电工技术学报  2018, Vol. 33 Issue (15): 3510-3517    DOI: 10.19595/j.cnki.1000-6753.tces.180089
电力系统 |
基于改进SVDD算法与马氏距离的未知局部放电类型的识别
高佳程, 朱永利, 贾亚飞, 郑艳艳, 刘帅
新能源电力系统国家重实验室(华北电力大学) 保定 071003
Pattern Recognition of Unknown Types of Partial Discharge Based on Improved SVDD Algorithm and Mahalanobis Distance
Gao Jiacheng, Zhu Yongli, Jia Yafei, Zheng Yanyan, Liu Shuai
State Key Laboratory of Alternate Electrical Power System with Renewable Energy Source North China Electric Power University Baoding 071003 China
全文: PDF (11102 KB)  
输出: BibTeX | EndNote (RIS)      
摘要 提出一种基于改进支持向量数据描述(SVDD)算法与马氏距离的未知类型的局部放电(PD)识别方法。首先,采集各个不同类型的放电样本,并提取特征向量构成样本集合;其次,利用SVDD算法求解得出训练样本的超球体中心a和半径R;然后,根据Otsu准则设定双阈值R1R2,将特征空间划分为三个不同区域;最后,依据不同区域内的判定准则,以马氏距离为判定条件,确定待测样本的放电类型。试验结果表明,该方法对于未知类型的放电样本具有较高的正确识别率,验证了该方法的可行性。
服务
把本文推荐给朋友
加入我的书架
加入引用管理器
E-mail Alert
RSS
作者相关文章
高佳程
朱永利
贾亚飞
郑艳艳
刘帅
关键词 局部放电模式识别未知类型局部放电改进SVDD算法马氏距离    
Abstract:A method to identify unknown partial discharge (PD) types based on improved support vector data description (SVDD) algorithm and Mahalanobis distance is presented in this paper. And a dual threshold method based on Otsu criterion is proposed to determine the types of PD samples. Firstly, PD samples were collected from artificial defects models and extracted feature vectors to constitute sample sets. Secondly, the SVDD algorithm was used to solve the center and the radius of the hypersphere of the training PD samples. Then, the double threshold R1 and R2 were set according to the Otsu criterion, and the feature space was divided into different regions. Finally, according to the classical criterion and Mahalanobis distance, the types of PD of the test samples were determined. The experimental results show that the accuracy of recognition obtained by the method proposed in this paper is high, which verifies the feasibility of the method. Compared with the traditional SVDD algorithm and the Euclidean distance method, the proposed method has a higher accuracy for the classification of PD samples.
Key wordsPartial discharge    pattern recognition    unknown partial discharge types    improved support vector data description algorithm    Mahalanobis distance   
收稿日期: 2018-01-17      出版日期: 2018-08-14
PACS: TM85  
基金资助:国家自然科学基金(51677072)和中央高校基本科研业务费专项资金(2017XS118)资助项目
通讯作者: 朱永利 男,1963年生,教授,博士生导师,研究方向为输变电设备网络化监测与信息分析处理。E-mail:yonglipw@163.com   
作者简介: 高佳程 男,1993年生,硕士研究生,研究方向为高压设备局部放电信号分析与故障诊断。E-mail:gaojiacheng1993@163.com
引用本文:   
高佳程, 朱永利, 贾亚飞, 郑艳艳, 刘帅. 基于改进SVDD算法与马氏距离的未知局部放电类型的识别[J]. 电工技术学报, 2018, 33(15): 3510-3517. Gao Jiacheng, Zhu Yongli, Jia Yafei, Zheng Yanyan, Liu Shuai. Pattern Recognition of Unknown Types of Partial Discharge Based on Improved SVDD Algorithm and Mahalanobis Distance. Transactions of China Electrotechnical Society, 2018, 33(15): 3510-3517.
链接本文:  
https://dgjsxb.ces-transaction.com/CN/10.19595/j.cnki.1000-6753.tces.180089          https://dgjsxb.ces-transaction.com/CN/Y2018/V33/I15/3510