Recursive variational mode extraction and its application in rolling bearing fault diagnosis

Pang, Bin; Nazari, Mojtaba; Tang, Guiji

doi:10.1016/j.ymssp.2021.108321

Cited by 83 publications

(46 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…29 For the initial parameters selection when using VME to extract fault feature signals, the center frequency ω d should correspond to the dominant frequency, and the penalty factor α is used to limit the bandwidth of the extracted component. 23 Reasonable selection of these two parameters is crucial to the accuracy and completeness of extracting components containing fault feature information. Hence, this paper proposes the spectral variational mode extraction (SVME) to adaptively determine the optimal parameters ( ω d , α ), so as to achieve the precise extraction of fault feature components.…”

Section: The Proposed Methodsmentioning

confidence: 99%

“…When the center frequency and penalty factor are selected reasonably, the performance of VME is better than VMD. 22,23 Hence, a reasonable choice of these two parameters is essential to apply VME to obtain the fault characteristic components. When the preset center frequency ω deviates from the frequency of the fault feature component in the spectrum, the separation accuracy of VME may be decreased.…”

Section: The Proposed Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Spectral variational mode extraction and its application in fault detection of rolling bearing

Pang

Zhang

Cheng

et al. 2022

Structural Health Monitoring

Self Cite

View full text Add to dashboard Cite

The core of fault diagnosis of rolling bearing is to extract the narrowband sub-components containing fault feature information from the bearing fault signal. Variational mode extraction (VME), a novel single sub-component separation algorithm originated from variational mode decomposition (VMD), provides a promising solution to bearing fault detection. However, its performance is closely related to the hyperparameter selection, including the center frequency ω d and the penalty factor α. This paper proposes a non-recursive and adaptive signal decomposition algorithm termed spectral variational mode extraction (SVME). SVME can be seen as a spectral decomposition technique whose framework is composed of the adaptive spectral boundary division and boundary constrained VME. In the adaptive spectral boundary division, an adaptive iterative spectral envelope method referring to the continuous envelope correlation (CCE) index is developed to integrate with the parameterless scale-space division to adaptively locate the frequency band boundary. The presented adaptive spectral boundary division approach can effectively inhibit the spectral boundary over-division. In the boundary constrained VME, the dominant frequency of each frequency band determined by the optimal spectral division is distinguished as the preset center frequency. Meanwhile, the optimal penalty factor is determined based on the envelope spectral kurtosis (ESK) index and the boundary-constraint principle. The SVME method is utilized in the simulation and experimental case studies to investigate its capability. Furthermore, its superiority is highlighted through the comparison with the variational mode decomposition (VMD) and Autogram methods.

show abstract

Section: The Proposed Methodsmentioning

confidence: 99%

Section: The Proposed Methodsmentioning

confidence: 99%

Spectral variational mode extraction and its application in fault detection of rolling bearing

Pang

Zhang

Cheng

et al. 2022

Structural Health Monitoring

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, there are some problems in the decomposition results. To address the problems of endpoint effect and modal confusion of EMD, scholars have improved EMD and proposed ensemble empirical mode decomposition (EEMD), local characteristic scale decomposition (LCD), variational mode decomposition (VMD), and time-varying filter-based empirical mode decomposition (TVFEMD) and applied them to the field of fault diagnosis well [ 15 , 16 , 17 ]. EEMD [ 18 ] improves the decomposition of EMD by adding Gaussian white noise.…”

Section: Introductionmentioning

confidence: 99%

A New Method of Wheelset Bearing Fault Diagnosis

Sun

Yang

Yao

et al. 2022

Entropy

View full text Add to dashboard Cite

During the movement of rail trains, trains are often subjected to harsh operating conditions such as variable speed and heavy loads. It is therefore vital to find a solution for the issue of rolling bearing malfunction diagnostics in such circumstances. This study proposes an adaptive technique for defect identification based on multipoint optimal minimum entropy deconvolution adjusted (MOMEDA) and Ramanujan subspace decomposition. MOMEDA optimally filters the signal and enhances the shock component corresponding to the defect, after which the signal is automatically decomposed into a sequence of signal components using Ramanujan subspace decomposition. The method’s benefit stems from the flawless integration of the two methods and the addition of the adaptable module. It addresses the issues that the conventional signal decomposition and subspace decomposition methods have with redundant parts and significant inaccuracies in fault feature extraction for the vibration signals under loud noise. Finally, it is evaluated through simulation and experimentation in comparison to the current widely used signal decomposition techniques. According to the findings of the envelope spectrum analysis, the novel technique can precisely extract the composite flaws that are present in the bearing, even when there is significant noise interference. Additionally, the signal-to-noise ratio (SNR) and fault defect index were introduced to quantitatively demonstrate the novel method’s denoising and potent fault extraction capabilities, respectively. The approach works well for identifying bearing faults in train wheelsets.

show abstract

“…However, the aforementioned studies aim to process the signal of a single sensor which cannot completely reflect the information of the bearing failure features. In addition, vibration signal detection is easily interfered with by external factors [18]. The changes in the working environment and monitoring position particularly impact the collected data.…”

Section: Introductionmentioning

confidence: 99%

Intelligent Bearing Fault Diagnosis Based on Multivariate Symmetrized Dot Pattern and LEG Transformer

et al. 2022

Self Cite

View full text Add to dashboard Cite

Deep learning based on vibration signal image representation has proven to be effective for the intelligent fault diagnosis of bearings. However, previous studies have focused primarily on dealing with single-channel vibration signal processing, which cannot guarantee the integrity of fault feature information. To obtain more abundant fault feature information, this paper proposes a multivariate vibration data image representation method, named the multivariate symmetrized dot pattern (M-SDP), by combining multivariate variational mode decomposition (MVMD) with symmetrized dot pattern (SDP). In M-SDP, the vibration signals of multiple sensors are simultaneously decomposed by MVMD to obtain the dominant subcomponents with physical meanings. Subsequently, the dominant subcomponents are mapped to different angles of the SDP image to generate the M-SDP image. Finally, the parameters of M-SDP are automatically determined based on the normalized cross-correlation coefficient (NCC) to maximize the difference between different bearing states. Moreover, to improve the diagnosis accuracy and model generalization performance, this paper introduces the local-to-global (LG) attention block and locally enhanced positional encoding (LePE) mechanism into a Swin Transformer to propose the LEG Transformer method. Then, a novel intelligent bearing fault diagnosis method based on M-SDP and the LEG Transformer is developed. The proposed method is validated with two experimental datasets and compared with some other methods. The experimental results indicate that the M-SDP method has improved diagnostic accuracy and stability compared with the original SDP, and the proposed LEG Transformer outperforms the typical Swin Transformer in recognition rate and convergence speed.

show abstract

Recursive variational mode extraction and its application in rolling bearing fault diagnosis

Cited by 83 publications

References 35 publications

Spectral variational mode extraction and its application in fault detection of rolling bearing

Spectral variational mode extraction and its application in fault detection of rolling bearing

A New Method of Wheelset Bearing Fault Diagnosis

Intelligent Bearing Fault Diagnosis Based on Multivariate Symmetrized Dot Pattern and LEG Transformer

Contact Info

Product

Resources

About