摘要
为了对电缆的局部放电试验结果进行分析,文中提出了一种利用放电信号的脉冲幅值q与相位角φ的余弦和正弦函数乘积绘制极坐标谱图的方法,指出了该谱图的特点。结合3种电缆接头放电模型的试验结果,分析了不同放电类型的谱图特征。提取了极坐标谱图的若干有关分布和对称的特征信息,形成了16维的特征向量,用人工神经网络方法进行了放电的模式识别研究。
In order to analyze the data from partial discharge test of cable, the polar spectrum is drawn from multiplying the pulse amplitude by cosine and sine of phase angle. Advantage of this spectrum is present. According to the test results of 3 kinds of cable joint model, spectrum characteristics of different discharge type are studied. 16 characteristic values of polar spectrum about distribution and symmetry are calculated for the feature vector. Method of artificial neural network is used to study the pattern recognition of partial discharge.
出处
《高压电器》
CAS
CSCD
北大核心
2015年第7期97-101,共5页
High Voltage Apparatus
关键词
局部放电
三角函数
放电脉冲相位分布
极坐标谱图
模式识别
人工神经网络
电缆
partial pattern discharge （PD）
trigonometric function
phase resolved partial discharge
polar spectrum
recognition
artificial neural networks
cable
