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

振动图像结合CNN的轴承振动信号分析方法研究

郝勇 刘尚宗 吴文辉

郝勇,刘尚宗,吴文辉. 振动图像结合CNN的轴承振动信号分析方法研究[J]. 机械科学与技术,2022,41(12):1943-1949 doi: 10.13433/j.cnki.1003-8728.20200535
引用本文: 郝勇,刘尚宗,吴文辉. 振动图像结合CNN的轴承振动信号分析方法研究[J]. 机械科学与技术,2022,41(12):1943-1949 doi: 10.13433/j.cnki.1003-8728.20200535
HAO Yong, LIU Shangzong, WU Wenhui. Research on Bearing Vibration Signal Analysis Method Combining Vibration Image and CNN[J]. Mechanical Science and Technology for Aerospace Engineering, 2022, 41(12): 1943-1949. doi: 10.13433/j.cnki.1003-8728.20200535
Citation: HAO Yong, LIU Shangzong, WU Wenhui. Research on Bearing Vibration Signal Analysis Method Combining Vibration Image and CNN[J]. Mechanical Science and Technology for Aerospace Engineering, 2022, 41(12): 1943-1949. doi: 10.13433/j.cnki.1003-8728.20200535

振动图像结合CNN的轴承振动信号分析方法研究

doi: 10.13433/j.cnki.1003-8728.20200535
基金项目: 国家自然科学基金项目(51665013)
详细信息
    作者简介:

    郝勇(1978−), 副教授,博士,研究方向为机器视觉检测、精密仪器开发研制和信息提取算法,haonm@163.com

  • 中图分类号: TH133.3;TP18

Research on Bearing Vibration Signal Analysis Method Combining Vibration Image and CNN

  • 摘要: 本文以强背景噪声下振动信号特征提取和建模分析为研究目标,提出将振动信号转换为振动图像的信号变换方法,以深沟球轴承故障诊断振动信号和轴承质量等级评估振动信号为实验数据集,基于振动图像的卷积神经网络模型(VI-CNN),并采用正确识别率(CRR)作为模型精度的评价指标。实验结果表明:对于轴承故障诊断和质量等级评估的定性判别,采用VI-CNN对比其他建模方法正确识别率分别为100%和98.16%,模型有更好的稳健性。
  • 图  1  振动图像构建过程示意图

    图  2  典型的卷积神经网络

    图  3  轴承质量品质评估分析流程

    图  4  4种状态轴承振动图像

    图  5  轴承故障识别结果比较

    图  6  VI-CNN模型最佳结果混淆矩阵

    图  7  轴承检测装置简图

    图  8  3种品质轴承振动信号图

    图  9  3种轴承品质的振动图像

    图  10  轴承质量等级评估结果比较

    图  11  VI-CNN模型识别结果混淆矩阵

    表  1  公共轴承故障诊断数据样本说明

    编号故障状态损伤程度/mm训练样本测试样本
    1正常3020
    2内圈0.17783020
    3外圈0.17783020
    4滚动体0.17783020
    下载: 导出CSV

    表  2  轴承故障识别结果统计

    方法训练集平均识别率/%测试集平均识别率/%
    VS-SVM100.00 ± 095.62 ± 1.50
    VSTF-SVM98.82 ± 0.4097.25 ± 2.15
    VI+HOG+SVM100.00 ± 099.62 ± 0.80
    VI-CNN100.00 ± 0100.00 ± 0
    下载: 导出CSV

    表  3  轴承质量等级评估结果统计

    方法训练集平均识别率/%测试集平均识别率/%
    VS-SVM100.00 ± 084.83 ± 4.43
    VSTF-SVM97.77 ± 1.4086.66 ± 3.33
    VI-HOG-SVM100.00 ± 095.83 ± 2.49
    VI-CNN100.00 ± 098.16 ± 0.49
    下载: 导出CSV
  • [1] 沈功田, 刘渊. 大型机械系统的健康管理理论研究及应用设想[J]. 机械工程学报, 2017, 53(6): 1-9 doi: 10.3901/JME.2017.06.001

    SHEN G T, LIU Y. Research and application assumptions of health management theory of large mechanical system[J]. Journal of Mechanical Engineering, 2017, 53(6): 1-9 (in Chinese) doi: 10.3901/JME.2017.06.001
    [2] 李舜酩, 郭海东, 李殿荣. 振动信号处理方法综述[J]. 仪器仪表学报, 2013, 34(8): 1907-1915 doi: 10.3969/j.issn.0254-3087.2013.08.031

    LI S M, GUO H D, LI D R. Review of vibration signal processing methods[J]. Chinese Journal of Scientific Instrument, 2013, 34(8): 1907-1915 (in Chinese) doi: 10.3969/j.issn.0254-3087.2013.08.031
    [3] 郝勇, 吴文辉, 商庆园. 基于变分模态分解和支持向量机的滚动轴承品质评估[J]. 控制理论与应用, 2020, 37(7): 1544-1551 doi: 10.7641/CTA.2020.90594

    HAO Y, WU W H, SHANG Q Y. Rolling bearing quality evaluation based on variational mode decomposition and support vector machines[J]. Control Theory & Applications, 2020, 37(7): 1544-1551 (in Chinese) doi: 10.7641/CTA.2020.90594
    [4] 邵思羽. 基于深度学习的旋转机械故障诊断方法研究[D]. 南京: 东南大学, 2019

    SHAO S Y. Methodologies for fault diagnosis of rotary machine based on deep learning[D]. Nanjing: Southeast University, 2019 (in Chinese)
    [5] 汪海燕, 黎建辉, 杨风雷. 支持向量机理论及算法研究综述[J]. 计算机应用研究, 2014, 31(5): 1281-1286 doi: 10.3969/j.issn.1001-3695.2014.05.001

    WANG H Y, LI J H, YANG F L. Overview of support vector machine analysis and algorithm[J]. Application Research of Computers, 2014, 31(5): 1281-1286 (in Chinese) doi: 10.3969/j.issn.1001-3695.2014.05.001
    [6] KONG D H, YAN Y F. Industrial process deep feature representation by regularization strategy autoencoders for process monitoring[J]. Measurement Science and Technology, 2020, 31(2): 025104 doi: 10.1088/1361-6501/ab48c7
    [7] 叶壮, 余建波. 基于多通道一维卷积神经网络特征学习的齿轮箱故障诊断方法[J]. 振动与冲击, 2020, 39(20): 55-66

    YE Z, YU J B. Gearbox fault diagnosis based on feature learning of multi-channel one-dimensional convolutional neural network[J]. Journal of Vibration and Shock, 2020, 39(20): 55-66 (in Chinese)
    [8] 李益兵, 王磊, 江丽. 基于PSO改进深度置信网络的滚动轴承故障诊断[J]. 振动与冲击, 2020, 39(5): 89-96

    LI Y B, WANG L, JIANG L. Rolling bearing fault diagnosis based on DBN algorithm improved with PSO[J]. Journal of Vibration and Shock, 2020, 39(5): 89-96 (in Chinese)
    [9] WANG R X, JIANG H K, LI X Q, et al. A reinforcement neural architecture search method for rolling bearing fault diagnosis[J]. Measurement, 2020, 154: 107417 doi: 10.1016/j.measurement.2019.107417
    [10] 宁柏锋. 基于深度学习的无人机巡检图像销钉故障检测[J]. 计算机测量与控制, 2019, 27(11): 25-29

    NING B F. Pin fault detection in UAV inspection image based on deep learning[J]. Computer Measurement & Control, 2019, 27(11): 25-29 (in Chinese)
    [11] 李少波, 姚勇, 桂桂, 等. 基于CNN与多通道声学信号的齿轮故障诊断[J]. 中国测试, 2019, 45(10): 1-5 doi: 10.11857/j.issn.1674-5124.2018080093

    LI S B, YAO Y, GUI G, et al. Gear fault diagnosis based on CNN and multi-channel acoustic signals[J]. China Measurement & Test, 2019, 45(10): 1-5 (in Chinese) doi: 10.11857/j.issn.1674-5124.2018080093
    [12] 姜洪开, 邵海东, 李兴球. 基于深度学习的飞行器智能故障诊断方法[J]. 机械工程学报, 2019, 55(7): 27-34 doi: 10.3901/JME.2019.07.027

    JIANG H K, SHAO H D, LI X Q. Deep learning theory with application in intelligent fault diagnosis of aircraft[J]. Journal of Mechanical Engineering, 2019, 55(7): 27-34 (in Chinese) doi: 10.3901/JME.2019.07.027
    [13] 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 doi: 10.1016/j.neucom.2018.05.002
    [14] HOANG D T, KANG H J. Rolling element bearing fault diagnosis using convolutional neural network and vibration image[J]. Cognitive Systems Research, 2019, 53: 42-50 doi: 10.1016/j.cogsys.2018.03.002
    [15] 王海龙, 夏筱筠, 孙维堂. 基于EMD与卷积神经网络的滚动轴承故障诊断[J]. 组合机床与自动化加工技术, 2019(10): 46-48,52

    WANG H L, XIA X Y, SUN W T. rolling bearing fault diagnosis based on EMD and convolutional neural network[J]. Modular Machine Tool & Automatic Manufacturing Technique, 2019(10): 46-48,52 (in Chinese)
    [16] 胡晓依, 荆云建, 宋志坤, 等. 基于CNN-SVM的深度卷积神经网络轴承故障识别研究[J]. 振动与冲击, 2019, 38(18): 173-178

    HU X Y, JING Y J, SONG Z K, et al. Bearing fault identification by using deep convolution neural networks based on CNN-SVM[J]. Journal of Vibration and Shock, 2019, 38(18): 173-178 (in Chinese)
    [17] 谢远东, 雷文平, 韩捷. 基于全矢1D-CNN的轴承故障诊断研究[J]. 设备管理与维修, 2019(15): 21-24

    XIE Y D, LEI W P, HAN J. Research on be-aring fault diagnosis based on full vector 1D-CNN[J]. Equipment Management and Maintenance, 2019(15): 21-24 (in Chinese)
    [18] 中华人民共和国国家质量监督检验检疫总局, 中国国家标准化管理委员会. GB/T 24608-2009 滚动轴承及其商品零件检验规则[S]. 北京: 中国标准出版社, 2010

    General Administration of Quality Supervision, Inspection and Quarantine of the People's Republic of China, Standardization Administration of the People's Republic of China. GB/T 24608-2009 Inspection rules for rolling bearings and commercial parts[S]. Beijing: Standards Press of China, 2010 (in Chinese)
    [19] 中华人民共和国国家发展和改革委员会. JB/T 7047-2006 滚动轴承 深沟球轴承振动(加速度)技术条件[S]. 北京: 机械工业出版社, 2006

    National Development and Reform Commission. JB/T 7047-2006 Rolling bearings-specifications of vibration (acceleration) for deep groove ball bearings[S]. Beijing: China Machine Press, 2006 (in Chinese)
    [20] Kenneth LOPARO K. Case western reserve university bearing data center[M/OL]. http://csegroups.case.edu/bearingdatacenter/
    [21] 万齐杨, 熊邦书, 李新民, 等. 基于多噪声数据训练CNN的自动倾斜器滚动轴承故障诊断[J]. 南昌航空大学学报(自然科学版), 2019, 33(2): 21-26

    WAN Q Y, XIONG B S, LI X M, et al. Fault diagnosis for rolling bearing of swashplate based on multi-noise data training CNN[J]. Journal of Nanchang Hangkong University (Social Sciences), 2019, 33(2): 21-26 (in Chinese)
    [22] Smith W A, Randall R B. Rolling element bearing diagnostics using the Case Western Reserve University data: A benchmark study[J]. Mechanical Systems and Signal Processing, 2015, 64-65: 100-131
  • 加载中
图(11) / 表(3)
计量
  • 文章访问数:  275
  • HTML全文浏览量:  234
  • PDF下载量:  27
  • 被引次数: 0
出版历程
  • 收稿日期:  2020-12-29
  • 网络出版日期:  2023-02-16
  • 刊出日期:  2022-12-05

目录

    /

    返回文章
    返回