摘要
电力设备中,不同类型的放电因放电功率、能量的差异对设备绝缘的损害能力存在差异,即对绝缘的危害程度不同,确定局部放电类型是放电危险度评估的基础。文中对典型缺陷条件下的局部放电谱图提取了基本参量及统计参量等多种特征指纹;为了降低识别参量的维度,定义了特征向量可分性评估准则,并使用浮动前向搜索算法选取了可分性最优的9组特征参量;分别使用主成分分析、线性可分性分析、核主成分分析及通用可分性分析4种方法将特征向量降为2维,结果表明,使用通用可分性分析降维后特征参量可分性最优。之后,提出了多算法联合的模式识别分类器,通过对比最小距离法、人工神经网络及支持向量机,3种方法确定最终识别结果,实验结果表明,该分类器识别准确率达95.8%。最后将所提出模式识别方法应用于现场局部放电缺陷类型识别,通过设备实验结果对比验证了识别结果的准确性。
In electrical equipment, different types of discharge have different damage to oil-paper insulation because of the difference of discharge power and energy, which means different detriment to insulation. Determining the partial discharge mode and type are the basis of discharge risk assessment. Many feature parameters including the basic parameters and statistical parameters are extracted from partial discharge spectrogram under different defects in this paper. In an attempt to reduce the dimension of identification parameters, the characteristic vector separability assessment criteria are defined and using the floating forward search algorithm, 9 group feature parameters with optimal separability are selected. The feature vector is reduced to 2-dimention adopting the principal component analysis, linear discriminant analysis, kernel principal component analysis and generalized discriminant analysis methods. The results show that the optimal separability of feature vector can be obtained using the general separabili- ty analysis method. Then, the pattern recognition classifier which combines many kinds of algorithm is extracted. Comparing the recognition results of minimum distance method, artificial neural network and support vector machine （SVM） methods, the results present that the classifier recognition accuracy reaches 95.8%. Finally, the adopted pattern recognition method is applied to recognize the defects type of partial discharge of actual electrical equipment. The results reveal the accuracy of the adopted recognition method.
作者
王世强
薛建议
胡海燕
刘全桢
穆海宝
WANG Shiqiang;XUE Jianyi;HU Haiyan;LIU Quanzhen;MU Haibao(SINOPEC Research Institute of Safety Engineering,State Key Laboratory of Safety and Control for Chemicals,Shandong Qingdao 266071,China;State Key Lab of Electrical Insulation and Power Equipment,Xi＇an Jiaotong University,Xi＇an 710049,China)
出处
《高压电器》
CAS
CSCD
北大核心
2018年第10期112-119,共8页
High Voltage Apparatus
关键词
局部放电
模式识别
特征参量
典型缺陷
特征优选与降维
partial discharge
pattern recognition
feature parameter
typical defects
feature selection and dimension reduction
