基于AFF-Stablenet模型的小样本轴承故障诊断*

doi:10.16731/j.cnki.1671-3133.2024.09.019

现代制造工程 ›› 2024, Vol. 528 ›› Issue (9): 144-151.doi: 10.16731/j.cnki.1671-3133.2024.09.019

• 设备设计/诊断维修/再制造 • 上一篇下一篇

基于AFF-Stablenet模型的小样本轴承故障诊断^*

郭康^1,2, 王志刚^1,2, 徐增丙^1,2

1 武汉科技大学机械自动化学院,武汉 430081;
2 武汉科技大学冶金装备及其控制教育部重点实验室,武汉 430081

收稿日期:2024-01-16 出版日期:2024-09-18 发布日期:2024-09-27
通讯作者: 徐增丙,博士,硕士生导师,主要研究方向为机器视觉、故障诊断和模式识别。 E-mail:guokang_2024@163.com
作者简介:郭康,硕士研究生,主要研究方向为故障诊断。
基金资助:
^*国家自然科学基金项目(51775391)

Fault diagnosis of small sample bearings based on the AFF-Stablenet model

GUO Kang^1,2, WANG Zhigang^1,2, XU Zengbing^1,2

1 School of Mechanical Automation,Wuhan University of Science and Technology,Wuhan 430081,China;
2 Key Laboratory of Metallurgical Equipment and Control,Ministry of Education, Wuhan University of Science and Technology,Wuhan 430081,China

Received:2024-01-16 Online:2024-09-18 Published:2024-09-27

摘要/Abstract

摘要： 针对滚动轴承在小样本条件下诊断准确率低和泛化性弱的问题,提出了一种基于注意力特征融合的深度稳定学习(Attention Feature Fusion and Deep Stable Learning,AFF-Stablenet)模型的故障诊断方法。该方法首先使用经验模态分解(Empirical Mode Decompositim,EMD)将样本分解成多段频率的子信号,求取子信号与原始信号的互相关系数,选择系数较高的前三阶子信号;利用连续小波变换(Continuws Narelet Transorm,CWT)将子信号转换为时频图表示,通过注意力特征融合的方式将这些时频图特征进行融合;最后将融合特征输入到深度稳定学习(Stablenet)模型进行训练与预测。为验证模型的有效性,采用凯斯西储大学轴承数据集进行各组对比试验,都灵理工大学轴承数据集进行验证。实验结果表明,AFF-Stablenet模型在小样本情况下的泛化性和鲁棒性均强于其他对比模型,证明了模型的优越性。

关键词: 注意特征融合, 深度稳定学习, 滚动轴承, 小样本, 故障诊断

Abstract: A fault diagnosis method based on the AFF-Stablenet model is proposed to address the issues of low diagnostic accuracy and weak generalization of rolling bearings under small sample conditions.Initially,the samples are decomposed into sub-signals of multiple frequencies using EMD. The cross-correlation coefficients between the sub-signals and the original signal are computed. The top three sub-signals with higher coefficients are selected.These sub-signals are transformed into time-frequency representations using CWT. Through attention-based feature fusion,the time-frequency features are integrated.Finally,the fused features are input into the Stablenet model for training and prediction. To validate the effectiveness of the proposed model,comparative experiments are conducted using the Case Western Reserve University bearing dataset and verified using the Politecnico di Torino bearing dataset. Experimental results demonstrate that the AFF-Stablenet model exhibits superior generalization and robustness under small sample conditions compared to other models,affirming the superiority of the proposed approach.

Key words: pay attention to feature fusion, deep and stable learning, rolling bearing, small samples, fault diagnosis

中图分类号:

郭康, 王志刚, 徐增丙. 基于AFF-Stablenet模型的小样本轴承故障诊断^*[J]. 现代制造工程, 2024, 528(9): 144-151.

GUO Kang, WANG Zhigang, XU Zengbing. Fault diagnosis of small sample bearings based on the AFF-Stablenet model[J]. Modern Manufacturing Engineering, 2024, 528(9): 144-151.

参考文献

[1] HUANG D,FU Y,QIN N,et al.Fault diagnosis of high-speed train bogie based on LSTM neural network[J].Sci.Chin.Inf.Sci,2021,64:1-3.
[2] WANG Z,DONG Y,LIU W,et al.A novel fault diagnosis approach for chillers based on 1-D convolutional neural network and gated recurrent unit[J].Sensors,2020,20(9):2458.
[3] WANG X,MAO D,LI X.Bearing fault diagnosis based on vibro-acoustic data fusion and 1D-CNN network[J].Measurement,2021,173:108518.
[4] LI J,LI X,HE D,et al.Unsupervised rotating machinery fault diagnosis method based on integrated SAE-DBN and a binary processor[J].Journal of Intelligent Manufacturing,2020,31(8):1-18.
[5] LI X,ZHANG W,DING Q,et al.Intelligent rotating machinery fault diagnosis based on deep learning using data augmentation[J].Journal of Intelligent Manufacturing,2020,31:433-452.
[6] ZHOU K,DIEHL E,TANG J.Deep convolutional generative adversarial network with semi-supervised learning enabled physics elucidation for extended gear fault diagnosis under data limitations[J].Mechanical Systems and Signal Processing,2023,185:109772.
[7] LUO J,HUANG J,MA J,et al.An evaluation method of conditional deep convolutional generative adversarial networks for mechanical fault diagnosis[J].Journal of Vibration and Control,2022,28(11/12):1379-1389.
[8] ZHANG XUEXIA,ZHOU J,CHEN W. Data-driven fault diagnosis for PEMFC systems of hybrid tram based on deep learning[J]. International Journal of Hydrogen Energy,2020,45(24):13483-13495.
[9] HOANG D T,TRAN X T,VAN M,et al.A deep neural network-based feature fusion for bearing fault diagnosis[J].Sensors,2021,21(1):244.
[10] 张龙,甄灿壮,易剑昱,等.双通道特征融合CNN-GRU齿轮箱故障诊断[J].振动与冲击,2021,40(19):239-245.
[11] SHANG Z,LI W,GAO M,et al.An intelligent fault diagnosis method of multi-scale deep feature fusion based on information entropy[J].Chinese Journal of Mechanical Engineering,2021,34(1):1-16.
[12] ZHANG X,CUI P,XU R,et al.Deep stable learning for out-of-distribution generalization[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.[S.l.]:[s.n.],2021:5372-5382.
[13] DAI Y,GIESEKE F,OEHMCKE S,et al.Attentional feature fusion[C]//Proceedings of the IEEE/CVF winter conference on applications of computer vision.[S.l.]:[s.n.],2021:3560-3569.
[14] LIU M,SUN X,WANG Q,et al.Short-Term Load Forecasting Using EMD with Feature Selection and TCN-Based Deep Learning Model[J].Energies,2022,15(19):7170.
[15] CHEN Z,CEN J,XIONG J.Rolling bearing fault diagnosis using time-frequency analysis and deep transfer convolutional neural network[J].Ieee Access,2020,8:150248-150261.
[16] LIU W,RABINOVICH A,BERG A C.Parsenet:Looking wider to see better[J].arXiv preprint arXiv,2015:1506-1521.
[17] SHEN Z,CUI P,ZHANG T,et al.Stable Learning Via Sample Reweighting[J].Proceedings of the AAAI Conference on Artificial Intelligence,2020,34(4):5692-5699.
[18] XIE J,LIU F,WANG K,et al.Deep Kernel Learning Via Random Fourier Features[J].arXiv preprint arXiv,2019:1910-1923.
[19] 张建飞,黄晋英,吕阳,等.基于CBAM-ResNet的轴承剩余寿命预测[J].中北大学学报(自然科学版),2023,44(4):360-365,396.
[20] HEBDA-SOBKOWICZ J,ZIMROZ R,WYŁOMANSKA A.Selection of the Informative Frequency Band in a Bearing Fault Diagnosis in the Presence of Non-Gaussian Noise—Comparison of Recently Developed Methods[J].Applied Sciences,2020,10(8):2657.
[21] DAGA A P,FASANA A,MARCHESIELLO S,et al.The Politecnico di Torino rolling bearing test rig:Description and analysis of open access data[J].Mech.Syst.Signal Process,2019,120:252-273.

基于AFF-Stablenet模型的小样本轴承故障诊断^*

Fault diagnosis of small sample bearings based on the AFF-Stablenet model

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	王斐, 许波. 基于自适应LPP特征降维和改进VPMCD的滚动轴承故障诊断^*[J]. 现代制造工程, 2024, 525(6): 154-161.
[2]	刘满强, 吴杰. 基于ICEEMDAN与POA-SVM的感应电机故障诊断^*[J]. 现代制造工程, 2024, 524(5): 127-137.
[3]	牛礼民, 万凌初, 胡超. 基于IPSO-MCKD的汽车变速箱轴承故障诊断^*[J]. 现代制造工程, 2024, 522(3): 134-139.
[4]	纪京生, 周莉, 马向阳. VMD结合小波包信息熵和GJO-SVM的电机轴承故障诊断[J]. 现代制造工程, 2024, 521(2): 128-136.
[5]	肖伟, 李泽军, 管天福, 贺路, 陈绪兵. 基于PSO-IBP神经网络的纯电动汽车电驱总成故障诊断^*[J]. 现代制造工程, 2024, 520(1): 137-141.
[6]	胡晨;李志敏. 基于多特征阈值判据的航空液压柱塞泵故障诊断方法研究[J]. 现代制造工程, 2023, 516(9): 145-151.
[7]	莫坚;张泽. 轴承剩余使用寿命的注意力多尺度卷积神经网络预测[J]. 现代制造工程, 2023, 515(8): 148-154.
[8]	焦博森，蔺梦雄，张益农，张瑞钦，唐少虎. RV减速器故障诊断方法研究现状[J]. 现代制造工程, 2023, 513(6): 150-159.
[9]	殷才茗，王文瑞，鲁方林，姜山，马娜，吴波. 基于联邦学习和改进多尺度ResNet的故障诊断[J]. 现代制造工程, 2023, 512(5): 127-134.
[10]	王凯，吉卫喜，卢璟钰，苏璇. 基于改进GADF-SeResNet滚动轴承故障诊断方法[J]. 现代制造工程, 2023, 512(5): 135-142.
[11]	刘昕宇;姜长泓;刘一铮;王其铭. 基于空洞CNN和LSTM的滚动轴承剩余使用寿命预测[J]. 现代制造工程, 2023, 511(4): 130-135.
[12]	郑直，李显泽，刘伟民，王志军，曾魁魁. 基于log-SAM改进Autogram的滚动轴承故障诊断[J]. 现代制造工程, 2023, 519(12): 132-139.
[13]	吴宝存. 基于AP-ELM地铁转向架轴承系统故障诊断方法[J]. 现代制造工程, 2023, 508(1): 122-126.
[14]	毕浩程、蒋章雷、吴国新、刘秀丽、栾忠权. 基于SSA-VMD和1.5维包络谱的齿轮箱磨损故障诊断的研究[J]. 现代制造工程, 2022, 500(5): 130-137.
[15]	逄英，高军伟. 基于ICEEMDAN能量矩和MFOA-PNN的轴承故障诊断[J]. 现代制造工程, 2022, 498(3): 122-126.