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

doi:10.3901/JME.2025.11.171

Abstract

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

CLC Number:

TH17

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.

References

[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.