音频事件检测算法在计量费控用电压开关柜局部放电检测中的应用研究  

Application Research of Audio Event Detection Algorithm in Partial Discharge Detection of Switchgear for Power Metering and Control

作　　者：张思建 梁荣业 赵闻 张捷 ZHANG Sijian;LIANG Rongye;ZHAO Wen;ZHANG Jie(The Metrology Center of Guangdong Power Grid Co.,Ltd,Guangzhou 510080,China;Guangzhou Unisun Power Technology Co.,Ltd,Guangzhou 510080,China)

机构地区：[1]广东电网有限责任公司计量中心,广州510080 [2]广州宇阳电力科技有限公司,广州510080

出　　处：《电子器件》2020年第2期309-314,共6页Chinese Journal of Electron Devices

摘　　要：有效检测开关柜故障是影响电网安全的因素,如何进行有效的非浸入式检测是国内外的研究热点之一。提出一种基于音频信号的电压开关柜局部放电检测算法,可识别开关柜正常态、电晕态和放电态3种状态。算法首先提取电压开关柜放电声音的MFCC特征作为识别特征,然后构建基于支持向量机的分类器来识别出电压开关柜的状态,从而进行故障检测。实验表明本文提出的检测算法具有较高的局部放电检测正确率。Effective detection of switchgear faults is one of factors affecting power grid security. How to carry out effective non-immersion detection is one of the research hotspots at home and abroad. A partial discharge detection algorithm is proposed for low voltage switchgear based on audio signal,which can recognize three states:normal state,corona state and discharge state. The algorithm first extracts MFCC features of discharge sound of low-voltage switchgear as identification features,and then constructs a classifier based on support vector machine to identify the state of low-voltage switchgear,so as to conduct fault detection. Experiments show that the proposed detection algorithm has a high partial discharge detection accuracy.

关 键 词：电压开关柜 局部放电 支持向量机 美尔倒谱系数 

分 类 号：TM591[电气工程—电器]