低压配网断路器机械故障信号波形自动识别算法  

Automatic recognition algorithm for mechanical fault signal waveform of low-voltage distribution network circuit breakers

作　　者：柳羿 张培馨 孟锦鹏 夏小军 LIU Yi;ZHANG Pei-xin;MENG Jin-peng;XIA Xiao-jun(Shenzhen Power Supply Bureau Co.,Ltd.,Shenzhen 518000,Guangdong Province,China)

机构地区：[1]深圳供电局有限公司,广东深圳518000

出　　处：《信息技术》2025年第2期66-73,共8页Information Technology

基　　金：高品质供电引领区关键技术研究与示范应用项目(090000KK52220023)。

摘　　要：低压配网环境中断路器机械故障信号产生的数据量大且存在较多噪声,使得对其故障信号识别变得更加困难。为此,提出低压配网机械故障信号波形自动识别算法。利用Hankel矩阵融合有用信号分量,去噪处理断路器机械故障信号;根据自适应噪声完备集合经验模态分解(Complete Ensemble Empirical Mode Decomposition with Adaptive Noise, CEEMDAN)算法分解故障信号,提取其谱形状熵特征;利用K最近邻分类器(k-Nearest Neighbor Classifier, KNNC)分类特征,完成故障信号波形自动识别。实验结果表明,所提算法增强了故障信号去噪效果,波形识别的准确率在95%以上,且识别效率较高。In the low-voltage distribution network environment,the mechanical fault signal of circuit breakers generates a large amount of data and there is a lot of noise,which makes it more difficult to identify the fault signal.Therefore,an automatic waveform recognition algorithm for mechanical fault signal in low-voltage distribution network is proposed.Hankel matrix is used to fuse useful signal components and denoise the circuit breaker mechanical fault signals.Based on the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise(CEEMDAN)algorithm,the fault signal is decomposed and its spectral shape entropy is extracted.The classification feature of K-Nearest Neighbor Classifier(KNNC)is used to automatically identify fault signal waveform.The experiment results show that the proposed algorithm enhances the de-noising effect of the fault signal,the accuracy rate of waveform recognition is above 95%,and the recognition efficiency is high.

关 键 词：低压配网机械故障 信号降噪 模态分量 HANKEL矩阵 波形自动识别算法 

分 类 号：TM561[电气工程—电器]