内核噪声拓展自适应多元变分模态分解及机械复合故障诊断应用

doi:10.3901/JME.2025.11.171

机械工程学报 ›› 2025, Vol. 61 ›› Issue (11): 171-182.doi: 10.3901/JME.2025.11.171

• 机械动力学 • 上一篇

扫码分享

内核噪声拓展自适应多元变分模态分解及机械复合故障诊断应用

孙世博¹, 袁静¹, 赵倩¹, 蒋会明¹, 魏颖²

1. 上海理工大学机械工程学院上海 200093;
2. 上海无线电设备研究所上海 201109

收稿日期:2024-06-14 修回日期:2024-12-01 发布日期:2025-07-12
作者简介:孙世博，男，1999年出生。主要研究方向为机械设备故障诊断和故障特征提取。E-mail：sunshibo_cc@163.com;袁静(通信作者)，女，1983年出生，博士，教授。主要研究方向为机械设备故障诊断、动态信号处理、故障特征提取。E-mail：yuanjing@usst.edu.cn
基金资助:
国家自然科学基金(52375111，52205113)和上海市青年科技英才扬帆计划(21YF1430600)资助项目。

Kernel Noise-expanded Self-adaptive Multivariate Variational Mode Decomposition and Its Application to Mechanical Compound Fault Diagnosis

SUN Shibo¹, YUAN Jing¹, ZHAO Qian¹, JIANG Huiming¹, WEI Ying²

1. School of Mechanical Engineering, University of Shanghai for Science and Technology, Shanghai 200093;
2. Shanghai Radio Equipment Institute, Shanghai 201109

Received:2024-06-14 Revised:2024-12-01 Published:2025-07-12

摘要/Abstract

摘要： 为解决复合故障特征信息难以有效同步获取问题，提出一种内核噪声拓展自适应多元变分模态分解的机械复合故障诊断方法。首先，利用核主成分分析和奇异熵增量曲率谱设计多元噪声同步估计技术，通过对多元信号高维空间模型进行降维和重构处理，有效地从非线性原始信号中同步获取多元噪声分量。其次，利用同步估计的多元噪声分量构造内核噪声拓展模型作为输入数据源，提高相应分解层带宽选取准确性以改善模态混淆现象，为复合故障特征有效分离提供解决方案。同时，结合带宽平衡参数更新策略，为内核噪声拓展模型设计用于递归并行分解的新目标函数，自适应选择最优分解层数和各分解层多元本征模态函数(Intrinsic mode function，IMF)带宽平衡参数。最终，输出完整多元期望IMF集合以同步提取复合故障特征。由工程实例结果表明，所提方法可有效应用于机车走行部轴承和星载天线指向机构谐波减速器复合故障诊断。

关键词: 多元变分模态分解, 核主成分分析, 多元噪声利用, 同步提取, 复合故障诊断

Abstract: In order to solve the difficulties of effectively and synchronously access to compound fault feature information, a kernel noise-expanded self-adaptive multivariate variational mode decomposition is proposed as a mechanical compound fault diagnosis method. First, kernel principal component analysis and curvature spectrum of increment of singular entropy are used to design multivariate noise synchronization estimation technique, which effectively obtains multivariate noise components from nonlinear original signals synchronously by dimensionality reduction and reconstructing process for the high-dimensional space model of multivariate signals. Second, the synchronously estimated multivariate noise components are used to construct a kernel noise-expanded model as the input data source to improve the selection accuracy of bandwidths of the corresponding decomposition layer and to improve mode mixing phenomenon and provide a solution for the effective separation of compound fault features. Meanwhile, combining with a bandwidth balance parameter updating strategy, a new objective function for recursive parallel decomposition is designed for the kernel noise-expanded model, and the optimal number of decomposition layers and the multivariate intrinsic mode function (IMF) bandwidth balance parameter of each decomposition layer are selected adaptively. At last, complete multivariate expected IMF sets are output to synchronize extraction of compound fault features. The results of engineering cases show that the proposed method can be effectively used for compound fault diagnosis including locomotive rolling bearing, and harmonic reducer of a pointing mechanism for spaceborne antenna.

Key words: multivariate variational mode decomposition, kernel principal component analysis, multivariate noise utilization, synchronous extraction, compound fault diagnosis

中图分类号:

TH17

孙世博, 袁静, 赵倩, 蒋会明, 魏颖. 内核噪声拓展自适应多元变分模态分解及机械复合故障诊断应用[J]. 机械工程学报, 2025, 61(11): 171-182.

SUN Shibo, YUAN Jing, ZHAO Qian, JIANG Huiming, WEI Ying. Kernel Noise-expanded Self-adaptive Multivariate Variational Mode Decomposition and Its Application to Mechanical Compound Fault Diagnosis[J]. Journal of Mechanical Engineering, 2025, 61(11): 171-182.

参考文献

[1] 王国彪，何正嘉，陈雪峰，等. 机械故障诊断基础研究“何去何从”[J]. 机械工程学报，2013，49(1)：63-72. WANG Guobiao，HE Zhengjia，CHEN Xuefeng，et al. Basic research on machinery fault diagnosis—what is the prescription[J]. Journal of Mechanical Engineering, 2013，49(1)：63-72.
[2] ZHANG Suofeng，WANG Yanxue，HE Shuilong，et al. Bearing fault diagnosis based on variational mode decomposition and total variation denoising[J]. Measurement Science and Technology，2016，27(7)： 075101.
[3] 袁静，何正嘉，訾艳阳. 基于提升多小波的机电设备复合故障分离和提取[J]. 机械工程学报，2010，46(1)：79-85. YUAN Jing，HE Zhengjia，ZI Yanyang. Separation and extraction of electromechanical equipment compound faults using lifting multiwavelets[J]. Journal of Mechanical Engineering，2010，46(1)：79-85.
[4] 袁静，訾艳阳，倪修华，等. 改进集成噪声重构经验模式分解的微弱时频特征增强方法及应用[J]. 机械工程学报，2016，52(19)：88-94. YUAN Jing，ZI Yanyang，NI Xiuhua，et al. Weak time-frequent feature enhancement method using improved ensemble noise-reconstructed empirical mode decomposition and its application[J]. Journal of Mechanical Engineering，2016，52(19)：88-94.
[5] 雷亚国，贾峰，孔德同，等. 大数据下机械智能故障诊断的机遇与挑战[J]. 机械工程学报，2018，54(5)： 94-104. LEI Yaguo，JIA Feng，KONG Detong，et al. Opportunities and challenges of machinery intelligent fault diagnosis in big data era[J]. Journal of Mechanical Engineering，2018，54(5)：94-104.
[6] REHMAN N U，MANDIC D P. Multivariate empirical mode decomposition[J]. Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences，2010，466(2117)：1291-1302.
[7] REHMAN N U，AFTAB H. Multivariate variational mode decomposition[J]. IEEE Transactions on Signal Processing，2019，67(23)：6039-6052.
[8] LV Yong，YUAN Rui，SONG Gangbing，et al. Multivariate empirical mode decomposition and its application to fault diagnosis of rolling bearing[J]. Mechanical Systems and Signal Processing，2016，81：219-234.
[9] AHRABIAN A，LOONEY D，STANKOVIĆ L，et al. Synchrosqueezing-based time-frequency analysis of multivariate data[J]. Signal Processing，2015，106：331-341.
[10] ENSHAEIFAR S，KOUCHAKI S，TOOK C C，et al. Quaternion singular spectrum analysis of electroencephalogram with application in sleep analysis[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering，2016，24(1)：57-67.
[11] 胡超凡，王衍学. 基于张量分解的滚动轴承复合故障多通道信号降噪方法研究[J]. 机械工程学报，2019，55(12)：50-57. HU Chaofan，WANG Yanxue. Research on multi-channel signal denoising method for multiple faults diagnosis of rolling element bearings based on tensor factorization[J]. Journal of Mechanical Engineering，2019，55(12)：50-57.
[12] YUAN Jing，SONG Zhitian，JIANG Huiming，et al. The Msegram: A useful multichannel feature synchronous extraction tool for detecting rolling bearing faults[J]. Mechanical Systems and Signal Processing，2023，187：109923.
[13] REHMAN N U，MANDIC D P. Filter bank property of multivariate empirical mode decomposition[J]. IEEE Transactions on Signal Processing，2011，59(5)：2421-2426.
[14] ZISOU C A，APOSTOLIDIS G K，HADJILEONTIADIS L J. Noise-assisted multivariate variational mode decomposition[C]// IEEE International Conference on Acoustics，Speech and Signal Processing (ICASSP). Electr Network：2021 IEEE，Jun 06-11，2021：5090-5094.
[15] SONG Qiuyu，JIANG Xingxing，WANG Shuang，et al. Self-adaptive multivariate variational mode decomposition and its application for bearing fault diagnosis[J]. IEEE Transactions on Instrumentation and Measurement，2022，71：3503913.
[16] DRAGOMIRETSKIY K，ZOSSO D. Variational mode decomposition[J]. IEEE Transactions on Signal Processing，2014，62(3)：531-544.
[17] ZHONG Shangping，CHEN Daya，XU Qiaofen，et al. Optimizing the Gaussian kernel function with the formulated kernel target alignment criterion for two-class pattern classification[J]. Pattern Recognition，2013，46(7)：2045-2054.
[18] YUAN Jing，XU Chong，ZHAO Qian, et al. High-fidelity noise-reconstructed empirical mode decomposition for mechanical multiple and weak fault extractions[J]. ISA Transactions，2022，129：380-397.
[19] MOHAN S，TSAI C W. Derivation of vertical concentration profile for nonuniform sediment in suspension using Shannon entropy[J]. Chaos, Solitons & Fractals，2024，178：114313.
[20] CHEN Shiqian，YANG Yang，PENG Zhike，et al. Adaptive chirp mode pursuit: Algorithm and applications[J]. Mechanical Systems and Signal Processing，2019，116：566-584.
[21] LI Jimeng，YAO Xifeng，WANG Hui，et al. Periodic impulses extraction based on improved adaptive VMD and sparse code shrinkage denoising and its application in rotating machinery fault diagnosis[J]. Mechanical Systems and Signal Processing，2019，126：568-589.
[22] WANG Yanxue，LIANG Ming. Identification of multiple transient faults based on the adaptive spectral kurtosis method[J]. Journal of Sound and Vibration，2012，331(2)：470-486.
[23] WANG Xia，WANG Yaomin，SHI Xinling，et al. A probabilistic multimodal optimization algorithm based on Buffon principle and Nyquist sampling theorem for noisy environment[J]. Applied Soft Computing，2021，104：107068.
[24] NAZARI M，SAKHAEI S M. Successive variational mode decomposition[J]. Signal Processing，2020，174：107610.
[25] ANTONI J. Fast computation of the kurtogram for the detection of transient faults[J]. Mechanical Systems and Signal Processing，2007，21(1)：108-124.
[26] WANG Yanxue，MARKERT R. Filter bank property of variational mode decomposition and its applications[J]. Signal Processing，2016，120：509-521.
[27] LI Xinzi，SONG Chaosheng，ZHU Caichao，et al. Load analysis of thin-walled flexible bearing in harmonic reducer considering assembly with flexspline and cam[J]. Mechanism and Machine Theory，2023，180：105154.
[28] WANG Dong，ZHONG Jingjing，SHEN Changqing，et al. Correlation dimension and approximate entropy for machine condition monitoring：revisited[J]. Mechanical Systems and Signal Processing，2021，152：107497.

内核噪声拓展自适应多元变分模态分解及机械复合故障诊断应用

Kernel Noise-expanded Self-adaptive Multivariate Variational Mode Decomposition and Its Application to Mechanical Compound Fault Diagnosis

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 6

编辑推荐

Metrics

本文评价

[1]	杨阳, 胡明辉, 江志农, 卢子元. 多分量同步提取变换驱动的无键相状态下中介轴承故障诊断[J]. 机械工程学报, 2024, 60(16): 83-97.
[2]	宋立业, 范抑伶, 王燚增. 基于KPCA与IHHO-LSSVM的电力变压器故障诊断方法研究^*[J]. 电气工程学报, 2022, 17(1): 95-103.
[3]	黄伟国, 李仕俊, 毛磊, 马玉强, 王俊, 沈长青, 阙红波, 朱忠奎. 多源稀疏优化方法研究及其在齿轮箱复合故障检测中的应用[J]. 机械工程学报, 2021, 57(7): 87-99.
[4]	王庆锋, 卫炳坤, 刘家赫, 马文生, 许述剑. 一种数据驱动的旋转机械早期故障检测模型构建和应用研究[J]. 机械工程学报, 2020, 56(16): 22-32.
[5]	胡超凡, 王衍学. 基于张量分解的滚动轴承复合故障多通道信号降噪方法研究[J]. 机械工程学报, 2019, 55(12): 50-57.
[6]	李太福;易军;苏盈盈;胡文金;高婷. 基于KPCA子空间虚假邻点判别的非线性建模的变量选择[J]. , 2012, 48(10): 192-198.