基于深度自编码器的振动信号盲去噪方法

PDF(1781 KB)

振动与冲击 ›› 2023, Vol. 42 ›› Issue (12) : 118-125.

论文

基于深度自编码器的振动信号盲去噪方法

万若青，张纯，江汇强，黎寅斌

作者信息 +

A blind denoising method of vibration signals based on a deep autoencoder

WAN Ruoqing，ZHANG Chun，JIANG Huiqiang，LI Yinbin

Author information +

文章历史 +

摘要

为减少传统振动信号去噪方法对信号时、频域先验信息的依赖性，提出了一种基于深度自编码器的振动信号盲去噪方法。在缺少干净信号作为神经网络训练目标的情况下，使用邻近采样及扩展的策略，从原始信号中构造去噪深度神经网络的训练样本对，通过自监督学习得到能对原始信号有效降噪的深度神经网络；并提出适用性评价指标来指导在实际工程应用时信号采样频率的设置。对仿真信号和实测信号的去噪分析表明该方法不依赖于真实信号的先验信息，且对于稳态信号和非稳态信号都有良好的自适应去噪效果。

Abstract

In order to reduce the dependence of traditional vibration signal denoising methods on the prior information in time or frequency domain, a blind vibration signal denoising method based on deep autoencoder was proposed. In the absence of clean signals as the training target of the neural network, the adjacent sampling and expansion strategy was used to construct the training sample pair of the denoising deep neural network from the original signal. The deep neural network that can effectively denoise the original signals was obtained through self-supervised learning. And the applicability evaluation index was proposed to guide the setting of signal sampling frequency in practical engineering application. The denoising analysis of simulation signals and measured signals shown that the proposed method does not depend on the prior information of real signals and has great adaptive denoising effect for both steady and unsteady signals.

导出引用

万若青，张纯，江汇强，黎寅斌. 基于深度自编码器的振动信号盲去噪方法[J]. 振动与冲击, 2023, 42(12): 118-125

WAN Ruoqing，ZHANG Chun，JIANG Huiqiang，LI Yinbin. A blind denoising method of vibration signals based on a deep autoencoder[J]. Journal of Vibration and Shock, 2023, 42(12): 118-125

参考文献

[1] 李舜酩，郭海东，李殿荣. 振动信号处理方法综述[J]. 仪器仪表学报，2013, 34(08):1907-1915.
LI Shun-ming, GUO Hai-dong, LI Dian-rong. Review of vibration signal processing methods[J]. Chinese Journal of Scientific Instrument, 2013, 34(8): 1907-1915.
[2] FAN Gao, LI Jun, HAO Hong. Vibration signal denoising for structural health monitoring by residual convolutional neural networks[J]. Measurement, 2020, 157: 107651.
[3] 顾名坤，吕振华. 基于振动加速度测量的振动速度和位移信号识别方法探讨[J]. 机械科学与技术，2011, 30(04):522-526.
Gu Ming-kun, Lv Zhen-hua. Identification of a mechanism's vibration velocity and displacement based on the acceleration measurement[J]. Mechanical Science and Technology for Aerospace Engineering, 2011, 30(4): 522-526.
[4] 王宏强，尚春阳，高瑞鹏，等. 基于小波系数变换的小波阈值去噪算法改进[J]. 振动与冲击，2011, 30(10):165-168.
WANG Hong-qiang, SHANG Chun-yang, GAO Rui-peng, et al. An improvement of wavelet shrinkage denoising via wavelet coefficient transformation[J]. Journal of Vibration and Shock, 2011, 30(10): 165-168.
[5] 马宏伟，张大伟，曹现刚，等. 基于EMD的振动信号去噪方法研究[J]. 振动与冲击，2016, 35(22):38-40.
MA Hong-wei, ZHANG Da-wei, CAO Xiang-gang, et al. Vibration signal de-noising method based on empirical mode decomposition[J]. Journal of Vibration Shock, 2016, 35: 38-40.
[6] Wang X, Zhao Y, Teng X, et al. A stacked convolutional sparse denoising autoencoder model for underwater heterogeneous information data[J]. Applied Acoustics, 2020, 167: 107391.
[7] 曹现刚，许欣，雷卓，等. 基于降噪自编码器与改进卷积神经网络的采煤机健康状态识别[J]. 信息与控制，2022, 51(01):98-106.
CAO Xian-gang, XU Xin, LEI Zhuo, et al. Health status identification of shearer based on denoising autoencoder and improved convolutional neural network[J]. Information and Control, 2022, 51(01):98-106.
[8] Meng Z, Zhan X, Li J, et al. An enhancement denoising autoencoder for rolling bearing fault diagnosis[J]. Measurement, 2018, 130: 448-454.
[9] Langarica S, Rüffelmacher C, Núñez F. An industrial internet application for real-time fault diagnosis in industrial motors[J]. IEEE Transactions on Automation Science and Engineering, 2019, 17(1): 284-295.
[10] Majumdar A. Blind denoising autoencoder[J]. IEEE transactions on neural networks and learning systems, 2018, 30(1): 312-317.
[11] Langarica S, Pizarro G, Poblete P M, et al. Denoising and Voltage Estimation in Modular Multilevel Converters Using Deep Neural-Networks[J]. IEEE Access, 2020, 8: 207973-207981.
[12] Cui X, Li D, Li Z, et al. A GAN noise modeling based blind denoising method for guided waves[J]. Measurement, 2022, 188: 110596.
[13] Lehtinen J, Munkberg J, Hasselgren J, et al. Noise2Noise: Learning Image Restoration without Clean Data[C]// International Conference on Machine Learning. PMLR, 2018. 2965-2974.
[14] Huang T, Li S, Jia X, et al. Neighbor2Neighbor: Self-Supervised Denoising from Single Noisy Images[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2021. 14781-14790.
[15] 李占龙，刘林霞，李虹，等. 基于 VMD-Teager 的非平稳振动时频特性研究[J]. 兵器装备工程学报，2021, 42( 01) : 150-156.
LI Zhan-long，LIU Lin-xia，LI Hong，et al. Research on Time-Frequency Characteristics of Non-Stationary Vibration Based on VMD-Teager[J]. Journal of Ordnance Equipment Engineering, 2021, 42( 01) : 150-156.