SSA-VMD联合改进小波阈值去噪算法在局部放电中应用  

Application of SSA-VMD Combined Improved Wavelet Threshold Denoising Algorithm in Partial Discharge

作　　者：孟小斐 刘红兵[1] MENG Xiao-fei;LIU Hong-bing(School of Electronic Information Engineering,Taiyuan University of Science and Technology,Taiyuan 030024,China)

机构地区：[1]太原科技大学电子信息工程学院,山西太原030024

出　　处：《电工电气》2025年第3期29-34,40,共7页Electrotechnics Electric

摘　　要：针对电力设备局部放电信号的噪声干扰问题,提出了一种麻雀搜索算法(SSA)、变分模态分解(VMD)与改进小波阈值去噪法相结合的去噪算法。以排列熵作为适应度函数,使用麻雀搜索算法确定变分模态分解的模态数和惩罚因子并将含噪局放信号拆分成多个固有模态分量,再根据样本熵确定有效阈值和去噪阈值。将样本熵大于有效阈值的模态分量视为噪声分量剔除,将样本熵小于有效阈值且大于去噪阈值的模态分量进行改进小波阈值法处理,将去噪后的模态分量和小于去噪阈值的模态重构完成信号去噪。在MATLAB软件中进行对比仿真实验,该算法在信噪比x_(SNR)和均方根误差x_(RMSE)方面均有提升且保留了原始信号中的有效信息,验证了其有效性。To solve the noise interference problem of partial discharge signal of power equipment,an algorithm combining sparrow search algorithm(SSA),variational mode decomposition(VMD)and improved wavelet threshold denoising method is proposed.Firstly,with permu-tation entropy as fitness function,the sparrow search algorithm is used to determine the mode number and penalty factor of variational mode decomposition,and the signal with noise is divided into multiple inherent modal components.Consider modal components having a sample en-tropy higher than the effective threshold as noise components and eliminate them.For modal components where the sample entropy is lower than the effective threshold yet higher than the denoising threshold,carry out the treatment with the improved wavelet threshold approach.Subse-quently,reconstruct the modal components that have been denoised and those with sample entropy below the denoising threshold,thus achieving signal denoising.In the MATLAB based comparative simulation experiments,the algorithm proposed in this paper demonstrates improvements in both the signal-to-noise ratio x_(SNR) and root-mean-square error x_(RMSE).Moreover,it effectively preserves the valid information within the original signal,thus verifying its effectiveness.

关 键 词：信号去噪 变分模态分解 麻雀搜索算法 局部放电 改进小波阈值法 

分 类 号：TM744[电气工程—电力系统及自动化]