequency bands for machine condition monitoring. Mech Syst Signal Process 168:108673. https://doi.org/10.1016/j.ymssp.2021.108673
Chen Y, Rao M, Feng K, Zuo MJ (2022) Physics-Informed LSTM hyperparameters selection for gearbox fault detection. Mech Syst Signal Process 171:108907. https://doi.org/10.1016/j.ymssp.2022.108907
Yucesan YA, Viana FAC (2022) A hybrid physics-informed neural network for main bearing fatigue prognosis under grease quality variation. Mech Syst Signal Process 171:108875. https://doi.org/10.1016/j.ymssp.2022.108875
Zhou K, Diehl E, Tang J (2023) Deep convolutional generative adversarial network with semi-supervised learning enabled physics elucidation for extended gear fault diagnosis under data limitations. Mech Syst Signal Process 185:109772. https://doi.org/10.1016/j.ymssp.2022.109772
Li Z, Yan X, Tian Z, Yuan C, Peng Z, Li L (2013) Blind vibration component separation and nonlinear feature extraction applied to the nonstationary vibration signals for the gearbox multi-fault diagnosis. Measurement 46:259–271. https://doi.org/10.1016/j.measurement.2012.06.013
Yu X, Huangfu Y, He Q, Yang Y, Du M, Peng Z (2022) Gearbox fault diagnosis under nonstationary condition using nonlinear chirp components extracted from bearing force. Mech Syst Signal Process 180:109440. https://doi.org/10.1016/j.ymssp.2022.109440
Wang L-H, Zhao X-P, Wu J-X, Xie Y-Y, Zhang Y-H (2017) Motor fault diagnosis based on short-time Fourier transform and convolutional neural network, Chinese. J Mech Eng 30:1357–1368. https://doi.org/10.1007/s10033-017-0190-5
Kankar PK, Sharma SC, Harsha SP (2011) Fault diagnosis of ball bearings using continuous wavelet transform. Appl Soft Comput 11:2300–2312. https://doi.org/10.1016/j.asoc.2010.08.011
Cheng Y, Lin M, Wu J, Zhu H, Shao X (2021) Intelligent fault diagnosis of rotating machinery based on continuous wavelet transform-local binary convolutional neural network. Knowledge-Based Syst 216:106796. https://doi.org/10.1016/j.knosys.2021.106796
Yu D, Yang Y, Cheng J (2007) Application of time–frequency entropy method based on Hilbert-Huang transform to gear fault diagnosis. Measurement 40:823–830. https://doi.org/10.1016/j.measurement.2007.03.004
Liu Z, Peng D, Zuo MJ, Xia J, Qin Y (2022) Improved Hilbert-Huang transform with soft sifting stopping criterion and its application to fault diagnosis of wheelset bearings. ISA Trans 125:426–444. https://doi.org/10.1016/j.isatra.2021.07.011
Chen X, Feng Z (2016) Iterative generalized time–frequency reassignment for planetary gearbox fault diagnosis under nonstationary conditions. Mech Syst Signal Process 80:429–444. https://doi.org/10.1016/j.ymssp.2016.04.023
Feng Z, Liang M, Chu F (2013) Recent advances in time–frequency analysis methods for machinery fault diagnosis: a review with application examples. Mech Syst Signal Process 38:165–205. https://doi.org/10.1016/j.ymssp.2013.01.017
Gupta V, Mittal M, Mittal V (2021) Chaos theory and ARTFA: emerging tools for interpreting ECG signals to diagnose cardiac arrhythmias. Wirel Pers Commun 118:3615–3646. https://doi.org/10.1007/s11277-021-08411-5
An X, Jiang D, Zhao M, Liu C (2012) Short-term prediction of wind power using EMD and chaotic theory. Commun Nonlinear Sci Numer Simul 17:1036–1042. https://doi.org/10.1016/j.cnsns.2011.06.003
Webber CL, Zbilut JP (1994) Dynamical assessment of physiological systems and states using recurrence plot strategies. J Appl Physiol 76:965–973. https://doi.org/10.1152/jappl.1994.76.2.965
Marwan N, Thiel M, Nowaczyk NR (2002) Cross recurrence plot based synchronization of time series. Nonlinear Process Geophys 9:325–331. https://doi.org/10.5194/npg-9-325-2002
Afonso LCS, Rosa GH, Pereira CR, Weber SAT, Hook C, Albuquerque VHC, Papa JP (2019) A recurrence plot-based approach for Parkinson’s disease identification. Futur Gener Comput Syst 94:282–292. https://doi.org/10.1016/j.future.2018.11.054
Ouyang G, Zhu X, Ju Z, Liu H (2014) Dynamical characteristics of surface EMG signals of hand grasps via recurrence plot. IEEE J Biomed Heal Informatics 18:257–265. https://doi.org/10.1109/JBHI.2013.2261311
Rousseeuw PJ (1987) Silhouettes: A graphical aid to the interpretation and validation of cluster analysis. J Comput Appl Math 20:53–65. https://doi.org/10.1016/0377-0427(87)90125-7
Takens F (1981) Detecting strange attractors in turbulence. In: Rand D, Young L-S (eds) Dyn Syst Turbul Warwick 1980. Springer Berlin Heidelberg, Berlin, Heidelberg, pp 366–381
Cao L (1997) Practical method for determining the minimum embedding dimension of a scalar time series. Phys D Nonlinear Phenom 110:43–50
March TK, Chapman SC, Dendy RO (2005) Recurrence plot statistics and the effect of embedding. Phys D Nonlinear Phenom 200:171–184. https://doi.org/10.1016/j.physd.2004.11.002
Hegger R, Kantz H (1999) Improved false nearest neighbor method to detect determinism in time series data. Phys Rev E 60:4970–4973. https://doi.org/10.1103/PhysRevE.60.4970
Eckmann J-P, Kamphorst SO, Ruelle D (1987) Recurrence plots of dynamical systems. Europhys Lett 4:973–977. https://doi.org/10.1209/0295-5075/4/9/004
Matassini L, Kantz H, Hołyst J, Hegger R (2002) Optimizing of recurrence plots for noise reduction. Phys Rev E 65:021102. https://doi.org/10.1103/PhysRevE.65.021102
Cao P, Zhang S, Tang J, Gear Fault Data, https://figshare.com/articles/dataset/Gear_Fault_Data/6127874/1
Case Western Reserve University Bearing Fault Data, https://engineering.case.edu/bearingdatacenter/download-data-file
Cao P, Zhang S, Tang J (2018) Preprocessing-free gear fault diagnosis using small datasets with deep convolutional neural network-based transfer learning. IEEE Access 6:26241–26253. https://doi.org/10.1109/ACCESS.2018.2837621
Boudiaf A, Moussaoui A, Dahane A, Atoui I (2016) A comparative study of various methods of bearing faults diagnosis using the Case Western Reserve University data. J Fail Anal Prev 16:271–284. https://doi.org/10.1007/s11668-016-0080-7
Jolliffe IT (2002) Principal component analysis, Springer-Verlag. N Y. https://doi.org/10.1007/b98835
van der Maaten L, Hinton G (2008) Visualizing Data using t-SNE. J Mach Learn Res 9 2579–2605. http://jmlr.org/papers/v9/vandermaaten08a.html
Starczewski A, Krzyżak A (2015) Performance evaluation of the Silhouette index. In: Rutkowski L, Korytkowski M, Scherer R, Tadeusiewicz R, Zadeh LA, Zurada JM (eds) Artif Intell Soft Comput. Springer International Publishing, Cham, pp 49–58
Zhou K, Tang J (2021) Computational inference of vibratory system with incomplete modal information using parallel, interactive and adaptive Markov chains. J Sound Vib 511:116331. https://doi.org/10.1016/j.jsv.2021.116331
Mucherino A, Papajorgji PJ, Pardalos PM (2009) k-nearest neighbor classification. Data Min Agric. Springer New York, New York, NY, pp 83–106. https://doi.org/10.1007/978-0-387-88615-2_4
Kadilar C, Cingi H (2003) Ratio estimators in stratified random sampling. Biometrical J 45:218–225. https://doi.org/10.1002/bimj.200390007
Berrar D (2019) Cross-Validation, in: Encycl Bioinforma Comput Biol, Elsevier, pp. 542–545. https://doi.org/10.1016/B978-0-12-809633-8.20349-X
Funding
This research is supported by National Science Foundation under grant CMMI–2138522.
Author information
Authors and Affiliations
Contributions
K. Zhou carried out algorithm development and data analysis and interpretation, paper writing, and funding acquisition.
Corresponding author
Ethics declarations
Ethical approval
Not applicable.
Consent to participate
Not applicable.
Consent to publication
Not applicable.
Conflict of interest
The author declares no competing interests.
Additional information
Publisher's note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Zhou, K. Enhanced feature extraction for machinery condition monitoring using recurrence plot and quantification measure. Int J Adv Manuf Technol 123, 3421–3436 (2022). https://doi.org/10.1007/s00170-022-10392-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00170-022-10392-z