Seismic Random Noise Denoising Using Mini-Batch Multivariate Variational Mode Decomposition

Wu, Guoning; Liu, Guochang; Wang, Junxian; Fan, Pingping

doi:10.1155/2022/2132732

Cited by 4 publications

(2 citation statements)

References 32 publications

(28 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Variational mode decomposition (VMD) [15] is a signal processing algorithm under a new framework, which uses an iterative approach to minimize an objective function and obtain a set of restricted narrowband signals centered at different frequencies. It is proved that VMD can effectively overcome the mode mixing problem of EMD, as well as exhibit good noise robustness and solid theoretical foundation [28,29], making VMD widely used in various fields [30][31][32][33]. However, in practical applications, the results of VMD are heavily dependent on the parameter settings, including mode number K and balancing parameter α.…”

Section: Introductionmentioning

confidence: 99%

Adaptive spectrum segmentation Ramanujan decomposition and its application to gear fault diagnosis

Huang,

Yang,

Cheng

et al. 2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

Ramanujan Fourier mode decomposition (RFMD) is a novel non-stationary signal decomposition method, which can decompose a complex signal into several components and extract the periodic characteristics of the signal. However, the mode generation method adopted by RFMD does not consider the physical meaning of the component signal, which makes over-decomposition when dealing with real-life gear signals with complex modulation characteristics, thus destroying the integrity of the signal sideband, increasing the difficulty of subsequent analysis, and even losing key fault information. The iterative envelope-segmentation algorithm combines the modulation characteristics of the fault gear signal and divides the original signal into a limited number of dominant frequency bands containing the modulation region in the Fourier spectrum, thereby ensuring that the obtained frequency bands contain rich fault information. Based on the above algorithm, a new adaptive decomposition method is proposed in this paper, which is Adaptive Spectrum Segmentation Ramanujan Decomposition (ASSRD). ASSRD uses fault envelope harmonic noise ratio (FHNR) as theindex to evaluate the fault information content of component signals and uses it to assist theiterative envelopesegmentation algorithm to complete the adaptive segmentation of the Fourier spectrum. Finally, based on the segmentation result, the inverse RFT reconstruction of each frequency band is performed. Thus, the signal is decomposed into a finite number of component signals containing rich fault information. In addition, through the gear simulation signal and the measured gear signal experiment, the ASSRD method is compared with the original RFMD method and the existing ensemble empirical mode decomposition, variational mode decomposition, empirical wavelet transform, and singular spectrum decomposition method, verifying the feasibility and superiority of ASSRD in gear fault diagnosis. The results show that the proposed method can extract the fault information in the gear signal more effectively, and the performance is better than the comparison method.

show abstract

Section: Introductionmentioning

confidence: 99%

Adaptive spectrum segmentation Ramanujan decomposition and its application to gear fault diagnosis

Huang,

Yang,

Cheng

et al. 2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…The results show that complete ensemble empirical mode decomposition has high feature recognition ability in complex random desert noise. Wu et al (2022) uses multivariate variational modal decomposition on the segmented seismic data. This method significantly improves the lateral continuity and SNR of the seismic data.…”

Section: Introductionmentioning

confidence: 99%

Prestack seismic random noise attenuation using the wavelet-inspired invertible network with atrous convolutions spatial pyramid

Wu²,

Xu³

2023

Front. Earth Sci.

View full text Add to dashboard Cite

Convolutional Neural Network (CNN) is widely used in seismic data denoising due to its simplicity and effectiveness. However, traditional seismic denoising methods based on CNN ignore multi-scale features of seismic data in the wavelet domain. The lack of these features will decrease the accuracy of denoising results. To address this barrier, a seismic denoise method based on the wavelet-inspired invertible network with atrous convolutions spatial pyramid (WINNet_ACSP) is proposed. WINNet_ACSP follows the principle of lifting wavelet transform. The proposed method utilizes the redundant orthogonal wavelet transform to obtain frequency multi-scale information from noisy seismic data. Then predict update network (PUNet) extracts spatial multi-scale features of approximate and detailed parts. The sparse driven network (SDN) learns the complex multi-scale information and obtains sparse features. These sparse features are processed to eliminate random noise. Compared to standard convolution, the atrous convolutions spatial pyramid (ACSP) can extract more features. The redundant features are the key to ensure the precision of multi-scale information. Therefore, the introduction of ACSP in PUNet can guarantee the denoising effect of the network. WINNet_ASCP combines the characteristics of wavelet transform and neural network and has a high generalization. Besides, transfer learning is used to overcome the difficulty caused by the training sample size of seismic data. The training process includes pre-training and post-training. The former is trained to obtain the initial denoising network by natural image samples. The latter is trained with a small sample of seismic data to enhance stratigraphic continuity. Finally, the proposed method is tested with synthetic and field data. The experimental results show that the proposed method can effectively remove random noise and reduce the loss of detailed information in prestack seismic data. In the future, we will make further improvements on this basis and conduct experiments on 3D prestack data.

show abstract

An Optimized Heading De-Noising Method of the Polarization Compass for Improving Orientation Accuracy

Zhao

Guan

et al. 2023

IEEE Sensors J.

View full text Add to dashboard Cite

Seismic Random Noise Denoising Using Mini-Batch Multivariate Variational Mode Decomposition

Cited by 4 publications

References 32 publications

Adaptive spectrum segmentation Ramanujan decomposition and its application to gear fault diagnosis

Adaptive spectrum segmentation Ramanujan decomposition and its application to gear fault diagnosis

Prestack seismic random noise attenuation using the wavelet-inspired invertible network with atrous convolutions spatial pyramid

An Optimized Heading De-Noising Method of the Polarization Compass for Improving Orientation Accuracy

Contact Info

Product

Resources

About