基于一维RepVGG协同领域自适应的电机滚动轴承故障诊断

微特电机 ›› 2023, Vol. 51 ›› Issue (4): 1-7.

• 理论研究 • 下一篇

基于一维RepVGG协同领域自适应的电机滚动轴承故障诊断

周涛, 罗响, 朱莉

上海交通大学电子信息与电气工程学院,上海 200240

收稿日期:2022-11-21 出版日期:2023-04-28 发布日期:2023-04-25
通讯作者: 罗响,男,博士,助理研究员,研究方向为电机控制及设计,无位置传感器控制理论研究,全海深水下电力推进系统。
作者简介:周涛(1999—),男,硕士研究生,研究方向为电机轴承故障诊断算法。朱莉,女,博士,副教授,研究方向为电机性能分析优化,特种电机的设计与控制。

Motor Rolling Bearings Fault Diagnosis Based on One-dimensional RepVGG and Domain Adaptation

ZHOU Tao, LUO Xiang, ZHU Li

School of Electric Information and Electrical Engineering, Shanghai Jiaotong University,Shanghai 200240, China

Received:2022-11-21 Online:2023-04-28 Published:2023-04-25

摘要/Abstract

摘要： 在使用传统机器学习类方法对电机滚动轴承故障进行诊断时,电机运行工况的变化以及采集信号时的噪声干扰,会出现源域训练集和目标域测试集分布不一致的问题。提出了基于一维RepVGG协同领域自适应的故障诊断方法。RepVGG具有精度高和速度快的特点,使用一维RepVGG实现对电机滚动轴承信号的特征提取;基于提取的特征,在网络顶层结构中使用集成优化目标函数来实现域自适应,并完成轴承故障诊断。基于凯斯西储大学轴承数据集,对该方法进行了实验验证。实验结果表明,在电机变工况运行时,改进方法为诊断性能优于现有其他诊断方法。

关键词: 电机滚动轴承, 故障诊断, 一维RepVGG, 领域自适应, 变工况

Abstract: When traditional machine learning method is used to diagnose motor rolling bearings faults, the distribution of source domain and target domain is inconsistent, due to the change of operating conditions and the noisy signal. The fault diagnosis method, based on one-dimensional re-parameterization Visual Geometry Group (RepVGG) and domain adaptation, was proposed. RepVGG had the characteristics of high precision and fast speed, which was convenient for model deployment and acceleration.One-dimensional RepVGG was used to extract the features of signals. The method used the integrated optimization objective function in the top-level structure of the network to achieve domain adaptation and the fault diagnosis of motor rolling bearings. Based on the bearing dataset of Case Western Reserve University, the experimental results show that the improved method has better diagnostic performance than other existing diagnostic methods when the motor runs under variable conditions.

Key words: motor rolling bearings, fault diagnosis, one-dimensional RepVGG, domain adaptation, variable conditions

中图分类号:

TM307+.1

周涛, 罗响, 朱莉. 基于一维RepVGG协同领域自适应的电机滚动轴承故障诊断[J]. 微特电机, 2023, 51(4): 1-7.

ZHOU Tao, LUO Xiang, ZHU Li. Motor Rolling Bearings Fault Diagnosis Based on One-dimensional RepVGG and Domain Adaptation[J]. Small & Special Electrical Machines, 2023, 51(4): 1-7.

参考文献

[1] 刘吉臻,王庆华,房方,等.数据驱动下的智能发电系统应用架构及关键技术[J].中国电机工程学报,2019,39(12):3578-3587.
[2] SUN C,ZHANG Z,HE Z,et al.Manifold learning-based subspace distance for machinery damage assessment[J].Mechanical Systems and Singal Processing,2016(3):637-649.
[3] 宋向金,赵文祥.交流电机信号特征分析的滚动轴承故障诊断方法综述[J].中国电机工程学报,2022,42(4):1582-1596.
[4] ZHANG Q,ZHAO Z ,ZHANG X,et al.Conditional adversarial domain generalization with a single discriminator for bearing fault diagnosis[J].IEEE Transactions on Instrumentation and Measurement,2021(70):1-15.
[5] 王崇宇,郑召利,刘天源,等.基于卷积神经网络的汽轮机转子不平衡与不对中故障检测方法研究[J].中国电机工程学报,2021,41(7):2417-2427.
[6] 袁建虎,韩涛,唐建,等.基于小波时频图和CNN的滚动轴承智能故障诊断方法[J].机械设计与研究,2017,33(2):93-97.
[7] JIA F,LEI Y.Deep normalized convolutional neural network for imbalanced fault classification of machinery and its understanding via visualization[J].Mechanical Systems and Signal Processing,2018(110):349-367.
[8] 王玉静,吕海岩,康守强,等.不同型号滚动轴承故障诊断方法[J].中国电机工程学报,2021,41(1):267-276,416.
[9] 梁丽冰.基于卷积神经网络滚动轴承故障诊断建模方法研究[D].北京:北京化工大学,2021.
[10] 褚若波,张认成,杨凯,等.基于多层卷积神经网络的串联电弧故障检测方法[J].电网技术,2020,44(12):4792-4798.
[11] 张根保 ,李浩 ,冉琰,等.一种用于轴承故障诊断的迁移学习模型[J].吉林大学学报(工学版),2020,50(5):1617-1626.
[12] WEN L,LI X,GAO L.A transfer convolutional neural network for fault diagnosis based on ResNet-50[J].Neural Computing & Applications,2020,32(10):6111-6124.
[13] HUANG X,SHANG E,XUE J,et al.A multi-feature fusion-based deep learning for insulator image identification and fault detection[C]//2020 IEEE 4th Information Technology,Networking,Electronic and Automation Control Conference,2020:1957-1960.
[14] NERGIZ M.Analysis of RepVGG on small sized dandelion images dataset in terms of transfer learning,regularization,spatial attention as well as squeeze and excitation blocks[C]// 6th International Conference on Computer Science and Engineering,2021:378-382.
[15] 侯东晓,穆金涛,方成,等.基于GADF与引入迁移学习的ResNet34对变速轴承的故障诊断[J].东北大学学报(自然科学版),2022,43(3):383-389.
[16] 董绍江,朱朋,裴雪武,等.基于子领域自适应的变工况下滚动轴承故障诊断[J].吉林大学学报(工学版),2022 ,52(2):288-295.
[17] 曹洁,尹浩楠,雷晓刚,等.基于领域自适应的变工况轴承故障诊断[J/OL].北京航空航天大学学报:1-13 [2022-11-16].https://doi.org/10.13700/j.bh.1001-5965.2022.0631.
[18] LI X,ZHANG W,DING Q.A robust intelligent fault diagnosis method for rolling element bearings based on deep distance metric learning[J].Neurocomputing,2018(310):77-95.
[19] DING X,ZHANG X,MA N,et al.RepVGG:Making VGG-Style convnets great again[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).Kuala Lumpur,Malaysia:IEEE,2021(1):13728-13737.
[20] WEINBERGER K,SAUL L.Distance metric learning for large margin nearest neighbor classification[J]. Journal of Machine Learning Research,2009(10):207-244.
[21] GLOBERSON A,ROWEIS S.Metric learning by collapsing classes[C]//Proceedings of the Eighteenth International Conference on Neural Information Processing Systems,2005(1):451-458.
[22] DENG J,DONG W,SOCHER R,et al.Imagenet:a large-scale hierarchical image database[C]//IEEE-Computer-Society Conference on Computer Vision and Pattern Recognition Workshops,2009:248-255.
[23] ZHU Y,ZHUANG F,WANG J,et al.Deep subdomain adaptation network for image classification[J].IEEE Transactions on Neural Networks and Learning Systems.2020,32(4):1713-1722.
[24] GRETTON A,BORGWARD K M,RASCH M J,et al.A kernel two-sample test[J].Journal of Machine Learning Research,2012(13):723-773.
[25] 顾晓辉,杨绍普,刘永强,等.基于多目标交叉熵优化的轮对轴承故障特征提取方法[J].机械工程学报,2018,54(4):285-292.

基于一维RepVGG协同领域自适应的电机滚动轴承故障诊断

Motor Rolling Bearings Fault Diagnosis Based on One-dimensional RepVGG and Domain Adaptation

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 13

编辑推荐

Metrics

本文评价

联系我们

[1]	陈其. 改进GAN结合SDAE的传动系统主轴承故障诊断[J]. 微特电机, 2023, 51(2): 20-25.
[2]	汤成, 张懿, 魏海峰, 周啸伟, 丁伟. 基于EEMD和HHT的低压异步电动机故障诊断[J]. 微特电机, 2021, 49(7): 44-49.
[3]	赵乾麟, 赵屹, 方炳平, 游张平. 异步电动机故障仿真与诊断研究[J]. 微特电机, 2021, 49(6): 58-60.
[4]	刘力宇, 崔江. 基于深度学习的发电机整流器诊断系统研究[J]. 微特电机, 2020, 48(4): 39-42.
[5]	李楷然, 刘永强, 吴立泉, 梁兆文. 一种感应电机转子断条故障建模方法[J]. 微特电机, 2020, 48(3): 33-37.
[6]	孙晟桐, 刘剑, 宋吉江, 徐飞, 谭芳堃. 基于电流残差矢量的逆变器开路故障诊断[J]. 微特电机, 2019, 47(8): 35-40.
[7]	姬相磊, 高旭东, 杜振东. 风力发电机轴承振动监测故障诊断分析[J]. 微特电机, 2019, 47(8): 74-76.
[8]	吴文军, 张晋瑞, 尚仪. 负载波动下感应电动机转子断条故障诊断[J]. 微特电机, 2019, 47(6): 31-36.
[9]	. 粒子群优化融合随机森林的电机故障诊断方法[J]. 微特电机, 2019, 47(10): 42-45.
[10]	支康仪,武登云,史永丽. BLDCM霍尔位置传感器信号故障诊断及重构[J]. 微特电机, 2019, 47(1): 12-16.
[11]	柴永利,王炜,何卫国. 一种无刷直流电动机故障诊断方法研究[J]. 微特电机, 2018, 46(6): 49-52.
[12]	王炜, 钟书辉. 基于RBF神经网络的无刷直流电动机故障诊断[J]. 微特电机, 2018, 46(5): 44-47.
[13]	郑晓亮, 高佳华, 李飞龙. 基于谐波分析的异步电动机故障诊断研究[J]. 微特电机, 2018, 46(12): 34-37.