基于软阈值降噪的脉冲卷积神经网络轴承故障诊断方法  

Bearing fault diagnosis method based on soft threshold denoising for spiking convolutional neural network

作　　者：李浩[1] 黄晓峰[1] 邹豪杰 孙英杰[1] LI Hao;HUANG Xiaofeng;ZOU Haojie;SUN Yingjie(College of Railway Transportation,Hu’nan University of Technology,Zhuzhou,Hu’nan 412007;College of Computer Science,Hu’nan University of Technology,Zhuzhou,Hu’nan 412007)

机构地区：[1]湖南工业大学轨道交通学院,湖南株洲412007 [2]湖南工业大学计算机学院,湖南株洲412007

出　　处：《电气技术》2024年第2期12-20,共9页Electrical Engineering

基　　金：湖南省自然科学基金(2022JJ50088、2023JJ50198)。

摘　　要：针对工业场景下滚动轴承信号易受噪声干扰,导致故障诊断准确率低和稳定性差的问题,本文提出一种基于软阈值降噪的脉冲卷积神经网络诊断方法。该方法使用软阈值滤波去噪,运用带时间标签的卷积层处理二维信号,增强动态特征提取能力。同时,通过引入IF和LIF神经元实现对时域和频域信息的联合编码,并采用替代梯度法进行端到端训练。实验结果显示,在信噪比为6dB时,所提方法的诊断准确率达100%,在信噪比为-6dB时诊断准确率达77.33%,优于其他常用方法,表明所提方法在噪声下具有良好的诊断效果和稳定性。The signals of rolling bearings are easily interfered by noise in industrial environments,which reduces fault diagnosis accuracy and worsens stability.This paper proposes a diagnostic method based on soft threshold denoising for spiking convolutional neural network.Soft threshold filtering for noise reduction is proposed in this paper.This paper uses time-tagged convolutional layers to process two-dimensional signals to enhance dynamic feature extraction capabilities.IF and LIF neurons are introduced to jointly encode time domain and frequency domain information,and the surrogate gradient method is used for end-to-end training.The results show that the diagnostic accuracy reaches 100%under the signal-to-noise ratio of 6dB,and still reaches 77.33%under the signal-to-noise ratio of−6dB.The results of this method have certain advantages compared with commonly used methods,which verifies that the proposed method has better diagnostic results and higher stability under noise.

关 键 词：故障诊断 软阈值 脉冲神经网络(SNN) 替代梯度法 

分 类 号：TH133.3[机械工程—机械制造及自动化] TP183[自动化与计算机技术—控制理论与控制工程]