[1]吉 哲,吕 飞,王 冕.基于优化 VMD 和深度卷积神经网络的柴油发电机组故障诊断[J].机械与电子,2023,41(08):8-13.
　JI Zhe,LYU Fei,WANG Mian.Fault Diagnosis of Diesel Generator Set Based on Optimized VMD and Deep Convolution Neural Network[J].Machinery & Electronics,2023,41(08):8-13.
点击复制

基于优化 VMD 和深度卷积神经网络的柴油发电机组故障诊断()
分享到：

《机械与电子》[ISSN:1001-2257/CN:52-1052/TH]

卷:
41
期数:
2023年08期
页码:
8-13
栏目:
设计与研究
出版日期:
2023-08-25

文章信息/Info

Title:
Fault Diagnosis of Diesel Generator Set Based on Optimized VMD and Deep Convolution Neural Network
文章编号:
1001-2257 ( 2023 ) 08-0008-06
作者:
吉 哲; 吕 飞; 王 冕
海军士官学校,安徽 蚌埠 233012
Author(s):
JI Zhe ;  LYU Fei ;  WANG Mian
( Naval Petty Officer Academy , Bengbu 233012 , China )
关键词:
优化变分模态分解; 深度卷积神经网络; 柴油发电机组; 故障诊断
Keywords:
optimal variational modal decomposition ;  deep convolution neural network ;  diesel generator set ;  fault diagnosis
分类号:
TM314
文献标志码:
A
摘要:
针对柴油发电机组故障信号非平稳非线性特征参数难以提取的问题,结合深度学习的优势,提出一种基于变分模态分解( VMD )和深度卷积神经网络( CNN )相结合的故障诊断模型。为克服 VMD 算法中分解模态数较难确定的问题,采用峭度准则来选取最优分解模态数,将优化的 VMD 算法用于不同工况下的柴油发电机组声信号进行分解,转化为灰度图像作为网络输入,通过 CNN 自动进行特征提取,并利用训练集样本进行网络训练。为避免背景噪声和提高故障诊断精度,使用双传感器采集发电机组声信号。通过测试集的验证,表明该模型在对柴油发电机组的故障诊断中实现了不同工况下的可靠判别,进一步提升了故障判别的准确性。通过对比其他 4 种故障诊断方法,结果表明所提方法诊断精度更高且鲁棒性好。
Abstract:
In order to solve the problem that it is difficult to extract the non-stationary nonlinear characteristic parameters of diesel generator set fault signals , a fault diagnosis model based on the combination of variational mode decomposition( VMD ) and deep convolution neural network( CNN ) is proposed combined with the advantages of deep learning.In order to overcome the problem that it is difficult to determine the number of decomposition modes in VMD algorithm , the kurtosis criterion is used to select the optimal number of decomposition modes.The optimized VMD algorithm is used to decompose the acoustic signals of diesel generator sets under different working conditions , and is converted into gray images as network input.The feature is automatically extracted through CNN , and network training is conducted using training set samples.In order to avoid background noise and improve the accuracy of fault diagnosis , dual sensors are used to collect the acoustic signals of the generator set.The verification of the test set shows that the model can realize reliable discrimination under different working conditions in the fault diagnosis of diesel generator sets , and further improve the accuracy of fault discrimination.Compared with other four fault diagnosis methods , the results show that the proposed method has higher diagnosis accuracy and better robustness.

参考文献/References:

[ 1 ] 李晓博,江志农,张沛,等 . 基于 IMS 聚类算法的柴油发动机故障诊断方法研究[ J ] . 振动与冲击,2018 , 37( 7 ): 193-198 , 246.

[ 2 ] 蔡艳平,范宇,陈万,等 . 改进时频分析和特征融合在内燃机故障诊断中的应用[ J ] . 中国机械工程,2020 , 31( 16 ): 1901-1911.
[ 3 ] 唐文权,徐武,文聪,等 . 基于核主成分分析和深度置信网络的暂态稳定评估[ J ] . 电机与控制应用,2021 , 48( 1 ): 46-52.
[ 4 ] 姜洪开,邵海东,李兴球 . 基于深度学习的飞行器智能故障诊断方法[ J ] . 机械工程学报, 2019 , 55 ( 7 ): 27-34.
[ 5 ] 胡晓依,荆云建,宋志坤,等 . 基于 CNN-SVM 的深度卷积神经网络轴承故障识别研究[ J ] . 振动与冲击,2019 , 38 ( 18 ): 173-178.
[ 6 ] 王海龙,夏筱筠,孙维堂 . 基于 EMD 与卷积神经网络的滚动轴承故障诊断[ J ] . 组合机床与自动化加工技术,2019 ( 10 ): 46-48 , 52.
[ 7 ] 赵丹阳,董唯光,高锋阳 . 一种改进卷积神经网络的逆变器故障诊断[ J ] . 电源学报, 2020 , 18 ( 3 ): 124-132.
[ 8 ] 鲁文波,蒋伟康,潘思伟,等 . 基于近场声全息声像图纹理特征的机械故障诊断方法[ J ] . 振动工程学报, 2013 ,26 ( 4 ): 617-623.
[ 9 ] DRAGOMIRETSKIY K , ZOSSO D.Variational mode decomposition[ J ] .IEEE Transactions on signal processing , 2014 , 62 ( 3 ):531-544.
[ 10 ] LI Y B , XU M Q , WANG R X , et al.A fault diagnosis scheme for rolling bearing based on local mean decomposition and improved multiscale fuzzy entropy[ J ] .Journal of sound and vibration , 2016 , 360 : 277-299.
[ 11 ] JANSSENS O , SLAVKOVIKJ V , WERVISCH B , et al.Convolutional neural network based fault detection for rotating machinery[ J ] .Journal of sound and vibration , 2016 , 377 : 331-345.
[ 12 ] 焦李成,赵进,杨淑媛,等 . 深度学习、优化与识别[ M ] . 北京:清华大学出版社,2017.
[ 13 ] 景军锋,刘娆 . 基于卷积神经网络的织物表面缺陷分类方法[ J ] . 测控技术, 2018 , 37 ( 9 ): 20-25.
[ 14 ] WEN L , LI X Y , GAO L , et al.A new convolutional neural network-based data-driven fault diagnosis method [ J ] .IEEE Transactions on industrial electronics , 2018 , 65 ( 7 ): 5990-5998.

相似文献/References:

[1]傅春啸,屈天祥,滕 飞,等.基于 DCNN 的无人直升机自转过程建模[J].机械与电子,2022,(03):8.
　FU Chunxiao,QU Tianxiang,TENG Fei,et al.Modeling of Unmanned Helicopter Autorotation Process Based on DCNN[J].Machinery & Electronics,2022,(08):8.

备注/Memo

备注/Memo:
收稿日期: 2022-11-15
基金项目:院校科研发展基金项目( SXKY2020001 )
作者简介:吉 哲 ( 1983- ),男,江苏靖江人,硕士,副教授,研究方向为舰船电气故障诊断;吕 飞 ( 1982- ),男,安徽阜阳人,硕士,讲师,研究方向为电力设备故障诊断;王 冕 ( 1996- ),男,安徽蚌埠人,学士,助教,研究方向为电机及其控制。
更新日期/Last Update: 2023-09-07