基于残差神经网络的滚动轴承故障诊断方法

兰州理工大学学报 ›› 2022, Vol. 48 ›› Issue (3): 86-93.

• 自动化技术与计算机技术 • 上一篇下一篇

基于残差神经网络的滚动轴承故障诊断方法

朱奇先¹, 梁浩鹏^*2, 赵小强³, 宋昭様³

1.大型电气传动系统与装备技术国家重点实验室, 甘肃天水 741000;
2.兰州理工大学计算机与通信学院, 甘肃兰州 730050;
3.兰州理工大学电气工程与信息工程学院, 甘肃兰州 730050

收稿日期:2020-12-15 出版日期:2022-06-28 发布日期:2022-10-09
通讯作者: 梁浩鹏(1995-),男,河南周口人,博士生.Email:haop1115@163.com
基金资助:
国家自然科学基金(61763029),国防基础科研项目(JCKY2018427C002),甘肃省高等学校产业支撑引导项目(2019C-05),大型电气传动系统与装备技术国家重点实验室开放基金(SKLLDJ012016020),甘肃省工业过程先进控制重点实验室开放基金(2019KFJJ01)

Rolling bearing fault diagnosis method based on residual neural network

ZHU Qi-xian¹, LIANG Hao-peng², ZHAO Xiao-qiang³, SONG Zhao-yang³

1. State Key Laboratory of Large Electric Drive System and Equipment Technology, Tianshui 741000, China;
2. School of Computer and Communication, Lanzhou Univ. of Tech., Lanzhou 730050, China;
3. College of Electrical and Information Engineering, Lanzhou Univ. of Tech., Lanzhou 730050, China

Received:2020-12-15 Online:2022-06-28 Published:2022-10-09

摘要/Abstract

摘要： 针对轴承故障诊断方法在变工况条件下诊断效果不佳的问题,提出了一种基于残差神经网络的滚动轴承故障诊断方法.该方法首先以滚动轴承时域信号数据作为输入,针对信号的时变性改进了数据池化层,改进的数据池化层利用三个连续的卷积层串联构建而成,目的在于能够有效地提取振动信号中的故障特征信息,并减少残差神经网络中参数的计算量;然后设计了一种空洞卷积和残差块相结合的空洞残差块,用于特征信息的学习;最后通过在全连接层后加入Dropout层丢弃一定比例的神经元,能有效避免过拟合的负面影响.使用凯斯西储大学轴承数据集进行仿真实验,与SVM+EMD+Hilbert包络谱、BPNN+EMD+Hilbert包络谱和Resnet三种方法作对比分析,结果表明该方法在变工况下的滚动轴承故障诊断中具有更高的诊断准确率、更强的抗噪性和泛化能力.

关键词: 残差神经网络, 故障诊断, 滚动轴承, 变工况

Abstract: Because the rolling bearing has been working for a long time in an environment with complex and changeable working conditions and large noise interference, the bearing fault diagnosis method has a poor diagnostic effect under variable working conditions, aiming at this problem, a method of rolling bearing fault diagnosis based on residual neural network is proposed. First, the time domain signal data of rolling bearing is used as the input. Because the signal has a strong time-varying nature, the data pooling layer is improved for this characteristic. The improved data pooling layer is constructed by using three consecutive convolution layers in series. The purpose is to effectively extract feature information of the vibration signal and reduce the calculation amount of residual neural network parameters. Then a kind of dilated residual block combined with dilated convolution and residual block is designed for feature information learning. Finally, the dropout layer is added after the full connection layer to discard a certain proportion of neurons, which can effectively avoid the negative effects of over fitting. The bearing data sets of Case Western Reserve University is used for simulation experiment, and compared with SVM+EMD+Hilbert envelope spectrum, BPNN+EMD+Hilbert envelope spectrum and Resnet, the results show that the proposed method has higher diagnosis accuracy, stronger noise resistance and generalization ability in the fault diagnosis of rolling bearing under variable working conditions.

Key words: residual neural network, fault diagnosis, rolling bearing, variable working conditions

中图分类号:

朱奇先, 梁浩鹏, 赵小强, 宋昭様. 基于残差神经网络的滚动轴承故障诊断方法[J]. 兰州理工大学学报, 2022, 48(3): 86-93.

ZHU Qi-xian, LIANG Hao-peng, ZHAO Xiao-qiang, SONG Zhao-yang. Rolling bearing fault diagnosis method based on residual neural network[J]. Journal of Lanzhou University of Technology, 2022, 48(3): 86-93.

参考文献

[1] 唐贵基,庞彬.ITT变换在风电机组滚动轴承故障诊断中的应用 [J].电力自动化设备,2017,37(9):83-89.
[2] 刘乐.基于局部均值分解的滚动轴承故障诊断系统研究与应用 [D].太原:中北大学,2017.
[3] 王玉静,那晓栋,康守强,等.基于EEMD-Hilbert包络谱和DBN的变负载下滚动轴承状态识别方法 [J].中国电机工程学报,2017,37(23):6943-6950.
[4] YAN X A,JIA M P.A novel optimized SVM classification algorithm with multi-domain feature and its application to fault diagnosis of rolling bearing [J].Neurocomputing,2018,313:47-64.
[5] 袁莉芬,孙业胜,何怡刚,等.基于小波包优选的模拟电路故障特征提取方法 [J].电工技术学报,2018,33(11):158-165.
[6] WANG L,LIU Z,MIAO Q,et al.Time-frequency analysis based on ensemble local mean decomposition andfast Kurtogram for rotating machinery fault diagnosis [J].Mechanical Systems and Signal Processing,2018,103(3):60-75.
[7] 唐贵基,王晓龙.变分模态分解方法及其在滚动轴承早期故障诊断中的应用 [J].振动工程学报,2016,29(4):638-648.
[8] 李宏坤,杨蕊,任远杰,等.利用粒子滤波与谱峭度的滚动轴承故障诊断 [J].机械工程学报,2017,53(3):63-72.
[9] MAO W T,HE L,WANG J W,et al.Online sequential prediction of bearings imbalanced fault diagnosis by extreme learning machine [J].Mechanical Systems and Signal Processing,2017,83(1):450-473.
[10] 陈鹏,赵小强,朱奇先.基于VMD-MPE-KPCA特征提取与MRVM相混合的滚动轴承故障诊断方法 [J].兰州理工大学学报,2020,46(5):92-99.
[11] 庄福振,罗平,何清,等.迁移学习研究进展 [J].软件学报,2015,26(1):26-39.
[12] 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.
[13] LU C,WANG Z Y,QIN W L,et al.Fault diagnosis of rotary machinery components using a stacked denoising autoencoder-based health state identification [J].Signal Processing,2017,130(1):377-388.
[14] JING L,ZHAO M,LI P,et al.A convolutional neural network based feature learning and fault diagnosis method for the condition monitoring of gearbox [J].Measurement,2017,111(12):1-10.
[15] 孔子迁,邓蕾,汤宝平,等.基于时频融合和注意力机制的深度学习行星齿轮箱故障诊断方法 [J].仪器仪表学报,2019,40(6):221-227.
[16] 陈志刚,杜小磊,王衍学,等.改进集成深层自编码器在轴承故障诊断中的应用 [J].控制与决策,2021,36(1):135-142.
[17] ZHANG W,LI C,PENG G,et al.A deep convolutional neural network with new training methods for bearing fault diagnosis under noisy environment and different working load [J].Mechanical Systems and Signal Processing,2018,100(2):439-453.
[18] HE K M,ZHANG X Y,REN S Q,et al.Deep residual learning for image recognition [C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Piscataway,NJ,USA:IEEE,2016:770-778.
[19] YU F,KOLTUN V.Multi-scale context aggregation by dilated convolutions [C/OL].[2020-10-10].https://arxiv.org/pdf/1511.07122.pdf.
[20] LI Q,WANG H.A research review of Hilbert-Huang transform used for rolling bearing fault diagnosis [J].Applied Mechanics and Materials,2013,397(9):4558-4568.
[21] HE K M,ZHANG X Y,REN S Q,et al.Identity mappings in deep residual networks [C]//European Conference on Computer Vision.[S.l.]:Springer International Publishing,2016:630-645.

基于残差神经网络的滚动轴承故障诊断方法

Rolling bearing fault diagnosis method based on residual neural network

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 11

编辑推荐

Metrics

本文评价

[1]	赵小强, 罗维兰, 梁浩鹏. 基于SIR多级残差连接密集网络的轴承故障诊断[J]. 兰州理工大学学报, 2022, 48(6): 46-54.
[2]	赵荣珍, 薛勇, 吴耀春. 改进的D-t-SNE滚动轴承故障数据集降维方法[J]. 兰州理工大学学报, 2022, 48(3): 42-49.
[3]	赵荣珍, 常书源. 基于M-WDLS和PCA的转子故障诊断方法[J]. 兰州理工大学学报, 2021, 47(5): 38-44.
[4]	赵荣珍, 马森财, 吴耀春. 云模型和集成极限学习机相结合的滚动轴承故障诊断方法[J]. 兰州理工大学学报, 2021, 47(4): 33-39.
[5]	刘金霞. 基于深度学习的无线电信号分类[J]. 兰州理工大学学报, 2021, 47(4): 106-110.
[6]	剡昌锋, 赵伟坤, 孟佳东, 王文斌, 吴黎晓. 基于双脉冲特征的滚动轴承缺陷尺寸估计方法[J]. 兰州理工大学学报, 2021, 47(2): 39-47.
[7]	剡昌锋, 栗宇, 王慧滨, 张强, 艾科勇, 吴黎晓. 基于本体的汽轮发电机组故障诊断知识建模[J]. 兰州理工大学学报, 2020, 46(5): 41-48.
[8]	陈鹏, 赵小强, 朱奇先. 基于VMD-MPE-KPCA特征提取与MRVM相混合的滚动轴承故障诊断方法[J]. 兰州理工大学学报, 2020, 46(5): 92-99.
[9]	赵荣珍, 户文刚. 基于LabVIEW的离心式化工泵振动测试系统设计[J]. 兰州理工大学学报, 2020, 46(4): 33-37.
[10]	赵小强, 姚红娟. 基于DDNPE算法的间歇过程故障诊断[J]. 兰州理工大学学报, 2020, 46(4): 96-102.
[11]	赵荣珍, 张琛, 邓林峰. 基于EEMD与模糊信息熵的旋转机械故障诊断方法[J]. 兰州理工大学学报, 2020, 46(3): 39-44.