自适应变分模式提取的轴承故障诊断方法

摘要
图/表
参考文献(18)
相关文章 (15)

全文: PDF (2780 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要变分模式提取(variational mode extraction, VME)能够从复杂信号中提取特定的模式分量，但其在轴承故障诊断中的应用潜力受到初始中心频率和平衡参数的影响。因此，为了克服VME在轴承故障诊断应用中超参数的设置问题，深入探究VME模型中心频率迭代更新过程，发现中心频率收敛趋势现象并通过理论证明其存在性，由此提出中心频率定位策略，可自适应地确定目标中心频率。为了最大化匹配故障信息，构造基于故障特征幅值比的平衡参数优化策略，能够优化目标分量的带宽。以上中心频率定位策略和平衡参数优化策略，构成自适应变分模式提取的故障诊断方法，该方法能够在无需预设初始中心频率及平衡参数的情况下自适应提取故障相关分量。仿真和两个实验案例分析结果验证所提方法在轴承故障诊断领域相比于连续变分模式分解、经验模式分解和快速谱峭度方法更具有效性和优越性。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	王鑫
	江星星
	宋秋昱
	杜贵府
	朱忠奎

关键词 ：变分模式提取, 中心频率, 平衡参数, 滚动轴承, 故障诊断

Abstract：Variational mode extraction (VME) can extract specific mode component from the complicated signal, but its application in bearing fault diagnosis is affected by initial center frequency and balance parameter. Therefore, in order to overcome the problem of setting hyperparameters in the application of VME in bearing fault diagnosis, the iterative updating process of center frequency of VME model is deeply explored to find the convergence trend of center frequency whose rationality is proved by theory. Then, a center frequency location strategy is formulated to adaptively determine the target center frequency. In order to match the maximize fault information, a balance parameter optimization strategy based on the ratio of fault characteristic amplitude is constructed, which can optimize the bandwidth of the target mode. The above center frequency location and balance parameter optimization strategy constitute a fault diagnosis method based on adaptive variational mode extraction, which can adaptively extract fault related components without presetting the initial center frequency and balance parameter. Compared with successive variational mode decomposition, empirical mode decomposition and fast Kurtogram method, the proposed method is more effective and superior in the field of bearing fault diagnosis.

Key words： variational mode extraction center frequency balance parameter rolling bearing fault diagnosis

收稿日期: 2022-08-09 出版日期: 2023-08-15

引用本文:

王鑫，江星星，宋秋昱，杜贵府，朱忠奎. 自适应变分模式提取的轴承故障诊断方法[J]. 振动与冲击, 2023, 42(15): 83-91.
WANG Xin, JIANG Xingxing, SONG Qiuyu, DU Guifu, ZHU Zhongkui. Bearing fault diagnosis method based on adaptive variational mode extraction. JOURNAL OF VIBRATION AND SHOCK, 2023, 42(15): 83-91.

链接本文:

http://jvs.sjtu.edu.cn/CN/ 或 http://jvs.sjtu.edu.cn/CN/Y2023/V42/I15/83

[1] 王贡献, 张淼, 胡志辉, 等. 基于多尺度均值排列熵和参数优化支持向量机的轴承故障诊断[J]. 振动与冲击, 2022, 41(01): 221-228.
WANG Gongxian, ZHANG Miao, HU Zhihui, et al. Bearing fault diagnosis based on multi-scale mean permutation entropy and parametric optimization SVM[J]. Journal of Vibration and Shock, 2022, 41(01): 221-228.
[2] 王思豪, 王晓东, 李卓睿, 等. 一种改进的MP-WVD滚动轴承信号时频分析方法[J]. 电子测量与仪器学报, 2020, 34(12): 133-143.
WANG Sihao, WANG Xiaodong, LI Zhuorui, et al. lmproved MP-WVD time-frequency analysis method for rolling bearing signal [J]. Journal of Electronic Measurement and Instrumentation, 2020, (12): 133-143.
[3] 陈仁祥, 周君, 胡小林, 等. 基于深度Q学习和连续小波变换的旋转机械故障诊断方法[J]. 振动工程学报, 2021, 34(05): 1092-1100.
CHEN Renxiang, ZHOU Jun, HU Xiaolin, et al. Fault diagnosis method of rotating machinery based on deep Q-learning and continuous wavelet transform [J]. Journal of Vibration Engineering, 2021, 34(05): 1092-1100.
[4] WANG S B, SELESNICK I W, CAI G G, et al. Synthesis versus analysis priors via heneralized minimax-concave penalty for sparsity-assisted machinery fault diagnosis[J], Mechanical Systems and Signal Processing, 2019, 127: 202-233.
[5] 郑近德, 王兴龙, 潘海洋, 等. 基于自适应自相关谱峭度图的滚动轴承故障诊断方法[J]. 中国机械工程, 2021, 32(07): 778-785+792.
ZHENG Jinde, WANG Xinglong, PAN Haiyang, et al. Rolling bearing fault diagnosis method based on adaptive Autogram [J]. China Mechanical Engineering, 2021, 32(07): 778-785+792.
[6] FENG Z P, ZHANG D, ZUO M J. Adaptive mode decomposition methods and their applications in signal analysis for machinery fault diagnosis: a review with examples [J]. IEEE Access, 2017, 5: 24301-24331.
[7] HUANG N, SHEN Z, LONG S, et al. The empirical mode decomposition and the hilbert spectrum for nonlinear and nonstationary time series analysis [J]. Proceedings Mathematical Physical and Engineering Sciences, 1998, 454(1971): 903-995.
[8] 李政, 张炜, 明安波, 等. 基于IEWT和MCKD的滚动轴承故障诊断方法[J]. 机械工程学报, 2019, 55(23): 136-146.
LI Zheng, ZHANG Wei, MING Anbo, et al. A novel fault diagnosis method based on improved empirical wavelet transform and maximum correlated Kurtosis deconvolution for rolling element bearing [J]. Journal of Mechanical Engineering, 2019, 55(23): 136-146.
[9] 刘少康, 武英杰, 安伟伦, 等. 基于声音信号和改进MS-LMD的风电齿轮箱故障诊断[J]. 振动与冲击, 2021, 40(11): 230-239+251.
LIU Shaokang, WU Yingjie, AN Weilun, et al. Wind turbine gearbox fault diagnosis based on sound signal and improved MS-LMD [J]. Journal of Vibration and Shock, 2021, 40(11): 230-239+251.
[10] DRAGOMIRETSKIY K, ZOSSO D. Variational mode decomposition [J]. IEEE Transactions on Signal Processing, 2013, 62(3): 531-544.
[11] NAZARI M, SAKHAEI S. Variational mode extraction: a new efficient method to derive respiratory signals from ECG[J]. IEEE Journal of Biomedical and Health Informatics, 2018, 22(4): 1059-1067.
[12] GUO Y J, JIANG S F, YANG Y D, et al. Gearbox fault diagnosis based on improved variational mode extraction[J]. Sensors, 2022, 22(5), 1779.
[13] NAZARI M, SAKHAEI S. Successive variational mode decomposition[J]. Signal Processing, 2020, 174, 107610.
[14] ZHONG X, XIA T, MEI Q. A parameter-adaptive VME method based on particle swarm optimization for bearing fault diagnosis[J]. Experimental Techniques, 2022. https://doi.org/10.1007/s40799-022-00553-w.
[15] NI Q, JI J C, FENG K, et al. A fault information-guided variational mode decomposition (FIVMD) method for rolling element bearings diagnosis [J]. Mechanical Systems and Signal Processing, 2021, 164, 108216.
[16] JIANG X X, WANG J, SHI J J, et al. A coarse-to-fine decomposing strategy of VMD for extraction of weak repetitive transients in fault diagnosis of rotating machines [J]. Mechanical Systems and Signal Processing, 2019, 116, 668-692.
[17] 程阳洋, 李锋, 汤宝平, 等. 量子基因链编码双向神经网络用于旋转机械剩余使用寿命预测[J]. 仪器仪表学报, 2020, 41(07): 164-174.
CHENG Yangyang, LI Feng, TANG Baoping, et al. Quantum gene chain coding bidirectional neural network for residual useful life prediction of rotating machinery [J]. Chinese Journal of Scientific Instrument, 2020, 41(07): 164-174.
[18] JIANG X X, SONG Q Y, WANG H E, et al. Central frequency mode decomposition and its applications to the fault diagnosis of rotating machines [J]. Mechanism and Machine Theory, 2022, 174, 104919.