电气设备局部放电灰度图象的矩特征提取研究  

Research on Moment Feature Extraction of Grey Image of Partial Discharge in Electrical Equipment

作　　者：李新[1] 成小瑛[1] 孟小红[2] 

机构地区：[1]重庆大学高电压与电工新技术教育部重点实验室,重庆400044 [2]煤炭科学研究总院重庆分院,重庆400037

出　　处：《矿业安全与环保》2003年第6期17-18,31,共3页Mining Safety & Environmental Protection

摘　　要：从图象识别角度研究了电气设备局部放电的模式识别。对电气设备局部放电灰度图象的矩特征进行了深入研究。制作了3种绝缘缺陷模型,在双层屏蔽室中对这3种模型进行了实验,取得了大量的放电样本数据。用BP人工神经网络分类器进行识别,结果表明矩特征的识别率较高,说明该方法具有良好的应用效果。In this paper, deep research on mode recognition for partial discharge in electrical equipment was conducted from the angle of image recognition. In the mode and image recognition, the moment feature is a widely-used characteristic parameter of image form. Deep research was conducted on the moment features of grey image of partial discharge in electrical equipment. Three kinds of insulation defect model were made, many tests on these models were conducted in a double-layer shielding chamber and a large amount of discharging sample data were obtained. The recognition with BP artificial neural net grader shows that the recognition rate of moment features is rather high, this indicates that this method has better applicable effect.

关 键 词：局部放电 灰度图象 矩特征 图象识别 BP人工神经网络分类器 

分 类 号：TD608[矿业工程—矿山机电]