Signal filtering method of variational mode decomposition and Euclidean distance based on optimizing parameters of classification particle swarm optimization algorithm

Abstract

In order to deal with the problem that the noise of leakage signals from natural gas pipelines has a great influence on the feature extraction of pipeline leakage, this paper proposes a signal denoising method of variational mode decomposition (VMD) and Euclidean distance (ED) based on optimizing parameters of classification particle swarm optimization (CPSO) algorithm. First, CPSO algorithm is used to optimize parameters K and [Formula: see text] of VMD, adaptively. The sum of the ratio of the mean and variance of the cross-correlation coefficient and the ratio of the mean and variance of kurtosis is used as the fitness function of CPSO. Then, the optimized VMD is used to decompose the signal to obtain several intrinsic mode functions (IMFs). Finally, ED is used to select the effective modes, and the signal is reconstructed to achieve signal noise reduction. The corresponding evaluation indicators show that the accuracy and robustness of the improved method are better than other noise reduction methods. The denoising effect is significant, which proves that the algorithm proposed in this paper is effective in signal filtering.

A Hybrid Energy Storage System Strategy for Smoothing Photovoltaic Power Fluctuation Based on Improved HHO-VMD

“…Therefore, compared with EMD and VMD, the parameteroptimized VMD can better complete the reasonable allocation of HESS power by distinguishing high-and lowfrequency components. [27], the correlated modes and uncorrelated modes are selected. The smaller the d is, the more relevant the submode component is to the original signal.…”

Ultra-short-term wind power prediction based on double decomposition and LSSVM

“…Among them, WD can be used to obtain unstable and nonlinear features from the signals and analyze the signals with intermittent instability (Liu et al, 2021). The problem of modal mixing appeared in the application of EMD (Lu et al, 2021), and the EEMD obtained by improving EMD has been used to solve this problem (Liu et al, 2016), while VMD not only has no problem of modal mixing, but also its number of components is far smaller than EEMD (Zhang et al, 2019). Given that the single signal decomposition methods do not fully consider the mutual influence of wind power sequence across different frequencies (Wu et al, 2020), a combined WD-VMD decomposition of the wind power sequence is adopted in this paper.…”