留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

基于深度网络的滚动轴承智能故障诊断

李金才 付文龙 王仁明 陈星 孟嘉鑫

李金才,付文龙,王仁明,等. 基于深度网络的滚动轴承智能故障诊断[J]. 工矿自动化,2022,48(4):78-88.  doi: 10.13272/j.issn.1671-251x.2022010008
引用本文: 李金才,付文龙,王仁明,等. 基于深度网络的滚动轴承智能故障诊断[J]. 工矿自动化,2022,48(4):78-88.  doi: 10.13272/j.issn.1671-251x.2022010008
LI Jincai, FU Wenlong, WANG Renming, et al. Intelligent fault diagnosis of rolling bearings based on deep network[J]. Journal of Mine Automation,2022,48(4):78-88.  doi: 10.13272/j.issn.1671-251x.2022010008
Citation: LI Jincai, FU Wenlong, WANG Renming, et al. Intelligent fault diagnosis of rolling bearings based on deep network[J]. Journal of Mine Automation,2022,48(4):78-88.  doi: 10.13272/j.issn.1671-251x.2022010008

基于深度网络的滚动轴承智能故障诊断

doi: 10.13272/j.issn.1671-251x.2022010008
基金项目: 国家自然科学基金资助项目(51741907);湖北省水电动机械设计与维修重点实验室开放基金(2020KJX03)。
详细信息
    作者简介:

    李金才(1996-),男,河南开封人,硕士研究生,主要研究方向为机械故障诊断与人工智能,E-mail:2953700543@qq.com

    通讯作者:

    付文龙(1988-),男,湖北仙桃人,副教授,博士,主要研究方向为信号处理与旋转机械系统状态分析,E-mail:ctgu_fuwenlong@126.com

  • 中图分类号: TD712

Intelligent fault diagnosis of rolling bearings based on deep network

  • 摘要: 针对变工况环境中滚动轴承的源域与目标域数据分布不同及目标域样本不含标签的问题,提出一种基于深度自适应迁移学习网络(DATLN)的滚动轴承故障诊断模型。首先,搭建领域共享特征提取网络,采用多尺度卷积神经网络(MSCNN)抑制噪声的干扰,进而有效提取振动信号中蕴含的局部故障信息;其次,结合双向长短时记忆网络(BiLSTM)进一步学习局部故障信息中的时间特征;最后,引入迁移学习,以域对抗(DA)训练结合自适应联合分布(AJD)度量构建域自适应模块,通过最大化域分类损失和最小化AJD距离,实现源域与目标域特征样本对齐。在开源CWRU数据集与机械故障平台实测数据集上分别进行抗噪实验和迁移实验。抗噪实验表明:① 在无噪声环境下,MSCNN−BiLSTM网络的识别准确率均达到99%以上,说明其具有较好的特征提取能力;② MSCNN−BiLSTM,LeNet−5,MSCNN和BiLSTM四种网络的识别准确率随着噪声强度的增强而降低;③ 在3,5,10 dB噪声环境下,MSCNN−BiLSTM网络的平均识别准确率比LeNet−5,MSCNN和BiLSTM 网络的平均识别准确率均高,说明MSCNN−BiLSTM网络具有较好的抗噪声干扰性能;④ MSCNN−BiLSTM网络在无噪声环境和3 dB噪声环境下,均最先达到收敛且波动较小。迁移实验表明:① 在无标签目标域数据集上,DA+AJD方法的平均识别准确率为97.36%,均高于Baseline,迁移成分分析(TCA),域对抗神经网络(DANN)的识别准确率;② 在测试集混淆矩阵上,DA+AJD方法仅有1个样本被错误识别,表明基于域适应的DA+AJD方法具备更好的故障迁移诊断性能;③ 利用t−SNE算法对处理后的源域与目标域特征样本进行可视化,DA+AJD方法只有少量目标域的滚动体故障和外圈故障特征样本被错误对齐到源域的内圈故障特征样本区域,说明DA+AJD方法可有效减少源域与目标域的边缘分布和条件分布差异,进而达到更好的特征样本对齐效果。

     

  • 图  1  迁移学习

    Figure  1.  Transfer learning

    图  2  BiLSTM网络结构

    Figure  2.  Structure of BiLSTM network

    图  3  MSCNN−BiLSTM网络

    Figure  3.  MSCNN-BilSTM network

    图  4  滚动轴承故障诊断模型

    Figure  4.  Model of rolling bearing fault diagnosis

    图  5  CWRU轴承数据采集系统

    Figure  5.  CWRU bearing data acquisition system

    图  6  不重叠采样

    Figure  6.  Non-overlapping sampling

    图  7  正常状态下振动信号变化

    Figure  7.  Vibration signal changes under the normal state

    图  8  内圈故障(IR07)状态下振动信号变化

    Figure  8.  Vibration signal changes in the inner fault (IR07) state

    图  9  无噪声环境下对比实验结果

    Figure  9.  Comparison of experimental results in noiseless environment

    图  12  3 dB噪声环境下对比实验结果

    Figure  12.  Comparison of experimental results in 3 dB environment

    图  11  5 dB噪声环境下对比实验结果

    Figure  11.  Comparison of experimental results in 5 dB environment

    图  10  10 dB噪声环境下对比实验结果

    Figure  10.  Comparison of experimental results in 10 dB environment

    图  13  无噪声环境下0负载测试集识别结果

    Figure  13.  Identification results of 0 load test set in noise-free environment

    图  14  3 dB噪声环境下0负载测试集识别结果

    Figure  14.  Identification results of 0 load test set in 3 dB environment

    图  15  机械故障模拟实验台

    Figure  15.  Machinery fault simulator

    图  16  3 dB噪声环境下迁移结果

    Figure  16.  Transfer results of 3 dB environment

    图  17  迁移任务C to B的测试集混淆矩阵

    Figure  17.  Test dataset confusion matrix of transfer task C to B

    图  18  迁移任务C to B的t-SNE特征可视化

    Figure  18.  T-SNE characteristic visualization of transfer task C to B

    表  1  MSCNN−BiLSTM网络参数

    Table  1.   Parameters of MSCNN-BiLSTM network

    网络层类型核尺寸/步长核数量激活
    函数
    输入尺寸输出尺寸
    MSCNN网络通道1卷积层115/116ReLU(1,1 024)(16,1 010)
    卷积层215/132ReLU(16,1 010)(32,996)
    最大池化层2/2(32,996)(32,498)
    卷积层315/164ReLU(32,498)(64,484)
    卷积层415/1128ReLU(64,484)(128,470)
    自适应最大
    池化层
    (128,470)(128,4)
    MSCNN网络通道2卷积层55/116ReLU(1,1 024)(16,1 020)
    卷积层65/132ReLU(16,1 020)(32,1 016)
    最大池化层2/2(32,1 016)(32,508)
    卷积层75/164ReLU(32,508)(64,504)
    卷积层85/1128ReLU(64,504)(128,500)
    自适应最大
    池化层
    (128,500)(128,4)
    MSCNN网络
    汇聚层
    汇聚层(128,4),(128,4)(128,4)
    BiLSTM网络BiLSTM层ReLU(128,4)(256)
    下载: 导出CSV

    表  2  域分类器参数

    Table  2.   Parameters of domain classifier

    层次神经元个数
    全连接层1256
    全连接层2128
    全连接层32
    下载: 导出CSV

    表  3  0负载下数据集

    Table  3.   Date set under 0 load

    损伤直径/mm损伤位置标记
    正常N
    0.177 8内圈IR07
    0.355 6内圈IR14
    0.533 4内圈IR21
    0.177 8外圈OR07
    0.355 6外圈OR14
    0.533 4外圈OR21
    0.177 8滚动体B07
    0.355 6滚动体B14
    0.533 4滚动体B21
    下载: 导出CSV

    表  4  CWRU样本集

    Table  4.   CWRU sample set

    状态标签样本数
    00.75 kW1.5 kW2.25 kW
    N 0 100 100 100 100
    IR07 1 100 100 100 100
    B07 2 100 100 100 100
    OR07 3 100 100 100 100
    IR14 4 100 100 100 100
    B14 5 100 100 100 100
    OR14 6 100 100 100 100
    IR21 7 100 100 100 100
    B21 8 100 100 100 100
    OR21 9 100 100 100 100
    下载: 导出CSV

    表  5  不同网络的平均识别准确率

    Table  5.   Average accuracy of different network

    网络平均识别准确率/%
    3 dB5 dB10 dB
    LeNet−590.7493.8395.42
    MSCNN95.5796.8997.14
    BiLSTM89.1092.5896.99
    MSCNN−BiLSTM98.4399.0099.16
    下载: 导出CSV

    表  6  每种方法的平均识别准确率

    Table  6.   Average results of different methods

    方法平均识别准确率/%
    Baseline75.90
    TCA85.38
    DANN87.19
    DA+AJD97.36
    下载: 导出CSV
  • [1] 宫涛,杨建华,单振,等. 强噪声背景与变转速工况条件下滚动轴承故障诊断研究[J]. 工矿自动化,2021,47(7):63-71.

    GONG Tao,YANG Jianhua,SHAN Zhen,et al. Research on rolling bearing fault diagnosis under strong noise background and variable speed working condition[J]. Industry and Mine Automation,2021,47(7):63-71.
    [2] 鞠晨,张超,樊红卫,等. 基于小波包分解和PSO-BPNN的滚动轴承故障诊断[J]. 工矿自动化,2020,46(8):70-74.

    JU Chen,ZHANG Chao,FAN Hongwei,et al. Rolling bearing fault diagnosis based on wavelet packet decomposition and PSO-BPNN[J]. Industry and Mine Automation,2020,46(8):70-74.
    [3] LI Xiang,ZHANG Wei,DING Qian,et al. Multi-layer domain adaptation method for rolling bearing fault diagnosis[J]. Signal Processing,2019,157:180-197. doi: 10.1016/j.sigpro.2018.12.005
    [4] WANG Yujing, WANG Chao, KANG Shouqiang, et al. The network combined broad learning with transfer learning: a new intelligent fault diagnosis method for rolling bearings[J]. Measurement Science and Technology, 2020, 31(11). DOI: 10.1088/1361-6501/ab8fee.
    [5] CHEN Zhuyun,GRYLLIAS K,LI Weihua. Intelligent fault diagnosis for rotary machinery using transferable convolutional neural network[J]. IEEE Transactions on Industrial Informatics,2019,16(1):339-349.
    [6] 陈超,沈飞,严如强. 改进LSSVM迁移学习方法的轴承故障诊断[J]. 仪器仪表学报,2017,38(1):33-40. doi: 10.3969/j.issn.0254-3087.2017.01.005

    CHEN Chao,SHEN Fei,YAN Ruqiang. Enhanced least squares support vector machine-based transfer learning strategy for bearing fault diagnosis[J]. Chinese Journal of Scientific Instrument,2017,38(1):33-40. doi: 10.3969/j.issn.0254-3087.2017.01.005
    [7] 陈仁祥,陈思杨,杨黎霞,等. 改进TrAdaBoost多分类算法的滚动轴承故障诊断[J]. 振动与冲击,2019,38(15):36-41,48.

    CHEN Renxiang,CHEN Siyang,YANG Lixia,et al. Fault diagnosis of rolling bearings based on improved TrAdaBoost multi-classification algorithm[J]. Journal of Vibration and Shock,2019,38(15):36-41,48.
    [8] 康守强,邹佳悦,王玉静,等. 基于无监督特征对齐的变负载下滚动轴承故障诊断方法[J]. 中国电动机工程学报,2020,40(1):274-281,393.

    KANG Shouqiang,ZOU Jiayue,WANG Yujing,et al. Fault diagnosis method of a rolling bearing under varying loads based on unsupervised feature alignment[J]. Proceedings of the CSEE,2020,40(1):274-281,393.
    [9] GUO Liang,LEI Yaguo,XING Saibo,et al. Deep convolutional transfer learning network:a new method for intelligent fault diagnosis of machines with unlabeled data[J]. IEEE Transactions on Industrial Electronics,2018,66(9):7316-7325.
    [10] AN Zenghui,LI Sunming,WANG Jinrui,et al. Generalization of deep neural network for bearing fault diagnosis under different working conditions using multiple kernel method[J]. Neurocomputing,2019,352(8):42-53.
    [11] HAN Te,LIU Chao,YANG Wenguang,et al. A novel adversarial learning framework in deep convolutional neural network for intelligent diagnosis of mechanical faults[J]. Knowledge-Based Systems,2019,165(2):474-487.
    [12] CHENG Cheng,ZHOU Beitong,MA Guijun,et al. Wasserstein distance based deep adversarial transfer learning for intelligent fault diagnosis with unlabeled or insufficient labeled data[J]. Neurocomputing,2020,409:35-45. doi: 10.1016/j.neucom.2020.05.040
    [13] 吴静然,刘建华,崔冉. 子域适应无监督轴承故障诊断[J]. 振动与冲击,2021,40(15):34-40.

    WU Jingran,LIU Jianhua,CUI Ran. Sub-domain adaptive unsupervised bearing fault diagnosis[J]. Journal of Vibration and Shock,2021,40(15):34-40.
    [14] 许子非,金江涛,李春. 基于多尺度卷积神经网络的滚动轴承故障诊断方法[J]. 振动与冲击,2021,40(18):212-220.

    XU Zifei,JIN Jiangtao,LI Chun. New method for the fault diagnosis of rolling bearings based on a multiscale convolutional neural network[J]. Journal of Vibration and Shock,2021,40(18):212-220.
    [15] CHEN Xiaohan,ZHANG Beike,GAO Dong. Bearing fault diagnosis base on multi-scale CNN and LSTM model[J]. Journal of Intelligent Manufacturing,2021,32(4):971-987. doi: 10.1007/s10845-020-01600-2
    [16] XIE Junyao, ZHANG Laibin, DUAN Lixiang, et al. On cross-domain feature fusion in gearbox fault diagnosis under various operating conditions based on transfer component analysis[C]//2016 IEEE International Conference on Prognostics and Health Management (ICPHM), Ottawa, 2016: 20-22.
    [17] HAN Te,LIU Chao,YANG Wenguang,et al. Deep transfer network with joint distribution adaptation:a new intelligent fault diagnosis framework for industry application[J]. ISA Transactions,2020,97(2):269-281.
  • 加载中
图(18) / 表(6)
计量
  • 文章访问数:  485
  • HTML全文浏览量:  129
  • PDF下载量:  44
  • 被引次数: 0
出版历程
  • 收稿日期:  2022-01-05
  • 修回日期:  2022-04-05
  • 网络出版日期:  2022-04-08

目录

    /

    返回文章
    返回