An optimized variational mode decomposition method and its application in vibration signal analysis of bearings

Gu, Jun; Peng, Yuxing; Lu, Hao; Chang, Xiangdong; Cao, Shuang; Chen, Guoan; Cao, Bobo

doi:10.1177/14759217211057444

Cited by 15 publications

(6 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…38 On the other hands, adaptive signal decomposition methods can decompose original signal to directly obtain the information of target signal, which include empirical mode decomposition (EMD), wavelet packet transform (WPT), variational mode decomposition (VMD), and so on. 39 In addition, there are some improved methods, such as ensemble empirical mode decomposition (EEMD), complementary ensemble empirical mode decomposition (CEEMD), wavelet packet transform with Daubechies 3 (WPT-db3), and wavelet packet transform with Symlets 3 (WPT-sym3). However, it only reduces noise interference and achieves unsatisfactory performance due to the weak fault feature of centrifugal compressor, which need to further improvements to achieve accurate signal estimation.…”

Section: Theoretical Backgroundmentioning

confidence: 99%

Fault feature recognition of centrifugal compressor with cracked blade based on SNR estimation and adaptive stochastic resonance

Song

et al. 2022

Structural Health Monitoring

View full text Add to dashboard Cite

The centrifugal compressor is widely used in modern industry, and the blades are prone to crack due to complex loads and working conditions. Owing to the fault features caused by initial blade cracks are week and easily interfered by strong noise, it is difficult to recognize accurately by traditional methods. In this study, the SNR estimation and adaptive stochastic resonance (SEASR) method is proposed for fault feature recognition of centrifugal compressor with cracked blade. Based on the relationship between SNR and stochastic resonance (SR) parameters, the subtract noise by empirical mode decomposition (SNEMD) method is established with second-order and fourth-order moment (M2M4), hence solving the problem of adaptive SR. The effectiveness of SEASR is tested and analyzed by simulation signals and experimental data. The results demonstrate that the proposed method can accurately recognize fault features of cracked blades and compound faults, where the output SNR is superior to that of the previous methods. It is a new method to realize fault diagnosis for centrifugal compressor with cracked blade and other rotating machinery.

show abstract

Section: Theoretical Backgroundmentioning

confidence: 99%

Fault feature recognition of centrifugal compressor with cracked blade based on SNR estimation and adaptive stochastic resonance

Song

et al. 2022

Structural Health Monitoring

View full text Add to dashboard Cite

show abstract

“…Power spectral density (PSD) is also used [8]. Other studies apply variational mode decomposition (VMD) [9,10], and works like [11] combine the HT and wavelet transform (WT). Work [12] proposes a method based on WT and convolutional neural networks.…”

Section: Introductionmentioning

confidence: 99%

An Analysis of the WPT Function for Pattern Optimization to Detect Defects in Bearings

Zamorano,

Gómez,

Castejon

2024

Machines

View full text Add to dashboard Cite

New trends in maintenance techniques are oriented to digitization and prognosis. The new electronic devices based on IoT (Internet of Things) technology among others that support the industry 4.0 paradigm let enhance the traditional condition monitoring techniques to better understand and predict the state of a machine in service. Related to maintenance applications, one of the important steps in condition monitoring tasks for fault diagnosis is the selection of the optimal pattern to provide accurate results (avoiding fault positives/negatives) with adequate computation time. When implementing this, the selection of optimal parameters and thresholds for setting alarms are important to detect problems in the machine before the failure occurs. Vibratory signals have been proved to be a good variable to determine their mechanical behavior. Nevertheless, parameters obtained from time domain measurements are not computationally efficient nor good patterns to compare different machine conditions. In this sense, tools that represent the frequency domain or time–frequency domain have been useful to detect defects in rotating elements such as bearings. In this work, defects in ball bearings are studied using wavelet packet transform. For this, a methodology will be developed for the optimal selection of the mother wavelet, incorporating intelligent classification systems, and using a medium Gaussian support vector machine model. In this way, it will be verified that the correct selection of this function influences both the results and the ease and reliability of detection. The results using the selected mother wavelet will be compared to those using Daubechies 6, since it is the mother wavelet that has been used in previous works and which was selected based on experience. For it, vibratory signals are obtained from a testbench with different bearing conditions: healthy bearings and defective bearings (inner and outer race).

show abstract

“…In 2018, Li et al [17] utilized VMD and composite multi-scale symbolic dynamic entropy for diagnosing damage in planetary gearboxes. In 2022, Gu et al [18] proposed a feature extraction method that combines the VMD method and permutation entropy (PE). To address the problem of weak signal feature enhancement, Luo et al [19] presented an adaptive VMD method using improved difference search.…”

Section: Introductionmentioning

confidence: 99%

Study on the optimization of the classification method of rolling bearing fault type and damage degree based on SFO–VMD

Jing,

Bian,

et al. 2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

Currently, rolling bearings operate in harsh environments, resulting in acquired signals with a low signal-to-noise ratio. In light of this, this paper proposes an improved variational modal decomposition(VMD) combined with refine composite multi-scale fuzzy entropy (RCMFE) and linear support vector machine (LSVM) for fault diagnosis. Firstly, the sailfish optimization (SFO) algorithm is employed to optimize the important parameter combinations in the VMD algorithm, using the envelope entropy as its objective function. The analysis includes both simulated and real measured signals with varying signal-to-noise ratios. The results demonstrate that, compared to traditional manual parameter setting and empirical modal decomposition methods, this approach effectively addresses the parameter setting issue of VMD in the signal decomposition process. Additionally, it successfully eliminates noise to extract the fault characteristic signal hidden within the original signal. Secondly, the RCMFE algorithm is introduced to overcome the problem of commonly used dimensioned and dimensionless indicators being influenced by load and speed when used as characteristic indicators. By analyzing the influence of load and speed on the RCMFE value, the results demonstrate its strong stability as a feature indicator, unaffected by these factors. For the intelligent classification of failure type and damage degree, LSVM is chosen as the classification method. Analysis results indicate that the distribution characteristics of RCMFE values align better with LSVM compared to the common radial basis function support vector machine, resulting in a significant improvement in diagnosis accuracy.

show abstract

An optimized variational mode decomposition method and its application in vibration signal analysis of bearings

Cited by 15 publications

References 37 publications

Fault feature recognition of centrifugal compressor with cracked blade based on SNR estimation and adaptive stochastic resonance

Fault feature recognition of centrifugal compressor with cracked blade based on SNR estimation and adaptive stochastic resonance

An Analysis of the WPT Function for Pattern Optimization to Detect Defects in Bearings

Study on the optimization of the classification method of rolling bearing fault type and damage degree based on SFO–VMD

Contact Info

Product

Resources

About