摘要
分闸缓冲器的性能直接影响着高压断路器分闸机械特性与零部件寿命。时频分析能够准确揭示高压断路器振动信号的频率成分及时变特征,由此构建的时频图像包含丰富的高压断路器工作状态特征信息。为此,提出一种基于振动信号时频图像特征及支持向量机(SVM)的高压断路器分闸缓冲器状态评估方法。首先采用小波变换(WT)将高压断路器振动信号转换成时频谱图,然后提取时频图像的纹理特征和形状特征作为特征向量,最后利用 SVM 实现分闸缓冲器状态的识别。试验结果表明,所提方法能够有效识别高压断路器分闸缓冲器的状态,为高压断路器故障诊断尤其是分闸缓冲器状态监测与诊断提供了一种新方法。
The working performance of opening damper directly affects the opening mechanical characteristics and components life of high-voltage circuit breakers (HVCBs). The method of time- frequency analysis can reveal exactly the frequency components and time-varying characteristics of vibration signals of HVCB. Time-frequency image which constructed by using the time-frequency analysis method contains rich feature information of HVCB’s working condition. In this paper, a novel condition evaluation method for the opening damper of HVCB based on vibration time-frequency image and support vector machine (SVM) is proposed and analyzed. Firstly, the vibration signal is converted into time-frequency image by using wavelet transform (WT). Then, texture features and shape features of the time-frequency image are extracted as eigenvectors. Finally, SVM is used to classify the working status of the opening damper. The experimental results show that the method can effectively evaluate the condition of the opening damper. The method presented in this paper is almost newly for fault diagnosis of HVCB, especially for monitoring and diagnosis of HVCB’s opening damper.
作者
杨秋玉
阮江军
黄道春
庄志坚
Yang Qiuyu;Ruan Jiangjun;Huang Daochun;Zhuang Zhijian(School of Electrical Engineering and Automation Wuhan University ,Wuhan 430072 China;Power Product Medium Voltage Technology Center ABB (China) Co. Ltd ,Xiamen 361006 China)
出处
《电工技术学报》
EI
CSCD
北大核心
2019年第19期4048-4057,共10页
Transactions of China Electrotechnical Society
基金
国家重点研发计划资助项目（2017YFB0902400）
关键词
高压断路器
分闸缓冲器
状态评估
振动时频图像
小波变换
支持向量机
High-voltage circuit breakers (HVCBs)
opening damper
condition evaluation
vibration time-frequency image
wavelet transform (WT)
support vector machine (SVM)
