期刊文献+

基于经验模态分解的有载分接开关振动信号识别 被引量:1

Adaptive mode decomposition of vibration signal of on-load tap-changer based on EMD
下载PDF
导出
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.
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)
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)。
关键词 模态混叠 阈值滤波 固有模态函数 信号重构 mode mixing threshold filtering intrinsic mode function signal reconstruction
  • 相关文献

参考文献17

二级参考文献170

共引文献165

同被引文献17

引证文献1

二级引证文献8

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部