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

数控机床电动主轴WPD-TSNE-SVM模型故障诊断

李坤宏 江桂云 朱代兵

李坤宏,江桂云,朱代兵. 数控机床电动主轴WPD-TSNE-SVM模型故障诊断[J]. 机械科学与技术,2024,43(5):832-836 doi: 10.13433/j.cnki.1003-8728.20220292
引用本文: 李坤宏,江桂云,朱代兵. 数控机床电动主轴WPD-TSNE-SVM模型故障诊断[J]. 机械科学与技术,2024,43(5):832-836 doi: 10.13433/j.cnki.1003-8728.20220292
LI Kunhong, JIANG Guiyun, ZHU Daibing. Fault Diagnosis of CNC Machine Tool Electric Spindle with WPD-TSNE-SVM Model[J]. Mechanical Science and Technology for Aerospace Engineering, 2024, 43(5): 832-836. doi: 10.13433/j.cnki.1003-8728.20220292
Citation: LI Kunhong, JIANG Guiyun, ZHU Daibing. Fault Diagnosis of CNC Machine Tool Electric Spindle with WPD-TSNE-SVM Model[J]. Mechanical Science and Technology for Aerospace Engineering, 2024, 43(5): 832-836. doi: 10.13433/j.cnki.1003-8728.20220292

数控机床电动主轴WPD-TSNE-SVM模型故障诊断

doi: 10.13433/j.cnki.1003-8728.20220292
基金项目: 重庆市科技计划(应用开发重大)(cstc2015yykfC40001)
详细信息
    作者简介:

    李坤宏,教授,硕士,likunhong777@163.com

  • 中图分类号: TH17

Fault Diagnosis of CNC Machine Tool Electric Spindle with WPD-TSNE-SVM Model

  • 摘要: 为了提高数控机床电动主轴故障诊断效率,设计了一种WPD-TSNE-SVM组合模型。利用小波包方法分解主轴振动信号,并完成样本集TSNE降维的过程,利用SVM完成重构特征的故障分类。构建数控机床主轴信号混合特征空间向量,并进行故障诊断分析。研究结果表明:TSNE方法训练样数据形成规律分布特点,采用非线性SVM多故障分类器实现小波包混合特征的故障准确分类。根据径向基核函数建立的非线性SVM诊断方法获得更高准确率。该方法诊断轴承运行故障,获得更高维护效率,确保数控机床主轴运行稳定性。
  • 图  1  本文诊断方案

    Figure  1.  Diagnostic scheme of this paper

    图  2  振动信号时域图

    Figure  2.  Time domain of vibration signal

    图  3  样本特征降维分布

    Figure  3.  Dimensional reduction distribution of sample features

    图  4  分类结果

    Figure  4.  Classification results

    表  1  样本集

    Table  1.   Sample set

    类别信号种类训练样本数测试样本数
    1内圈故障205
    2外圈故障205
    3滚动体故障205
    4正常205
    下载: 导出CSV

    表  2  模型对比

    Table  2.   Model comparison

    类别模型准确率/%
    1径向基SVM100(50/50)
    2线性SVM92(46/50)
    3BP网络88(44/50)
    下载: 导出CSV
  • [1] 范丽婷, 陈加凯, 张丽秀, 等. 高速电主轴运行状态评价指标体系的建立与分析[J]. 制造技术与机床, 2018(1): 90-95.

    FAN L T, CHEN J K, ZHANG L X, et al. Indictor system for evaluating the running performance of high speed motorized spindle[J]. Manufacturing Technology & Machine Tool, 2018(1): 90-95. (in Chinese)
    [2] CHEN X Z, SONG Z Y, LI H, et al. Research on fault early warning and the diagnosis of machine tools based on energy fault tree analysis[J]. Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture, 2019, 233(11): 2147-2159.
    [3] 郑近德, 代俊习, 朱小龙, 等. 基于改进多尺度模糊熵的滚动轴承故障诊断方法[J]. 振动、测试与诊断, 2018, 38(5): 929-934.

    ZHENG J D, DAI J X, ZHU X L, et al. A rolling bearing fault diagnosis approach based on improved multiscale fuzzy entropy[J]. Journal of Vibration, Measurement & Diagnosis, 2018, 38(5): 929-934. (in Chinese)
    [4] 金志浩, 于宝刚, 杨铮鑫, 等. 基于小波分析-最小二乘支持向量机的转子碰摩故障诊断[J]. 沈阳化工大学学报, 2019, 33(3): 251-256. doi: 10.3969/j.issn.2095-2198.2019.03.012

    JIN Z H, YU B G, YANG Z X, et al. The rub-impact fault diagnosis based on wavelet analysis-least square support vector machine[J]. Journal of Shenyang University of Chemical Technology, 2019, 33(3): 251-256. (in Chinese) doi: 10.3969/j.issn.2095-2198.2019.03.012
    [5] YEN G G, LIN K C. Wavelet packet feature extraction for vibration monitoring[J]. IEEE Transactions on Industrial Electronics, 2000, 47(3): 650-667. doi: 10.1109/41.847906
    [6] 于岩, 许继秀, 张梦超, 等. 小波分析和小波包分析在轴承故障诊断中的对比分析[J]. 煤矿机械, 2019, 40(12): 170-173.

    YU Y, XU J X, ZHANG M C, et al. Comparative analysis of wavelet analysis and wavelet packet analysis in bearing fault diagnosis[J]. Coal Mine Machinery, 2019, 40(12): 170-173. (in Chinese)
    [7] MAATEN L V D, HINTON G. Visualizing data using t-SNE[J]. Journal of Machine Learning Research, 2008, 9(86): 2579-2605.
    [8] 谷玉海, 韩秋实, 徐小力, 等. t分布随机近邻嵌入机械故障特征提取方法研究[J]. 机械科学与技术, 2016, 35(12): 1900-1905.

    GU Y H, HAN Q S, XU X L, et al. An early fault feature extraction method based on t-distribution stochastic neighbor embedding for large rotating machinery[J]. Mechanical Science and Technology for Aerospace Engineering, 2016, 35(12): 1900-1905. (in Chinese)
    [9] 温廷新, 孔祥博. 基于KPCA-PSO-RBF-SVM的矿井突水水源识别模型[J]. 辽宁工程技术大学学报(自然科学版), 2020, 39(1): 6-11. doi: 10.11956/j.issn.1008-0562.2020.01.002

    WEN T X, KONG X B. Mine water inrush source identification model based on KPCA-PSO-RBBF-SVM[J]. Journal of Liaoning Technical University (Natural Science), 2020, 39(1): 6-11. (in Chinese) doi: 10.11956/j.issn.1008-0562.2020.01.002
    [10] 瞿金秀, 石长全, 丁锋, 等. 基于多尺度排列熵和支持向量机的轴承故障诊断[J]. 煤矿机械, 2018, 39(9): 143-146.

    QU J X, SHI C Q, DING F, et al. Bearing fault diagnosis based on multiscale permutation entropyand support vector machine[J]. Coal Mine Machinery, 2018, 39(9): 143-146. (in Chinese)
    [11] 李学军, 何能胜, 何宽芳, 等. 基于小波包近似熵和SVM的圆柱滚子轴承诊断[J]. 振动、测试与诊断, 2015, 35(6): 1031-1036.

    LI X J, HE N S, HE K F, et al. Cylindrical roller bearing diagnosis based on wavelet packet approximate entropy and support vector machines[J]. Journal of Vibration, Measurement & Diagnosis, 2015, 35(6): 1031-1036. (in Chinese)
    [12] 唐静, 王二化, 朱俊, 等. 基于频域特征和支持向量机的汽车水泵轴承故障诊断研究[J]. 机床与液压, 2018, 46(13): 163-167. doi: 10.3969/j.issn.1001-3881.2018.13.040

    TANG J, WANG E H, ZHU J, et al. Research on fault diagnosis of automotive water pump bearing based on frequency domain features and SVM[J]. Machine Tool & Hydraulics, 2018, 46(13): 163-167. (in Chinese) doi: 10.3969/j.issn.1001-3881.2018.13.040
    [13] 贾峰, 武兵, 熊晓燕, 等. 基于多维度排列熵与支持向量机的轴承早期故障诊断方法[J]. 计算机集成制造系统, 2014, 20(9): 2275-2282.

    JIA F, WU B, XIONG X Y, et al. Early fault diagnosis of bearing based on multi-dimension permutation entropy and SVM[J]. Computer Integrated Manufacturing Systems, 2014, 20(9): 2275-2282. (in Chinese)
    [14] 杨洪涛. 样本熵改进小波包阈值去噪的轴承故障诊断[J]. 组合机床与自动化加工技术, 2020(1): 79-82.

    YANG H T. Bearing fault diagnosis based on wavelet packet threshold de-noise algorithm improved by sample entropy[J]. Modular Machine Tool & Automatic Manufacturing Technique, 2020(1): 79-82. (in Chinese)
    [15] 史庆军, 郭晓振, 刘德胜. 基于特征量融合和支持向量机的轴承故障诊断[J]. 电子测量与仪器学报, 2019, 33(10): 104-111.

    SHI Q J, GUO X Z, LIU D S. Bearing fault diagnosis based on feature fusion and support vector machine[J]. Journal of Electronic Measurement and Instrumentation, 2019, 33(10): 104-111. (in Chinese)
    [16] 张龙, 宋成洋, 邹友军, 等. 基于VMD多特征融合与PSO-SVM的滚动轴承故障诊断[J]. 机械设计与研究, 2019, 35(6): 96-104.

    ZHANG L, SONG C Y, ZOU Y J, et al. A rolling bearingfault diagnosis method bsaed on VMD multi feature fusion and PSO-SVM[J]. Machine Design & Research, 2019, 35(6): 96-104. (in Chinese)
  • 加载中
图(4) / 表(2)
计量
  • 文章访问数:  38
  • HTML全文浏览量:  21
  • PDF下载量:  5
  • 被引次数: 0
出版历程
  • 收稿日期:  2021-10-17
  • 刊出日期:  2024-05-31

目录

    /

    返回文章
    返回