基于经验模态分解的有载分接开关振动信号识别  

Adaptive mode decomposition of vibration signal of on-load tap-changer based on EMD

作　　者：吴达 王康 叶紫燃 WU Da;WANG Kang;YE Ziran(Electric Power Research Institute of State Grid Fujian Electric Power Co.,Ltd.,Fuzhou 350007,China;Sichuan Huayinshengan Technology Co.,Ltd.,Chengdu 610095,China)

机构地区：[1]国网福建省电力有限公司电力科学研究院,福建福州350007 [2]四川华音盛安科技有限公司,四川成都610095

出　　处：《电子设计工程》2022年第13期82-86,共5页Electronic Design Engineering

基　　金：国网福建省电力有限公司科技项目资助(521304180011)。

摘　　要：为了提升有载分接开关振动信号降噪效果及故障识别准确率,研究了一种基于经验模态分解的有载分接开关振动信号识别方法。该方法对有载分接开关振动信号进行采用掩膜的经验模态分解,降低模态混叠;采用阈值滤波方法对各个固有模态函数进行处理,降低噪声影响;再采用相关系数法选取特定固有模态函数并进行信号重构,采用时频分析和卷积神经网络方法进行特征提取和故障识别,得到故障识别结果。实验结果表明,利用所提出的方法进行降噪处理后的识别准确率得到有效提高。In order to improve the noise reduction effect and fault identification accuracy of on-load tap switch vibration signal,a vibration signal identification method based on Empirical Mode Decomposition(EMD) was studied.The vibration signal of the on-load tap switch is decomposed by the empirical mode using a mask to reduce the mode mixing.Threshold filtering method is used to process each inherent mode function to reduce the influence of noise and the correlation coefficient method is used to select the specific natural mode function and reconstruct the signal.Time-frequency analysis and convolutional neural network are used to extract features and identify faults,and the fault recognition results are obtained.The experimental results show that the recognition accuracy is effectively improved by using the proposed method.

关 键 词：模态混叠 阈值滤波 固有模态函数 信号重构 

分 类 号：TM41[电气工程—电器]