[1]陈 宇,程道来,马向华,等.基于 WDCNN-LSTM 混合模型的滚动轴承故障诊断[J].机械与电子,2025,(02):9-15.
　CHEN Yu,CHENG Daolai,MA Xianghua,et al.Fault Diagnosis of Rolling Bearing Based on WDCNN-LSTM Hybrid Model[J].Machinery & Electronics,2025,(02):9-15.
点击复制

基于 WDCNN-LSTM 混合模型的滚动轴承故障诊断()
分享到：

《机械与电子》[ISSN:1001-2257/CN:52-1052/TH]

卷:
期数:
2025年02期
页码:
9-15
栏目:
研究与设计
出版日期:
2025-02-28

文章信息/Info

Title:
Fault Diagnosis of Rolling Bearing Based on WDCNN-LSTM Hybrid Model
文章编号:
1001-2257 ( 2025 ) 02-0009-07
作者:
陈 宇 1 ; 程道来 2 ; 马向华 3 ; 彭新开 4 ; 王建辉 4
1. 珠海科技学院智能制造与航空学院,广东 珠海 519040 ;?
2. 上海电子信息职业技术学院中德工程学院,上海 201411 ;?
3. 上海应用技术大学电气与电子工程学院,上海 201418 ;
4. 中数复新智能科技(上海)有限公司技术部,上海 201702
Author(s):
CHEN Yu1 ;  CHENG Daolai2 ;  MA Xianghua3 ;  PENG Xinkai4 ;  WANG Jianhui4
( 1.School of Intelligent Manufacturing and Aviation , Zhuhai College of Science and Technology , Zhuhai 519040 , China ;
2.School of Sino-German Engineering , Shanghai Technical Institute of Electronics and Information , Shanghai 201411 , China ;
3.School of Electrical and Electronic Engineering , Shanghai Institute of Technology , Shanghai 201418 , China ;
4.Technique Department , Zhongshu Fuxin Intelligent Technology ( Shanghai )Co. , Ltd. , Shanghai 201702 , China )
关键词:
卷积神经网络; 故障诊断; 长短期记忆网络; 滚动轴承
Keywords:
convolutional neural network ;  fault diagnosis ;  long short-term memory network ;  rolling bearing
分类号:
TH133.3
文献标志码:
A
摘要:
针对滚动轴承故障诊断过程中常忽略原始振动信号时间序列信息的问题,提出一种第 1 层为宽卷积核的深度卷积神经网络( WDCNN )与长短期记忆网络( LSTM )相结合的模型( WDCNN-LSTM ),用于滚动轴承故障诊断分类。首先,轴承故障的原始振动信号经过第 1 层宽卷积核提取特征信息和抑制噪声信息后,通过堆积多个小核函数提取获得更好的特征信息;然后,通过 LSTM 捕捉原始振动信号中的时间序列信息进一步提高模型的特征提取能力;最后,LSTM 将融合特征输入全连接层并通过 Softmax 函数输出轴承故障分类结果。实验结果表明, WDCNN-LSTM 模型能够较好利用原始振动信号中的时间序列信息,在不同的负载和噪声变化中仍具有较高的训练效率和识别率。
Abstract:
To solve the problem that the time series information of the original vibration signal is often ignored in the process of fault diagnosis of rolling bearings , a model ( WDCNN-LSTM ), which combines the deep convolutional neural network ( WDCNN ) with wide convolutional kernel at the first layer and long short-term memory network ( LSTM ), is proposed for fault diagnosis and classification of rolling bearings.Firstly , the original vibration signal of bearing fault is extracted by the first layer of wide convolution kernel , and the noise suppression information is extracted by stacking several small kernel functions to obtain better feature information.Then , LSTM captures the time series information of the original vibration signal to further improve the feature extraction capability of the model.Finally , LSTM inputs the fusion features into the fully connected layer and outputs the bearing fault classification results through Softmax function.The experimental results show that WDCNN-LSTM model can make better use of the time series information in the original vibration signal , and still has high training efficiency and recognition rate under different load and noise changes.

参考文献/References:

[ 1 ] ALI J B , FNAIECH N , SAIDI L , et al.Application of empirical mode decomposition and artificial neural network for automatic bearing fault diagnosis based on vibration signals [ J ] .Applied acoustics , 2015 , 89 :16-27.

[ 2 ] WANG X , MAO D X , LI X D.Bearing fault diagnosis based on vibro-acoustic data fusion and 1D-CNN network [ J ] .Measurement , 2021 , 173 : 108518.
[ 3 ] NANDI S , TOLIYAT H A , LI X.Condition monitoring and fault diagnosis of electrical motors : a review [ J ] .IEEE Transactions on energy conversion , 2005 , 20( 4 ): 719-729.
[ 4 ] 昝涛,王辉,刘智豪,等 . 基于多输入层卷积神经网络的滚动轴 承 故 障 诊 断 模 型 [ J ] . 振 动 与 冲 击, 2020 ,39 ( 12 ): 142-149 , 163.
[ 5 ] 金江涛,许子非,李春,等 . 基于卷积双向长短期记忆网络与混沌理论的滚动轴承故障诊断[ J ] . 振动与冲击,2022 , 41 ( 17 ): 160-169.
[ 6 ] WU S D , WU P H , WU C W , et al.Bearing fault diagnosis based on multiscale permutation entropy and support vector machine [ J ] .Entropy , 2012 , 14 ( 8 ): 1343-1356.
[ 7 ] CHEN X H , ZHANG B K , GAO D.Bearing fault diagnosis base on multi-scale CNN and LSTM model [ J ] .Journal of intelligent manufacturing , 2021 , 32 : 971-987.
[ 8 ] HE M , HE D.Deep learning based approach for bearing fault diagnosis [ J ] .IEEE Transactions on industry applications , 2017 , 53 ( 3 ): 3057-3065.
[ 9 ] 杜娟,刘志刚,宋考平,等 . 基于卷积神经网络的抽油机故障 诊 断 [ J ] . 电 子 科 技 大 学 学 报,2020 , 49 ( 5 ):751-757.
[ 10 ] 熊剑,邓松,时大方 . 基于改进残差网络的滚动轴承故障诊断[ J ] . 轴承, 2020 ( 11 ): 50-55.
[ 11 ] VIOLA J , CHEN Y Q , WANG J.FaultFace : deep convolutional generative adversarial network ( DCGAN ) based ball-bearing failure detection method [ J ] .Information sciences , 2021 , 542 : 195-211.
[ 12 ] 刘万宇,李宇鹏,石怀涛,等 . 基于 WDCNN-DLSTM的滚动 轴 承 故 障 诊 断 方 法 [ J ] . 科 学 技 术 与 工 程,2023 , 23 ( 13 ): 5522-5529.
[ 13 ] ZHANG A , LI S B , CUI Y X , et al.Limited data rolling bearing fault diagnosis with few-shot learning [ J ] .IEEE Access , 2019 , 7 : 110895-110904.
[ 14 ] FUAN W , JIANG H K , SHAO H D , et al.An adaptive deep convolutional neural network for rolling bearing fault diagnosis [ J ] .Measurement science and technology , 2017 , 28 ( 9 ): 095005.
[ 15 ] YANG X B , YANG H X , ZHANG F Q , et al.A random-weighted plane-Gaussian artificial neural network [ J ] .Neural computing and applications , 2019 , 31( 12 ): 8681-8692.
[ 16 ] 谢娟英,张建宇 . 图卷积神经网络综述[ J ] . 陕西师范大学学报(自然科学版),2024 , 52 ( 2 ): 89-101.
[ 17 ] ZHANG W , PENG G L , LI C H , et al.A new deep learning model for fault diagnosis with good anti noise and domain adaptation ability on raw vibration signals [ J ] .Sensors , 2017 , 17 ( 2 ): 425.
[ 18 ] 杜浩飞,张超,李建军 . 基于 SENet ResNext-LSTM的风机 轴承 故 障诊 断[ J ] . 机 械强 度,2023 , 45 ( 6 ):1271-1279.
[ 19 ] 陈保家,陈学力,沈保明,等 .CNN-LSTM 深度神经网络在滚动轴承故障诊断中的应用[ J ] . 西安交通大学学报,2021 , 55 ( 6 ): 28-36.
[ 20 ] 金海龙,马吴旭,孟宗,等 . 基于改进 1DCNN GRU的滚动 轴承 故 障诊 断[ J ] . 计 量学 报,2023 , 44 ( 9 ):1423-1428.
[ 21 ] 张弛 . 基于 CNN SVM 的滚动轴承故障诊断[ J ] . 组合机床与自动化加工技术,2021 ( 11 ): 114-116 , 124.
[ 22 ] SAFAEI M , BALOUCHIAN P , FOROOSH H.TICNN : a hierarchical deep learning framework for still image action recognition using ( ICIP ) .New York : IEEE , 2018 : 3463-3467.

相似文献/References:

[1]吕明珠１,２,苏晓明 １,等. 改进粒子群算法优化的支持向量机在滚动轴承故障诊断中的应用[J].机械与电子,2019,(01):42.
　,,et al.Application of SVM Optimized by IPSO in Rolling Bearing Fault Diagnosis[J].Machinery & Electronics,2019,(02):42.
[2]汪 伟,李 军,翟旭升,等.某型航空发动机中介主轴承早期微弱故障诊断研究[J].机械与电子,2019,(06):6.
　,,et al.Research on the Early Weak Fault Diagnosis of Aero-engine Intershaft Bearing[J].Machinery & Electronics,2019,(02):6.
[3]赵蕾,傅攀,胡龙飞,等.FOA-WPT降噪和PSO-SVM在滚动轴承故障诊断中的应用[J].机械与电子,2018,(12):3.
　ZHAO Lei,FU Pan,HU Longfei,et al.Applications of FOA-WPT and PSO-SVM in Faults Diagnosis of Rolling Bearing[J].Machinery & Electronics,2018,(02):3.
[4]吕明珠 苏晓明 陈长征 刘世勋.小波包能量熵与EMD结合分析法在风机滚动轴承故障诊断中的应用[J].机械与电子,2018,(06):8.
　LYU Mingzhu,SU Xingming,CHEN Changzheng,et al.Application of Wavelet Packet Energy Entropy and EMD Conjoint Analysis in Fault Diagnosis of Wind Turbine Bearing[J].Machinery & Electronics,2018,(02):8.
[5]王骁贤,张保华,陆思良.基于连续小波变换和卷积神经网络的无刷直流电机故障诊断[J].机械与电子,2018,(06):29.
　WANG Xiaoxian,ZHANG Baohua,LU Siliang.Fault Diagnosis of Brushless Direct Current Motor Based on Continuous Wavelet Transform and Convolutional Neural Network[J].Machinery & Electronics,2018,(02):29.
[6]刘志宇,黄亦翔.基于深度学习和迁移学习的液压泵健康评估方法[J].机械与电子,2018,(09):67.
　LIU Zhiyu,HUANG Yixiang.Health Assessment for Hydraulic Pump Based on Deep Learning and Transfer Learning[J].Machinery & Electronics,2018,(02):67.
[7]唐志宇,毛 兴,王路军.电力变压器绕组变形检测技术研究[J].机械与电子,2018,(11):53.
　TANG Zhiyu,MAO Xing,WANG Lujun.Research on Power Transformer Winding Deformation Detection Technology[J].Machinery & Electronics,2018,(02):53.
[8]杨伟力,于阳阳,罗达灿.基于小波包和PSO-Elman神经网络的滚动轴承故障诊断[J].机械与电子,2016,(05):13.
　YANG Weili,YU Yangyang,LUO Dacan.Rolling Bearing Fault Diagnosis Using Wavelet Packet Analysis and PSO-Elman Neural Network[J].Machinery & Electronics,2016,(02):13.
[9]曾雪琼,黎杰.基于卷积神经网络的时频图像识别研究[J].机械与电子,2016,(05):25.
　ZENG Xueqiong,LI Jie.Time-frequency Image Recognition Based on Convolutional Neural Network[J].Machinery & Electronics,2016,(02):25.
[10]袁小凯,李 果,蒋屹新,等.基于 ＨＳ- ＥＬＭ 的油浸式变压器故障诊断[J].机械与电子,2019,(12):30.
　,,et al.Fault Diagnosis of Oil Immersion Transformer Based on HS-ELM Algorithm[J].Machinery & Electronics,2019,(02):30.
[11]齐爱玲１,李 琳１,朱亦轩２,等.基于融合特征的双通道CNN滚动轴承故障识别[J].机械与电子,2021,(05):15.
　QI Ailing,LI Lin,ZHU Yixuan,et al.Dual Channel CNN Bearing Fault Identification Based on Fusion Feature[J].Machinery & Electronics,2021,(02):15.
[12]杨永灿,刘 韬,柳小勤,等.基于注意力机制的一维卷积神经网络行星齿轮箱故障诊断[J].机械与电子,2021,(10):3.
　YANG Yongcan,LIU Tao,LIU Xiaoqin,et al.Fault Diagnosis of Planetary Gearbox Based on One-dimensional Convolutional Neural Network with Attention Mechanism[J].Machinery & Electronics,2021,(02):3.
[13]王浏洋,徐彦伟,等.基于优化 CNN 与信息融合的地铁牵引电机轴承故障诊断[J].机械与电子,2023,41(08):39.
　WANG Liuyang,XU Yanwei,XIE Tancheng,et al.Fault Diagnosis of Metro Traction Motor Bearing Based on Optimized CNN and Information Fusion[J].Machinery & Electronics,2023,41(02):39.
[14]李 斌,张 砦,李泓锟.基于 MSAWPD-CNN 的行星齿轮箱端到端故障诊断研究[J].机械与电子,2025,(07):74.
　LI Bin,ZHANG Zhai,LI Hongkun.Research on End-to-end Fault Diagnosis of Planetary Gearbox Utilizing MSAWPD-CNN[J].Machinery & Electronics,2025,(02):74.

备注/Memo

备注/Memo:
收稿日期: 2024-07-23
基金项目:国家重点研发计划项目( 2020YFB2007700 )
作者简介:陈 宇 ( 1998- ),男,广西陆川人,硕士研究生,助教,研究方向为动力机械及工程;程道来 ( 1965- ),男,湖南常德人,博士,教授,研究方向为动力机械及工程、噪声与振动控制、机械故障诊断等,通信作者。
更新日期/Last Update: 2025-03-10