[1]谭继勇,罗 俊,谢江涛,等.基于鲸鱼优化和批量规范化卷积神经网络的振动信号去噪[J].机械与电子,2024,42(04):3-8.
　TAN Jiyong,LUO Jun,XIE Jiangtao,et al.A Convolutional Neural Network with Whale Optimization and Batch Normalization for the Denoising of Vibration Signal[J].Machinery & Electronics,2024,42(04):3-8.
点击复制

基于鲸鱼优化和批量规范化卷积神经网络的振动信号去噪()
分享到：

《机械与电子》[ISSN:1001-2257/CN:52-1052/TH]

卷:
42
期数:
2024年04期
页码:
3-8
栏目:
研究与设计
出版日期:
2024-04-23

文章信息/Info

Title:
A Convolutional Neural Network with Whale Optimization and Batch Normalization for the Denoising of Vibration Signal
文章编号:
1001-2257 ( 2024 ) 04-0003-06
作者:
谭继勇 1 ; 罗 俊 1 ; 谢江涛 1 ; 秦玉玺 2 ; 汪友明 2
1. 西南电子设备研究所,四川 成都 610036 ;
2. 西安邮电大学自动化学院,陕西 西安 710121
Author(s):
TAN Jiyong1 ;  LUO Jun1 ;  XIE Jiangtao1 ;  QIN Yuxi2 ;  WANG Youming2
( 1.Southwest China Research Institute of Electronic Equipment , Chengdu 610036 , China ;
2.School of Automation , Xi ’an University of Posts and Telecommunications , Xi ’an 710121 , China )
关键词:
鲸鱼优化; 批量规范化; 深度学习; 振动信号; 去噪
Keywords:
whale optimization ;  batch normalization ;  deep learning ;  vibration signal ;  denoising
分类号:
TP391.4
文献标志码:
A
摘要:
由于初始权值的随机选取,传统卷积神经网络模型易陷入局部最优解,难以从噪声振动信号中提取纯净信号。针对这一问题,提出鲸鱼优化算法和批量规范化卷积神经网络相结合的振动信号去噪方法。该方法通过批量规范化层对隐层中的参数分布进行归一化,采用鲸鱼优化算法对网络权值参数进行寻优,解决网络模型存在局部最优的问题。将含噪振动信号的幅度谱和噪声信号的时域波形分别作为网络的训练特征和目标,充分利用振动信号在时频域上的分布特性,通过残差学习实现去噪的目的。实验表明,与小波阈值去噪方法、 EMD 方法和卷积神经网络相比,所提方法有效提升了信噪比,降低了均方误差和平均绝对误差,有效保留了振动信号原始特征,并增强了其去噪能力。
Abstract:
Due to the random selection of the initial weights , traditional convolutional neural network is prone to trap in local optimum , which leads to the difficulties in the extraction of clean signals from noisy vibration signals.To address this problem , a convolutional neural network with whale optimization and batch normalization ( WO-BN-CNN ) is proposed.A batch normalization layer is added after the convolutional neural network to normalize the parameter distribution in the hidden layer.The whale optimization algorithm is applied to optimize the network weight parameters.The amplitude spectrum of the noisy vibration signal and the time-domain waveform of the noisy signal are taken as the training features and the training target respectively to fully utilize the distribution characteristics of vibration signals in the time frequency domain and realize the denoising by residual learning.The experimental results show that the proposed method improves the signal-to-noise ratio and reduces the mean square error and mean absolute error compared with wavelet threshold denoising , EMD , convolutional neural network , which enhances the denoising ability while preserving the original features of the vibration signal.

参考文献/References:

[ 1 ] WANG Y M , CAO G Q.A multiscale convolution neural network for bearing fault diagnosis based on frequency division denoising under complex noise conditions [ J ] .Complex and intelligent systems , 2023 , 9 :4263-4285.

[ 2 ] 范明浩,何文超,凌同华,等 . 基于小波变换时能密度法的爆破振动信号分析[ J ] . 交通科学与工程,2022 , 38( 3 ): 79-85.
[ 3 ] 纪俊卿,张亚靓,孟祥川,等 . 自适应小波阈值滚动轴承故障振动信号降噪方法[ J ] . 哈尔滨理工大学学报,2021 , 26 ( 2 ): 124-130.
[ 4 ] SAROSSY M , CROWSTON J , KUMAR D , et al.Empirical mode decomposition denoising of the electroretinogram to enhance measurement of the photopic negative response [ J ] .Biomedical signal processing and control , 2022 , 71 : 103164.
[ 5 ] 王利,张伟,罗定南 . 基于随机奇异值分解的局部放电脉冲提取及去噪技术[ J ] . 中国电力, 2021 , 54 ( 10 ): 196-203.
[ 6 ] QUAN Y H , CHEN Y X , SHAO Y Z , et al.Image denoising using complex-valued deep CNN [ J ] .Pattern recognition , 2021 , 111 : 107639.
[ 7 ] 周末,宋玉蓉,宋波,等 . 融合自注意力机制的 D-BGRU 文本分类模型[ J ] . 微电子学与计算机, 2021 , 38( 12 ): 8-16.
[ 8 ] 汪友明,程琳 . 改进的 CNN-LSTM 轴承故障诊断方法[ J ] . 西安邮电大学学报, 2021 , 26 ( 1 ): 97-103.
[ 9 ] JAIN V , SRUNG H S.Natural image denoising with convolutional networks [ J ] .Advances in neural information processing systems , 2009 , 21 : 769-776.
[ 10 ] HAN H , WANG H , LIU Z L , et al.Intelligent vibration signal denoising method based on non-local fully convolutional neural network for rolling bearings [ J ] . ISA Transactions , 2022 , 122 : 13-23.
[ 11 ] 邢玉龙,王剑,赵会兵,等 . 基于全卷积神经网络的机车信号降噪[ J ] . 西南交通大学学报, 2021 , 56 ( 2 ): 444-450.
[ 12 ] BASHAB A , IBRAHIM A O , ABEDELGABAR E E , et al.A systematic mapping study on solving university timetabling problems using meta-heuristic algorithms [ J ] .Neural computing and applications , 2020 , 32 ( 23 ): 17397-17432.
[ 13 ] MIRJALILI S , LEWIS A.The whale optimization algorithm [ J ] .Advances in engineering software , 2016 , 95 : 51 67.
[ 14 ] ZHANG K , ZUO W , CHEN Y , et al.Beyond a gaussian denoiser : residual learning of deep cnn for image denoising [ J ] .IEEE Transactions on image processing , 2017 , 26 ( 7 ): 3142-3155.

备注/Memo

备注/Memo:
收稿日期: 2023-09-16
基金项目:国家自然科学基金资助项目( 51875457 );陕西省重点研发计划( 2022SF-259 )
作者简介:谭继勇 ( 1980- ),男,四川资中人,博士,高级工程师,研究方向为设备智能运维,通信作者;罗 俊 ( 1983- ),男,四川江油人,硕士,高级工程师,研究方向为设备智能运维;谢江涛 ( 1997- ),男,云南昆明人,硕士,助理工程师,研究方向为设备智能诊断;秦玉玺 ( 1998- ),女,陕西延安人,硕士研究生,研究方向为设备监测与信号处理;汪友明 ( 1981- ),男,湖北黄冈人,博士,教授,研究方向为设备故障诊断。
更新日期/Last Update: 2024-04-29