摘要
为了利用断路器较少的状态数据样本对断路器的主要故障进行分析与判断,提出以近似熵作为一种新的断路器振动信号特征量,通过在SF6断路器上进行试验,采集到正常状态、铁心卡涩、润滑不足、底座松动4种状态的样本。将原始信号利用经验模态进行分解,得到的一组固有模态函数分量做为近似熵算法的输入,将多个分量的近似熵组成一个特征向量来表征原始信号。最后,引入支持向量机对不同状态的样本进行有效分类,验证以近似熵作为断路器振动信号特征量的有效性。
To make analysis and judgement of main circuit breaker fault with fewer circuit breaker data samples, approximate entropy is proposed as a new circuit breaker vibration signal feature, by performing tests on SF6 circuit breakers, samples under four states is collected: the normal state, the core jamming, insufficient lubrication, loose base. Empirical mode decomposition is used on original signal to get a group of intrinsic mode functions as an input component of approximate entropy algorithm, multiple components of approximate entropy form a feature vector to represent the original signal. Finally, effectively classify of samples under different states is made by support vector machine, to verify the validity of using approximate entropy as circuit breaker vibration signal features.
作者
王振浩
顾欣然
孙福军
WANG Zhenhao;GU Xinran;SUN Fujun(Northeast Electric Power University,Jilin Jilin 132012,China;Heilongjiang Electric Power Company Limited,Harbin 150090,China)
出处
《高压电器》
CAS
CSCD
北大核心
2018年第10期151-156,163,共7页
High Voltage Apparatus
基金
吉林省科技厅项目(20160307014GX)~~
关键词
在线监测
断路器振动信号
近似熵
支持向量机
on-line monitoring
circuit breaker vibration signal
approximate entropy
supporting vector machine (SVM)