[1]杨 云,王越寒,丁 磊,等.基于CWT-MDFA 的轴承故障诊断方法[J].机械与电子,2026,44(04):40-46.
　YANG Yun,WANG Yuehan,DING Lei,et al.Bearing Fault Diagnosis Method Based on DSCNN-Transforme[J].Machinery & Electronics,2026,44(04):40-46.
点击复制

基于CWT-MDFA 的轴承故障诊断方法()
分享到：

《机械与电子》[ISSN:1001-2257/CN:52-1052/TH]

卷:
44
期数:
2026年04期
页码:
40-46
栏目:
智能检测
出版日期:
2026-04-27

文章信息/Info

Title:
Bearing Fault Diagnosis Method Based on DSCNN-Transforme
文章编号:
1001-2257(2026)04-0040-07
作者:
杨 云1; 王越寒1; 丁 磊2; 陈 磊1
(1.华东交通大学电气与自动化工程学院,江西 南昌 330013;
2.中国铁路广州局集团有限公司中国长沙车辆段,湖南 长沙 410007)
Author(s):
YANG Yun1; WANG Yuehan1 ; DING Lei2; CHEN Lei1
(1.School of Electrical and Automation Engineering,East China Jiaotong University,Nanchang 330013,China;
2.Changsha Vehicle Depot,China Railway Guangzhou Group Co.,Ltd.,Changsha 410007,China)
关键词:
小波变换; 多尺度空洞卷积; 注意力机制; 故障诊断; 鲁棒性
Keywords:
wavelet transform;  multi scale dilated convolution;  attention mechanism;  fault diagnosis; robustness
分类号:
TH133.3;TP18
文献标志码:
A
摘要:
针对滚动轴承早期故障信号微弱、复杂特征难以全面捕捉,以及传统故障诊断方法存在特征提
取有限和故障检测准确率不高的问题,提出一种基于小波变换与多尺度空洞卷积轴承故障诊断方法。对原
始一维振动信号进行小波变换,经过小波函数转换成二维时频图。再构建改进的多尺度空洞卷积网络用于
增大神经网络感受视野,缓解特征提取时可能导致局部信息缺失的问题,并引入空间和通道注意力机制,应
对同一故障类型下不同损伤尺度时频图的敏感度问题。在CWRU 和JNU 轴承数据集上进行实验验证,并
在东南大学轴承数据集进行泛化实验。实验结果表明,所提方法能够准确分类轴承在不同故障状态的信
息,准确率可达99.07%,具有良好的泛化性和鲁棒性。
Abstract:
In response to the difficulty in capturing complex features of weak early fault signals in rolling
bearings comprehensively,and the limitations of traditional fault diagnosis methods,such as constrained
feature extraction and suboptimal fault detection accuracy,a new intelligent fault diagnosis method for
bearings is proposed,which is based on wavelet transform and multi scale dilated convolution for bearing
fault diagnosis. The original one dimensional vibration signals are converted into two dimensional time
frequency representations via wavelet transform using a wavelet function.An improved multi scale dilated
convolutional network is then constructed to enlarge the receptive field of the neural network,mitigating
the potential loss of local information during feature extraction.Additionally,spatial and channel attention
mechanisms are introduced to address sensitivity issues in time frequency representations under different
damage severities of the same fault type.Experimental validations are conducted on the CWRU and JNU
bearing datasets,and the generalization experiments are performed on the Southeast University bearing
dataset.The results show that the proposed method can accurately identify operational information of bearings
under different fault conditions and severity levels,achieving an accuracy of up to 99.07%,and exhibits
strong generalization capability and robustness.

参考文献/References:

[1] 周健,万烂军,罗海霞.基于域泛化的旋转机械故障诊断方法[J].组合机床与自动化加工技术,2025(1):127 131.
[2] 王瀚卿.基于LSTM 网络的滚动轴承寿命预测方法[D].西安:西安理工大学,2024.
[3] 赵志宏,陶旭,武超.基于局部描述子的小样本轴承故障诊断方法[J].铁道辆,2024,62(5):23 29.
[4] 寇梓良,张西宁,李兵,等.基于多模态数据融合与改进CNN的轴承故障诊断[J].振动、测试与诊断,2025,45
(6):1082 1089.
[5] 李学艺,王相凯,黄金凤,等.基于双通道信号驱动的CA Transformer轴承故障诊断方法[J].组合机床与
自动化加工技术,2025(7):121 127.
[6] ROSTAGHI M,KHATIB I,ASHORY M R,et al.Bearing fault diagnosis using refined composite generalized
multiscale dispersion entropy based skewness and variance and multiclass FCM ANFIS[J].Entropy,
2021,23(11):1510 1510.
[7] 杨兴宽,孙祯,周素霞,等.基于LLE TVF 和PE MOMEDA的货车轴承复合故障诊断方法[J].振动与
冲击,2024,43(23):56 65.
[8] 徐科繁,刘喆,姜海燕,等.基于振动和声发射的滚动轴承故障诊断技术[J].热能动力工程,2022,37(12):157 164.
[9] 方东亮,卓识,战利伟,等.基于CWT AT CNN的航空轴承故障诊断[J].轴承,2025(9):101 108.
[10] 周煊淇,苌道方,满星妤,等.基于零样本相关判别空间适应的船舶轴系故障诊断[J/OL].上海交通大学
学报,2025:1 20[2025 10 20].https://doi.org/10.16183/j.cnki.jsjtu.2025.067.
[11] 欧阳承达,齐铁臣,李善吉,等.实际工况下基于元学习算法的轴承故障诊断[J].轴承,2025(7):104 109.
[12] 苏泓臣,杨辰昕,边豪杰,等.基于自适应经验小波变换的轴承故障诊断研究[J].核科学与工程,2025,45
(3):510 518.
[13] 汪小虎,赵荣珍,邓林峰,等.基于多尺度空洞卷积神经网络的滚动轴承故障识别方法[J].兰州理工大学
学报,2025,51(3):161 169.
[14] LIU Q,LAI H X,WEN B,et al.A novel method of bearing fault diagnosis for train Bogie transmission
system based on MpResCNN BiLSTM model with attention mechanism[J].IEEE Transactions on intelligent
transportation systems,2025,26 (12):12890 12902.
[15] TANG H H,TANG Y M,SU Y X,et al.Feature extraction of multi sensors for early bearing fault diagnosis
using deep learning based on minimum unscented Kalman filter[J].Engineering applications of artificial
intelligence,2024,127:107138.
[16] 薛卓,和丹,倪泽行,等.ACCDMF在滚动轴承故障诊断中应用研究[J].噪声与振动控制,2025,45(6):
176 182.
[17] FAN C Z,ZHANG Y C,MA H,et al.A novel lightweight DDPM based data augmentation method for
rotating machinery fault diagnosis with small sample [J].Mechanical systems and signal processing,2025,
232:112741.
[18] 张继旺,丁克勤,王洪柱.基于VMD CNN 的滚动轴承早期微弱故障智能诊断方法[J].组合机床与自动
化加工技术,2020(11):15 19.

相似文献/References:

[1]贾勇,马戎,李岁劳.MEMS陀螺零偏温度补偿[J].机械与电子,2019,(03):18.
　JIA Yong,MA Rong,LI Suilao. Bias Temperature Compensation Method of MEMS Gyroscope [J].Machinery & Electronics,2019,(04):18.
[2]邹左明,刘丛志.基于FFT和DWT的柴油发电机电网谐波分析[J].机械与电子,2016,(06):16.
　ZOU Zuoming,LIU Congzhi.Harmonic Analysis of the Diesel Generator Power System Based on FFT and DWT[J].Machinery & Electronics,2016,(04):16.
[3]孙 佩,胡小敏.基于图像特征提取的地铁客流量自动统计系统[J].机械与电子,2020,(10):17.
　SUN Pei,HU Xiaomin.Metro Passenger Flow Statistics System Based on Image Feature Extraction[J].Machinery & Electronics,2020,(04):17.
[4]杜绪伟,陈 东.低比度钢板微小缺陷的图像增强和分割[J].机械与电子,2020,(12):65.
　DU Xuwei,CHEN Dong.Image Enhancement and Segmentation of Small Defects in Low Contrast Steel Plate[J].Machinery & Electronics,2020,(04):65.
[5]王建国,张明杰,李冠华.煤矿机械设备传动齿轮故障信号检测方法[J].机械与电子,2023,41(06):31.
　WANG Jianguo,ZHANG Mingjie,LI Guanhua.Detection Method of Fault Signal of Transmission Gear of Coal Mine Machinery and Equipment[J].Machinery & Electronics,2023,41(04):31.
[6]苏万斌,吕焕培,吴民忠,等.基于轴承热通量的高速电梯曳引机主轴智能监测方法研究[J].机械与电子,2025,(12):72.
　SU Wanbin,LYU Huanpei,WU Minzhong,et al.Study on Intelligent Monitoring Method for Main Shaft of High-speed Elevator Traction Machine Based on Bearing Heat Flux[J].Machinery & Electronics,2025,(04):72.
[7]张思思,滑文强. 基于时频双域协同与语义增强的复杂水域漂浮物检测方法[J].机械与电子,2026,44(03):47.
　ZHANG Sisi,HUA Wenqiang. A Dual-domain Synergistic and Semantically Enhanced Method for Floating Object Detection in Complex Water Environments[J].Machinery & Electronics,2026,44(04):47.

备注/Memo

备注/Memo:
收稿日期:2025-10-08
基金项目:国家自然科学基金资助项目(52267015)
作者简介:杨 云 (1972-),男,江苏徐州人,高级实验师,研究方向为故障诊断、检测技术及自动化;王越寒 (1999-),男,江西九江
人,硕士研究生,研究方向为故障诊断技术。
更新日期/Last Update: 2026-05-11