浏览全部资源
扫码关注微信
太原科技大学 机械工程学院, 山西 太原 030024
杜康宁(1994— ),男,山西朔州人,硕士;研究方向为轴承故障诊断;2843044851@qq.com。
宁少慧(1978— ),女,山西运城人,博士,副教授;研究方向为机械设备状态监测与故障诊断;ningshaohui@tyust.edu.cn。
纸质出版日期:2023-07-15,
收稿日期:2022-05-09,
修回日期:2022-07-06,
扫 描 看 全 文
杜康宁,宁少慧.基于二次迁移学习和EfficientNetV2的滚动轴承故障诊断[J].机械传动,2023,47(07):168-176.
Du Kangning,Ning Shaohui.Fault Diagnosis of Rolling Bearings Based on Two-step Transfer Learning and EfficientNetV2[J].Journal of Mechanical Transmission,2023,47(07):168-176.
杜康宁,宁少慧.基于二次迁移学习和EfficientNetV2的滚动轴承故障诊断[J].机械传动,2023,47(07):168-176. DOI: 10.16578/j.issn.1004.2539.2023.07.024.
Du Kangning,Ning Shaohui.Fault Diagnosis of Rolling Bearings Based on Two-step Transfer Learning and EfficientNetV2[J].Journal of Mechanical Transmission,2023,47(07):168-176. DOI: 10.16578/j.issn.1004.2539.2023.07.024.
针对工程实际故障诊断环境下,可用数据稀缺,导致智能诊断模型对轴承健康状态识别精度较低这一问题,提出一种基于二次迁移学习和EfficientNetV2(Two-Step Transfer of EfficientNetV2,TSTE)的滚动轴承故障诊断新方法。首先,将模型在轴承全寿命周期数据集中训练,之后冻结模型浅层权重,将其在多工况轴承数据集中训练,进行第一次迁移学习。其次,通过构造类不平衡数据集,研究实际故障环境下可用数据稀缺对故障诊断性能的影响。然后,基于合成少数类过采样技术(Synthetic Minority Oversampling Technique,SMOTE)过采样方法与编辑最近邻(Edited Nearest Neighbors,ENN)欠采样方法对故障数据进行扩充,使类不平衡数据集重构为类平衡数据集。最后,将模型在类平衡数据集中训练,冻结模型底层权重,训练模型深层,进行第二次迁移学习,使模型掌握平衡数据集故障特征。通过多种指标进行实验评估,同时与其他方法进行对比,并使用Grad-CAM方法进行了特征可视化。结果表明,所提方法能够将模型在实验室环境下积累的故障诊断知识应用于实际工程设备,适用于检测数据稀缺情形下的滚动轴承故障诊断。
A rolling bearing fault diagnosis model based on two-step transfer learning and EfficientNetV2 (TSTE) is proposed for the real fault diagnosis environment in engineering
where the scarcity of available data leads to the low accuracy of the intelligent diagnosis model in bearing health status diagnosis. Firstly
the model is trained on the full life time bearing data set and then the model shallow weights are freezed to train it on the multi-condition bearing data set for the first transfer learning. Secondly
by constructing a class-imbalance dataset
the impact of scarcity of available data on fault diagnosis performance is studied in actual fault environments is studied. Then
the synthetic minority oversampling technique (SMOTE) oversampling method and the edited nearest neighbors (ENN) under the sampling method are proposed to expand the fault data
reconstructing the class-imbalanced dataset into a class-balanced dataset. Finally
the model is trained on the class-balanced dataset
freezing the model's bottom weights and training the model deeper for a second transfer learning
enabling the model to take control of the failure characteristics of the balanced dataset. The experiments are evaluated by a variety of metrics
while comparing it with other methods
and using the Grad-CAM method for feature visualization. The results show that the proposed method is able to transfer the fault diagnosis knowledge accumulated by the model in a laboratory environment to actual engineering equipment. It is suitable for the diagnosis of rolling bearing faults in situations where test data is scarce.
滚动轴承二次迁移学习EfficientNetV2神经网络类不平衡重采样
Rolling bearingTwo-step transfer learningEfficientNetV2Class-imbalanceResample
李华,刘韬,伍星,等.相关奇异值比的SVD在轴承故障诊断中的应用[J].机械工程学报,2021,57(21):138-149.
LI Hua,LIU Tao,WU Xing,et al.Application of SVD based on correlated singular value ratio in bearing fault diagnosis[J].Journal of Mechanical Engineering,2021,57(21):138-149.
程兴国,翁璞.基于自学习字典的盲提取方法在滚动轴承多故障诊断中的应用[J].机械传动,2022,46(2):149-154.
CHENG Xingguo,WENG Pu.A blind source extraction method based on self-learned dictionary and its application in fault diagnosis of bearing multi-type fault[J].Journal of Mechanical Transmission,2022,46(2):149-154.
雷亚国,杨彬,李乃鹏,等.跨设备的机械故障靶向迁移诊断方法[J].机械工程学报,2022,58(12):1-9.
LEI Yaguo,YANG Bin,LI Naipeng,et al.Targeted transfer diagnosis method across different machines[J].Journal of Mechanical Engineering,2022,58(12):1-9.
苗宝权,陈长征,罗园庆,等.基于自适应增强差分积形态滤波器的滚动轴承故障特征提取方法[J].机械工程学报,2021,57(9):78-88.
MIAO Baoquan,CHEN Changzheng,LUO Yuanqing,et al.Rolling bearing fault feature extraction method based on adaptive enhanced difference product morphological filter[J].Journal of Mechanical Engineering,2021,57(9):78-88.
韩涛,袁建虎,唐建,等.基于MWT和CNN的滚动轴承智能复合故障诊断方法[J].机械传动,2016,40(12):139-143.
HAN Tao,YUAN Jianhu,TANG Jian,et al.An approach of intelligent compound fault diagnosis of rolling bearing based on MWT and CNN[J].Journal of Mechanical Transmission,2016,40(12):139-143.
叶楠,常佩泽,张露予,等.基于改进后半监督深度信念网络的多工况轴承故障诊断研究[J].机械工程学报,2021,57(15):80-90.
YE Nan,CHANG Peize,ZHANG Luyu,et al.Research on multi-condition bearing fault diagnosis based on improved semi-supervised deep belief network[J].Journal of Mechanical Engineering,2021,57(15):80-90.
ZHAO B,ZHANG X,ZHAN Z,et al.Deep multi-scale convolutional transfer learning network:a novel method for intelligent fault diagnosis of rolling bearings under variable working conditions and domains[J].Neurocomputing,2020,407:24-38.
吴定会,方钦,吴楚宜.基于数据生成与迁移学习的轴承小样本故障诊断[J].机械传动,2020,44(11):139-144.
WU Dinghui,FANG Qin,WU Chuyi.Bearing small sample fault diagnosis based on data generation and transfer learning[J].Journal of Mechanical Transmission,2020,44(11):139-144.
张楷,罗怡澜,邹益胜,等.高速列车的样本关联改进故障诊断方法[J].中国机械工程,2018,29(2):151-157.
ZHANG Kai,LUO Yilan,ZOU Yisheng,et al.Sample correlation improvement based high speed train fault diagnosis method[J].China Mechanical Engineering,2018,29(2):151-157.
何强,唐向红,李传江,等.负载不平衡下小样本数据的轴承故障诊断[J].中国机械工程,2021,32(10):1164-1171.
HE Qiang,TANG Xianghong,LI Chuanjiang,et al.Bearing fault diagnosis method based on small sample data under unbalanced loads[J].China Mechanical Engineering,2021,32(10):1164-1171.
雷亚国,杨彬,杜兆钧,等.大数据下机械装备故障的深度迁移诊断方法[J].机械工程学报,2019,55(7):1-8.
LEI Yaguo,YANG Bin,DU Zhaojun,et al.Deep transfer diagnosis method for machinery in big data era[J].Journal of Mechanical Engineering,2019,55(7):1-8.
WANG B,LEI Y,LI N,et al.A hybrid prognostics approach for estimating remaining useful life of rolling element bearings[J].IEEE Transactions on Reliability,2020,69(1):401-412.
DOSOVITSKIY A,BEYER L,KOLESNIKOV A,et al.An image is worth 16<math id="M82"><mo>×</mo></math>http://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=45810572&type=http://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=45810569&type=1.354666712.0320000616 words:transformers for image recognition at scale[C]//International Conference on Learning Representation,2021:11929.
LIU Z,LIN Y T,CAO Y,et al.Swin transformer:hierarchical vision transformer using shifted windows[J].ArXiv e-prints,2021:2103.14030.
刘俊锋,俞翔,万海波,等.基于MFMD和Transformer-CNN的滚动轴承故障诊断方法[J/OL].航空动力学报:1-11[2022-07-05].https://doi.org/10.13224/j.cnki.jasp.20210709https://doi.org/10.13224/j.cnki.jasp.20210709.
LIU Junfeng,YU Xiang,WAN Haibo,et al.Fault diagnosis method of rolling bearing using MFMD and Transformer-CNN[J/OL].Journal of Aerospace Power:1-11[2022-07-05].https://doi.org/10.13224/j.cnki.jasp.20210709https://doi.org/10.13224/j.cnki.jasp.20210709.
0
浏览量
21
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构