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

单向阀微弱内泄漏故障征提取与模式识别研究

熊力 刘宁 童成彪 程军圣

熊力,刘宁,童成彪, 等. 单向阀微弱内泄漏故障征提取与模式识别研究[J]. 机械科学与技术,2024,43(5):756-764 doi: 10.13433/j.cnki.1003-8728.20220293
引用本文: 熊力,刘宁,童成彪, 等. 单向阀微弱内泄漏故障征提取与模式识别研究[J]. 机械科学与技术,2024,43(5):756-764 doi: 10.13433/j.cnki.1003-8728.20220293
XIONG Li, LIU Ning, TONG Chengbiao, CHENG Junsheng. Research on Feature Extraction and Pattern Recognition of Tiny Internal Leakage of Check Valve[J]. Mechanical Science and Technology for Aerospace Engineering, 2024, 43(5): 756-764. doi: 10.13433/j.cnki.1003-8728.20220293
Citation: XIONG Li, LIU Ning, TONG Chengbiao, CHENG Junsheng. Research on Feature Extraction and Pattern Recognition of Tiny Internal Leakage of Check Valve[J]. Mechanical Science and Technology for Aerospace Engineering, 2024, 43(5): 756-764. doi: 10.13433/j.cnki.1003-8728.20220293

单向阀微弱内泄漏故障征提取与模式识别研究

doi: 10.13433/j.cnki.1003-8728.20220293
基金项目: 湖南省自然科学基金项目(2020JJ4045)与湖南省重点研发计划(2022NK2028)
详细信息
    作者简介:

    熊力,博士研究生,18390916939@139.com

    通讯作者:

    童成彪,教授,博士,tongcb@163.com

  • 中图分类号: TH165.3

Research on Feature Extraction and Pattern Recognition of Tiny Internal Leakage of Check Valve

  • 摘要: 单向阀被广泛应用于工程机械、农业机械、军事车辆液压系统中,泄漏是单向阀的常见故障。本文提出了一种基于时频分解的多源多域、多尺度特征提取与机器学习的单向阀微弱内泄漏故障诊断方法。对4类微弱内泄漏故障的振动信号和压力信号进行经验模态分解;采用时域、频域以及时频域的奇异值、波形因子、熵值等方法进行特征提取并构造故障特征向量;基于粒子群-支持向量机进行单向阀内泄漏故障模式识别。实验结果表明该方法能有效地检测单向阀内泄漏,模式识别准确率达到90%以上。本文为单向阀内泄漏量预测研究奠定了基础,具有较好的工程应用前景。
  • 图  1  单向阀泄漏故障诊断流程图

    Figure  1.  Flowchart of one-way valve leakage fault diagnosis

    图  2  实验用单向阀阀芯

    Figure  2.  One-way valve spools for experiment

    图  3  液压故障诊断实验台

    Figure  3.  Test platform for hydraulic troubleshooting

    图  4  被测对象和振动测点布置

    Figure  4.  Arrangement of measured objects and vibration measurement points

    图  5  偏心0.20 mm振动信号时域图

    Figure  5.  Time domain graph of vibration signal with 0.20 mm eccentricity

    图  6  偏心0.20 mm的振动信号EEMD分解

    Figure  6.  EEMD decomposition of vibration signal with 0.20 mm eccentricity

    图  7  压力信号各故障状态的波形因子曲线

    Figure  7.  Waveform factor curves for each fault state of the pressure signal

    图  8  压力信号各故障状态的精细广义多尺度熵曲线图

    Figure  8.  Fine generalized multiscale entropy curve for each fault state of the pressure signal

    图  9  PSO-SVM算法流程图

    Figure  9.  Flowchart of PSO-SVM algorithm

    图  10  振动信号泄漏检测结果

    Figure  10.  Leakage detection results of vibration signal

    图  11  压力信号泄漏检测结果

    Figure  11.  Leakage detection results of pressure signal

    图  12  振动信号泄漏模式识别结果

    Figure  12.  Leakage pattern recognition results of vibration signal

    图  13  压力信号泄漏模式识别结果

    Figure  13.  Leakage pattern recognition results of pressure signal

    表  1  各故障状态的平均泄漏量

    Table  1.   Average leakage rate of each fault state

    状态 平均泄漏量/(mL·s−1 故障 平均泄漏量/(mL·s−1
    1 0.022 6 8.552
    2 0.162 7 19.757
    3 0.196 8 0.224
    4 0.565 9 1.661
    5 0.079 10 11.552
    下载: 导出CSV

    表  2  振动原始信号与IMF分量的平均距离相关系数

    Table  2.   Mean distance correlation coefficients between vibration raw signals and IMF components

    状态平均距离相关系数
    IMF1IMF2IMF3IMF4IMF5IMF6IMF7IMF8IMF9
    10.2360.2020.2250.3970.5230.3660.1920.1390.127
    40.1530.1370.1650.3610.7320.3220.1450.1400.108
    70.2250.1930.2320.3610.5980.3750.1800.1580.133
    100.1050.1010.2420.7630.3680.1560.1080.0970.109
    下载: 导出CSV

    表  3  振动原始信号与IMF分量的平均能量占比

    Table  3.   Average energy ratio of vibration raw signal with IMF component

    状态平均能量占比
    IMF1IMF2IMF3IMF4IMF5IMF6IMF7IMF8IMF9
    10.0090.0640.1710.2130.3530.2010.0550.0330.011
    40.0320.0220.1320.1950.5090.1750.0250.0130.005
    70.0810.0530.1670.1980.3910.1760.0490.0270.010
    100.0230.0160.0730.6670.2340.0560.0200.0100.004
    下载: 导出CSV

    表  4  故障状态和振动信号奇异值

    Table  4.   Fault states and singular values of vibration signal

    状态 奇异值
    ${s'}_{ 3}$ $ {s'}_{ 4} $ $ {s'}_{ 5} $ $ {s'}_{ 6} $
    1 0.008 0.037 0.113 0.082
    4 0.016 0.149 0.223 0.056
    7 0.018 0.073 0.026 0.059
    10 0.039 0.455 0.228 0.055
    下载: 导出CSV

    表  5  故障状态下振动信号的频域特征

    Table  5.   Frequency-domain characteristics of vibration signals under fault conditions

    状态 频域特征
    $ FC $ $ MS F $ $ RV F $
    1 0.794 0.678 0.628
    4 0.285 0.304 0.317
    7 0.518 0.393 0.337
    10 0.339 0.436 0.478
    下载: 导出CSV

    表  6  故障状态的能量熵

    Table  6.   Energy entropy of fault states

    状态 ${H}_{{\rm{EN}}}$ 状态 ${H}_{{\rm{EN}}}$
    1 0.799 3 0.374
    2 0.168 4 0.021
    下载: 导出CSV

    表  7  故障状态与精细广义多尺度熵

    Table  7.   Fault states and fine generalized multiscale entropy

    状态 $ R{MS E}_{{\sigma }^{2}} $
    $ \mathrm{\tau }=2 $ $ \mathrm{\tau }=3 $ $ \mathrm{\tau }=4 $ $ \mathrm{\tau }=5 $
    1 0.818 0.799 0.831 0.875
    4 0.535 0.489 0.415 0.373
    7 0.620 0.557 0.495 0.489
    10 0.395 0.330 0.302 0.320
    下载: 导出CSV

    表  8  信号故障特征向量在两种预测模型中的准确率

    Table  8.   Accuracy of each signal fault eigenvector in both prediction models

    识别模型 准确率/%
    振动信号故障
    特征向量
    压力信号故障
    特征向量
    泄漏检测 98 100
    泄漏故障分类 70 94
    下载: 导出CSV
  • [1] JIN Y, SHAN C Z, WU Y, et al. Fault diagnosis of hydraulic seal wear and internal leakage using wavelets and wavelet neural network[J]. IEEE Transactions on Instrumentation and Measurement, 2019, 68(4): 1026-1034. doi: 10.1109/TIM.2018.2863418
    [2] LEI Y F, JIANG W L, JIANG A Q, et al. Fault diagnosis method for hydraulic directional valves integrating PCA and XGBoost[J]. Processes, 2019, 7(9): 589. doi: 10.3390/pr7090589
    [3] ZHANG Z T, HOU C G, LI X Y, et al. Research on the diagnosis method of reciprocating compressor valve leakage fault with vibration signal[C]// ASME 2019 International Mechanical Engineering Congress and Exposition. Salt Lake City: ASME, 2019.
    [4] TRAN V T, ALTHOBIANI F, TINGA T, et al. Single and combined fault diagnosis of reciprocating compressor valves using a hybrid deep belief network[J]. Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science, 2018, 232(20): 3767-3780.
    [5] 张丹威, 王晓东, 黄国勇, 等. EMD辅助相关系数SVD的单向阀故障诊断[J]. 机械科学与技术, 2019, 38(6): 846-854.

    ZHANG D W, WANG X D, HUANG G Y, et al. Fault diagnosis of check valve with EMD and auxiliary correlation coefficient SVD[J]. Mechanical Science and Technology for Aerospace Engineering, 2019, 38(6): 846-854. (in Chinese)
    [6] WATTON J, LUCCA-NEGRO O, STEWART J C. An on-line approach to fault diagnosis of fluid power cylinder drive systems[J]. Proceedings of the Institution of Mechanical Engineers, Part I: Journal of Systems and Control Engineering, 1994, 208(4): 249-262.
    [7] 熊鹏博, 王晓东. 多时域特征与SVM的隔膜泵单向阀故障诊断[J]. 机械科学与技术, 2019, 38(4): 538-543.

    XIONG P B, WANG X D. Fault diagnosis of check valve for diaphragm pump with multi-time domain feature and SVM[J]. Mechanical Science and Technology for Aerospace Engineering, 2019, 38(4): 538-543. (in Chinese)
    [8] 牟竹青, 冯早, 黄国勇, 等. 自适应随机共振和DEMD的单向阀早期故障诊断[J]. 机械科学与技术, 2018, 37(4): 537-544.

    MU Z Q, FENG Z, HUANG G Y, et al. Early fault diagnosis of check valve with adaptive stochastic resonance and DEMD[J]. Mechanical Science and Technology for Aerospace Engineering, 2018, 37(4): 537-544. (in Chinese)
    [9] LIN W G, WU S E, SHI Y F, et al. Research on non-intrusive acoustic monitoring for valve internal leakage[C]// 2017 29th Chinese Control And Decision Conference (CCDC). Chongqing: IEEE, 2017: 7796-7801.
    [10] CAFFREY C M, SILLANPÄÄ T, HUOVILA H, et al. Energy autonomous wireless valve leakage monitoring system with acoustic emission sensor[J]. IEEE Transactions on Circuits and Systems I:Regular Papers, 2017, 64(11): 2884-2893. doi: 10.1109/TCSI.2017.2702387
    [11] ZHU S B, LI Z L, LI X, et al. Convolutional neural networks-based valve internal leakage recognition model[J]. Measurement, 2021, 178: 109395. doi: 10.1016/j.measurement.2021.109395
    [12] SIM H Y, RAMLI R, SAIFIZUL A, et al. Detection and estimation of valve leakage losses in reciprocating compressor using acoustic emission technique[J]. Measurement, 2020, 152: 107315. doi: 10.1016/j.measurement.2019.107315
    [13] TONG C , SEPEHRI N , ZHOU J. Root cause detection of leakage in check valves using multi-scale signal analysis[J]. Journal of Mechanical Science and Technology, 2023. doi: 10.1007/s12206-022-1207-2
    [14] 李宝庆, 程军圣, 吴占涛, 等. 自适应最稀疏时频分析方法的分解能力研究[J]. 湖南大学学报(自然科学版), 2016, 43(2): 43-47.

    LI B Q, CHEN J S, WU Z T, et al. Research on the decomposing ability of the adaptive and sparsest time-frequency analysis method[J]. Journal of Hunan University (Natural Sciences), 2016, 43(2): 43-47. (in Chinese)
    [15] HOSSINE G, KATIA K. Analyze and fault diagnosis of double star induction motor using wavelet transformation[C]// International Conference in Artificial Intelligence in Renewable Energetic Systems. Berlin: Springer, 2021.
    [16] LI B B, ZHAO Q, LI H Y, et al. Analysis method of the cavitation vibration signals in poppet valve based on EEMD[J]. Advances in Mechanical Engineering, 2021, 13(2): 168781402199811.
    [17] SZÉKELY G J, RIZZO M L, BAKIROV N K. Measuring and testing dependence by correlation of distances[J]. The Annals of Statistics, 2007, 35(6): 2769-2794.
    [18] 张慧娟, 李冬. 相关系数判决的EMD在振动数据趋势项提取中的应用[J]. 舰船电子工程, 2018, 38(5): 159-163. doi: 10.3969/j.issn.1672-9730.2018.05.038

    ZHANG H J, LI D. Application of EMD of correlation coefficient judgment in the extraction of vibration data trend[J]. Ship Electronic Engineering, 2018, 38(5): 159-163. (in Chinese) doi: 10.3969/j.issn.1672-9730.2018.05.038
    [19] TIAN Y, MA J, LU C, et al. Rolling bearing fault diagnosis under variable conditions using LMD-SVD and extreme learning machine[J]. Mechanism and Machine Theory, 2015, 90: 175-186. doi: 10.1016/j.mechmachtheory.2015.03.014
    [20] 许迪, 葛江华, 王亚萍, 等. 量子遗传算法优化的SVM滚动轴承故障诊断[J]. 振动、测试与诊断, 2018, 38(4): 843-851.

    XU D, GE J H, WANG Y P, et al. Rolling bearing fault diagnosis of SVM based on improved quantum genetic algorithm[J]. Journal of Vibration, Measurement & Diagnosis, 2018, 38(4): 843-851. (in Chinese)
    [21] 赵柄锡, 冀大伟, 袁奇, 等. 采用时域与时频域联合特征空间的转子系统碰磨故障诊断[J]. 西安交通大学学报, 2020, 54(1): 75-84. doi: 10.7652/xjtuxb202001010

    ZHAO B X, JI D W, YUAN Q, et al. Rubbing fault diagnosis of rotor system based on combined feature space in time and time-frequency domains[J]. Journal of Xi'an Jiaotong University, 2020, 54(1): 75-84. (in Chinese) doi: 10.7652/xjtuxb202001010
    [22] 王永坚, 胡欢欢, 李品芳. EEMD能量熵和奇异值熵与SVM融合的船用空压机故障诊断[J]. 上海海事大学学报, 2020, 41(4): 95-102.

    WANG Y J, HU H H, LI P F. Fault diagnosis for marine air compressors by fusion of EEMD energy entropy and singular value entropy with SVM[J]. Journal of Shanghai Maritime University, 2020, 41(4): 95-102. (in Chinese)
    [23] LIU Y X, LIN Y F, WANG J, et al. Refined generalized multiscale entropy analysis for physiological signals[J]. Physica A:Statistical Mechanics and its Applications, 2018, 490: 975-985. doi: 10.1016/j.physa.2017.08.047
    [24] LI B C, TONG R, KANG J S, et al. Bearing fault diagnosis using synthetic quantitative index-based adaptive underdamped stochastic resonance[J]. Mathematical Problems in Engineering, 2021, 2021: 8888079.
    [25] 李莎, 潘宏侠, 都衡. 基于EEMD信息熵和PSO-SVM的自动机故障诊断[J]. 机械设计与研究, 2014, 30(6): 26-29.

    LI S, PAN H X, DU H. Automaton fault diagnosis based on EEMD information entropy and PSO-SVM[J]. Machine Design and Research, 2014, 30(6): 26-29. (in Chinese)
  • 加载中
图(13) / 表(8)
计量
  • 文章访问数:  53
  • HTML全文浏览量:  18
  • PDF下载量:  17
  • 被引次数: 0
出版历程
  • 收稿日期:  2021-10-24
  • 刊出日期:  2024-05-31

目录

    /

    返回文章
    返回