摘要
采用变分模态分解(VMD)算法对管道信号进行分析之前,针对VMD在自适应分解过程中人为预设参数会对测试结果造成不同影响的问题,利用海洋捕食者算法(MPA)对VMD算法中的关键参数进行自适应选取,从而提高了VMD的分解效果。计算VMD分解后的各模态分量与原始信号的概率密度之间的豪斯多夫距离(HD)选取有效分量,最后将有效分量进行重构得到去噪信号。试验结果表明,基于MPA优化VMD参数的信号去噪方法与灰狼优化算法(GWO)、鲸鱼优化算法(WOA)和遗传算法(GA)分别优化VMD参数的去噪方法相比,去噪后的信噪比得到了提高,均方误差和平均绝对误差均有所下降,表明本算法具有更好的去噪效果。
Before using the Variational Modal Decomposition(VMD) algorithm to analyze the pipeline signal, in order to solve the problem that the artificial preset parameters in the adaptive decomposition process of VMD will have different effects on the test results, the Marine Predator Algorithm(MPA) was used to adaptively select the key parameters in the VMD algorithm to improve the decomposition effect of VMD.The effective component was selected by calculating the Hausdorff distance(HD) between the probability density of each modal component after VMD decomposition and the original signal, and finally the effective components were reconstructed to obtain the denoising signal.The experimental results show that, compared with the denoising method of optimizing VMD parameters by gray wolf optimization algorithm(GWO),whale optimization algorithm(WOA) and genetic algorithm(GA),the signal-to-noise ratio of the denoising method of the signal based on VMD parameters optimized by MPA after denoising is improved, and both the mean square error and mean absolute error are reduced, indicating that the algorithm has better denoising effect.
作者
侯轶轩
路敬祎
张昆
张勇
HOU Yixuan;LU Jingyi;ZHANG Kun;ZHANG Yong(School of Electrical and Information Engineering,Northeast Petroleum University,Daqing 163318,China;Key Laboratory of Networked and Intelligent Control in Heilongjiang Province,Northeast Petroleum University,Daqing 163318,China;Daqing Oilfield Design Institute Co.,Ltd.,Daqing 163318,China;School of Physics and Electronic Engineering,Northeast Petroleum University,Daqing 163318,China)
出处
《压力容器》
北大核心
2022年第7期64-72,共9页
Pressure Vessel Technology
基金
国家自然科学基金(61873058)
国家自然科学基金青年科学基金项目(62103096)
海南省科技专项资助(ZDYF2022SHFZ105)
黑龙江省自然基金资助(LH2020F005)
海南省科技计划三亚崖州湾科技城联合项目资助(2021JJLH0025)。
关键词
管道泄漏
去噪
变分模态分解算法
海洋捕食者算法
豪斯多夫距离
pipeline leakage
denoising
variational modal decomposition
marine predators algorithm
Hausdorff distance
