Vibration signals are used to monitor the running state of mechanical equipment, but always suffer from a lot of noise in the acquisition process. In order to eliminate noise interference as much as possible, a multilevel residual convolution autoencoder network based noise learning method (LN-MRSCAE) is proposed in this paper. The LN-MRSCAE consists of a deep convolutional autoencoder network and multilevel residual, in which the learning noise module encodes and decodes the noise components, combining with a residual module to obtain the denoised signal. The multilevel residual structure is designed to address the gradient disappearance in network learning and improve the training speed. In specific, the noise learning replaces the traditional clean signal learning. Instead of learning the characteristics of the original clean signal, just learn the characteristics of the noise signal. The effectiveness of LN-MRSCAE network denoising is verified by classic analog signal and actual bearing vibration signals with different faults. The results show that the LN-MRSCAE model is superior to the latest models, and the noise component of the signal is obviously suppressed.
ChiangHHsiehYFuS, et al. (2019) Noise reduction in ECG signals using fully convolutional denoising autoencoders. IEEE Access7: 60806–60813.
2.
DengFLiuCLiuY, et al. (2021) A hybrid SVD-based denoising and self-adaptive TMSST for high-speed train axle bearing fault detection. Sensors21(18): 1–23.
3.
DongXLiGJiaY, et al. (2021) Non-iterative denoising algorithm for mechanical vibration signal using spectral graph wavelet transform and detrended fluctuation analysis. Mechanical Systems and Signal Processing149: 1–21.
4.
DoumanidisCCAnagnostouCArvanitiES (2021) Hybrid speech enhancement system based on RNN and spectral features. arXiv preprint arXiv:2105. 11813.
5.
FanGLiJHaoH, et al. (2020) Vibration signal denoising for structural health monitoring by residual convolutional neural networks. Measurement157: 1–15.
6.
GeJNiuTXuD, et al. (2020) A rolling bearing fault diagnosis method based on EEMD-WSST signal reconstruction and multi-scale entropy. Entropy22(3): 1–28.
7.
HuangNShenZLongS, et al. (1998) The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. Proceedings Mathematical Physical & Engineering Sciences454(1971): 903–995.
8.
JiaYLiGDongX, et al. (2021) A novel denoising method for vibration signal of hob spindle based on EEMD and grey theory. Measurement169: 1–12.
9.
JiangSXuanJDuanJ, et al. (2021) Dual attention dense convolutional network for intelligent fault diagnosis of spindle-rolling bearings. Journal of Vibration and Control27(21–22): 2403–2419.
10.
LeiYLiuZOuazriJ, et al. (2017) A fault diagnosis method of rolling element bearings based on CEEMDAN. Journal of Mechanical Engineering Science231(10): 1804–1815.
11.
LiHLiuTWuX, et al. (2019) Research on bearing fault feature extraction based on singular value decomposition and optimized frequency band entropy. Mechanical systems and signal processing118: 477–502.
12.
LiXShaoHLuS, et al. (2022) Highly-efficient fault diagnosis of rotating machinery under time-varying speeds using LSISMM and small infrared thermal images. IEEE Transactions on Systems, Man, and Cybernetics: Systems52: 7328–7340.
13.
LiuXZhouQZhaoJ, et al. (2019) Fault diagnosis of rotating machinery under noisy environment conditions based on a 1-D convolutional autoencoder and 1-D convolutional neural network. Sensors19(4): 1–20.
14.
LiuDCuiLChengW, et al. (2022) Rolling bearing fault severity recognition via data mining integrated with convolutional neural network. IEEE Sensors Journal22(6): 5768–5777.
15.
LvYYuanRSongG (2016) Multivariate empirical mode decomposition and its application to fault diagnosis of rolling bearing. Mechanical Systems & Signal Processing81: 219–234.
16.
MariyappaNSengottuvelSParasakthiC, et al. (2014) Baseline drift removal and denoising of MCG data using EEMD: role of noise amplitude and the thresholding effect. Medical Engineering & Physics36(10): 1266–1276.
17.
MiaoMLiuCYuJ, et al. (2021) Adaptive densely connected convolutional auto-encoder-based feature learning of gearbox vibration signals. IEEE Transactions on Instrumentation and Measurement70: 1–11.
18.
QinCShiGTaoJ, et al. (2022) An adaptive hierarchical decomposition-based method for multi-step cutterhead torque forecast of shield machine. Mechanical Systems and Signal Processing175: 1–29.
19.
SadooghiMSSiamakEK (2016) A new performance evaluation scheme for jet engine vibration signal denoising. Mechanical Systems and Signal Processing76–77: 201–212.
20.
ShiHChenJSiJ, et al. (2020) Fault diagnosis of rolling bearings based on a residual dilated pyramid network and full convolutional denoising autoencoder. Sensors20(20): 1–25.
21.
TangGWangX (2016) Early fault diagnosis of rolling bearings based on IVMD fusion singular value difference spectrum. Vibration, Testing and Diagnosis36(4): 700–707.
22.
TianSZhenDGuoJ, et al. (2021) Fault diagnosis of rolling bearing using improved wavelet threshold denoising and fast spectral correlation analysis. Shock and Vibration2021: 1–10.
23.
TorresMColominasMSchlotthauerG, et al. (2011) A complete ensemble empirical mode decomposition with adaptive noise. In: IEEE International Conference on Acoustics, Speech and Signal Processing, Prague, Czech Republic, 22–27 May 2011, pp. 4144–4147.
24.
VoDMNguyenDMLeTP, et al. (2021) HI-GAN: a hierarchical generative adversarial network for blind denoising of real photographs. Information Sciences570: 225–240.
25.
WangZZhangQXiongJ, et al. (2017) fault diagnosis of a rolling bearing using wavelet packet denoising and random forests. IEEE Sensors Journal17(17): 5581–5588.
26.
WangCZhuGLiuT, et al. (2021) A sub-domain adaptive transfer learning base on residual network for bearing fault diagnosis. Journal of Vibration and Control29(1–2): 105–117.
27.
WuZHuangNChenX, et al. (2009) Ensemble empirical mode decomposition: a noise-assisted data analysis method. Advances in adaptive data analysis1(1): 1–41.
28.
YuJZhouX (2020) One-dimensional residual convolutional autoencoder based feature learning for gearbox fault diagnosis. IEEE Transactions on Industrial Informatics16(10): 6347–6358.
29.
YueGCuiXZouY, et al. (2019) A Bayesian wavelet packet denoising criterion for mechanical signal with non-Gaussian characteristic. Measurement138: 702–712.
