This paper proposes a novel symbolic representation method of feature extraction for fault diagnosis and condition monitoring. The Symbolic Aggregate approXimation (SAX) technique basically transforming real-valued time series into symbol sequences, has been proven as a newly developed tool of feature extraction for fault diagnosis. However, the original SAX is based on the Piecewise Aggregate Approximation (PAA) representation, which is primarily transformed by the calculation of mean value of the equal sized data subsection for dimensionality reduction. Such mean value-based method has a high possibility of missing important information patterns in vibration signals. To overcome this limitation, an enhanced SAX (ESAX) is proposed to extract fault features well from vibration signals. The ESAX utilizes mean value together with two additional important points (the max and min points) to conduct the symbol representation in PAA process. Next, the Shannon entropy technique is conducted on the symbol sequences generated by ESAX to extract features for classification tasks. Compared with SAX, the ESAX can extract more comprehensive signal characteristics considering important information points and local fault patterns. The effectiveness and superiority of the ESAX were validated by experimental studies using the fault signals of rolling bearings.
Z.Feng, H.Ma and M.J.Zuo, Spectral negentropy based sidebands and demodulation analysis for planet bearing fault diagnosis[J], Journal of Sound and Vibration410 (2017), 124–150.
2.
Y.Miao, M.Zhao, J.Lin, et al., Application of an improved maximum correlated kurtosis deconvolution method for fault diagnosis of rolling element bearings[J], Mechanical Systems and Signal Processing92 (2017), 173–195.
3.
C.Mishra, A.K.Samantaray and G.Chakraborty, Rolling element bearing fault diagnosis under slow speed operation using wavelet de-noising[J], Measurement103 (2017), 77–86.
4.
T.D.Popescu and D.Aiordachioaie, Fault detection of rolling element bearings using optimal segmentation of vibrating signals[J], Mechanical Systems and Signal Processing116 (2019), 370–391.
5.
K.Kumar, S.Shukla and S.K.Singh, A combined approach for weak fault signature extraction of rolling element bearing using Hilbert envelop and zero frequency resonator[J], Journal of Sound and Vibration419 (2018), 436–451.
6.
R.Medina, X.Alvarez, JadánD, et al., Gearbox fault classification using dictionary sparse based representations of vibration signals[J], Journal of Intelligent & Fuzzy Systems34(6) (2018), 3605–3618.
7.
R.J.Alfredson and J.Mathew, Time domain methods for monitoring the condition of rolling element bearings[J], NASA STI/Recon Technical Report A86 (1985), 102–107.
8.
E.Sejdić, I.Orović and S.Stanković, Compressive sensing meets time-frequency: An overview of recent advances in time-frequency processing of sparse signals[J], Digital Signal Processing2017.
9.
A.Brandt and R.Brincker, Integrating time signals in frequency domain - Comparison with time domain integration[J], Measurement58 (2014), 511–519.
10.
C.Mateo and J.A.Talavera, Short-Time Fourier Transform with the Window Size Fixed in the Frequency Domain[J], Digital Signal Processing, 2017.
11.
A.K.S.Jardine, D.Lin and D.Banjevic, A review on machinery diagnostics and prognostics implementing condition-based maintenance[J], Mechanical Systems and Signal Processing20(7) (2006), 1483–1510.
12.
J.Li, M.Li, J.Zhang, et al., Frequency-shift multiscale noise tuning stochastic resonance method for fault diagnosis of generator bearing in wind turbine[J], Measurement133 (2019), 421–432.
13.
Z.K.Peng and F.L.Chu, Application of the wavelet transform in machine condition monitoring and fault diagnostics: A review with bibliography[J], Mechanical Systems and Signal Processing18(2) (2004), 199–221.
14.
Z.K.Peng, W.T.Peter and F.L.Chu, A comparison study of improved Hilbert-Huang transform and wavelet transform: Application to fault diagnosis for rolling bearing[J], Mechanical Systems and Signal Processing19(5) (2005), 974–988.
15.
H.Qiu, J.Lee, J.Lin, et al., Wavelet filter-based weak signature detection method and its application on rolling element bearing prognostics[J], Journal of Sound and Vibration289(4-5) (2006), 1066–1090.
16.
M.Gupta, S.S.Bharti and S.Agarwal, Emotion recognition from speech using wavelet packet transform and prosodic features[J], Journal of Intelligent & Fuzzy Systems (Preprint), 1–13.
17.
J.Zheng, H.Pan, S.Yang, et al., Adaptive parameterless empirical wavelet transform based time-frequency analysis method and its application to rotor rubbing fault diagnosis[J], Signal Processing130 (2017), 305–314.
18.
J.Wang, Q.Wei, L.Zhao, et al., An improved empirical mode decomposition method using second generation wavelets interpolation[J], Digital Signal Processing, 2018.
19.
N.E.Huang, The empirical mode decomposition method and the hilbert spectrum for non-stationary time series[J], Proc Roy Soc London45AA (1998), 703–775.
20.
T.Veerakumar, B.N.Subudhi and S.Esakkirajan, Empirical mode decomposition and adaptive bilateral filter approach for impulse noise removal[J], Expert Systems with Applications121 (2019), 18–27.
21.
J.Zheng, H.Pan, S.Yang, et al., Adaptive parameterless empirical wavelet transform based time-frequency analysis method and its application to rotor rubbing fault diagnosis[J], Signal Processing130 (2017), 305–314.
22.
J.Gilles, Empirical wavelet transform[J], IEEE Transactions on Signal Processing61(16) (2013), 3999–4010.
23.
H.Cao, F.Fan, K.Zhou, et al., Wheel-bearing fault diagnosis of trains using empirical wavelet transform[J], Measurement82 (2016), 439–449.
24.
M.Kedadouche, Z.Liu and V.H.Vu, A new approach based on OMA-empirical wavelet transforms for bearing fault diagnosis[J], Measurement90 (2016), 292–308.
25.
J.Pan, J.Chen, Y.Zi, et al., Mono-component feature extraction for mechanical fault diagnosis using modified empirical wavelet transform via data-driven adaptive Fourier spectrum segment[J], Mechanical Systems and Signal Processing72 (2016), 160–183.
26.
J.Chen, J.Pan, Z.Li, et al., Generator bearing fault diagnosis for wind turbine via empirical wavelet transform using measured vibration signals[J], Renewable Energy89 (2016), 80–92.
27.
D.Wang, K.L.Tsui and Y.Qin, Optimization of segmentation fragments in empirical wavelet transform and its applications to extracting industrial bearing fault features[J], Measurement133 (2019), 328–340.
28.
J.Lin, E.Keogh, S.Lonardi, et al., A symbolic representation of time series, with implications for streaming algorithms[C]//Proceedings of the 8th ACM SIGMOD workshop on Research issues in data mining and knowledge discovery, ACM (2003), 2–11.
29.
Y.Li, Y.Yang, X.Wang, et al., Early fault diagnosis of rolling bearings based on hierarchical symbol dynamic entropy and binary tree support vector machine[J], Journal of Sound and Vibration428 (2018), 72–86.
30.
A.Sultan, X.Yang, A.A.E.Hajomer, et al., Chaotic distribution of QAM symbols for secure OFDM signal transmission[J], Optical Fiber Technology47 (2019), 61–65.
31.
Z.Wang, Z.Wang and S.Chen, Encrypted image transmission in OFDM-based VLC systems using symbol scrambling and chaotic DFT precoding[J], Optics Communications431 (2019), 229–237.
32.
G.Georgoulas, P.Karvelis, T.Loutas, et al., Rolling element bearings diagnostics using the Symbolic Aggregate approXimation[J], Mechanical Systems and Signal Processing60 (2015), 229–242.
33.
J.Shieh and E.Keogh, i SAX: Indexing and mining terabyte sized time series[C]//Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining, ACM (2008), 623–631.
34.
S.Upadhyaya, K.Farahmand and T.Baker-Demaray, Comparison of NN and LR classifiers in the context of screening native American elders with diabetes[J], Expert Systems with Applications40(15) (2013), 5830–5838.
35.
J.Qiao, X.Meng and W.Li, An Incremental Neuronal-Activity-based RBF Neural Network for Nonlinear System Modeling[J], Neurocomputing, 2018.
