组合核支持向量机在放电模式识别中的优化策略

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (482 KB)
输出: BibTeX | EndNote (RIS)

摘要传统的单一核函数SVM无法实现局部放电中的多特征空间向量的映射分类,且目前SVM大都采用不同尺度的径向基函数作为核函数,核的调整空间较为有限,无法针对不同特征空间的放电参数达到普适的效果。针对上述问题,本文提出一种基于多分组特征的组合核多分类SVM的局部放电识别方法。该方法首先完成多类特征空间在不同类型SVM核函数中的映射分类,再采用骨干粒子群（BBPSO）优化方法选取最佳核参数,并求解核函数权值系数,最终形成最优核函数组合分类模型。实验结果表明,该方法对多个特征空间数据具有普适性,且融合效果理想,分类精度高于误差反向传播神经网络（BPNN）和SVM识别方法。

	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
	王瑜
	苑津莎
	尚海昆
	靳松

关键词 ：局部放电, 组合核, 支持向量机, 骨干粒子群, 模式识别

Abstract：Conventional single kernel SVM has natural defects on mapping multiple partial discharge(PD) feature spaces and classifying multiple PD types. Most popular SVM classifiers adopt RBF with different parameters as kernel functions that limited the adjustment space; moreover the universality to process multiple feature spaces is missed. Aiming at these problems, a grouped-feature based combined-kernel multiclass support vector machine(CKM-SVM) is proposed. Multiple PD feature spaces are constructed and mapped to different SVM kernel functions; then each kernel function is optimized via bare-bone particle swarm optimization(BBPSO), and then the weight coefficients for CKM-SVM model are calculated. Tests show that CKM-SVM performs good feature spatial fusion; additionally the recognition accuracy precedes BPNN and SVM.

Key words： PD combined-kernel SVM BBPSO pattern recognition

收稿日期: 2014-09-29 出版日期: 2015-04-14

PACS:

TM85

基金资助:中央高校基本科研专项资金（2014ZD32,13MS69）和国家自然科学基金（61204027）资助项目

作者简介: 王瑜男,1979年生,讲师,博士研究生,研究方向为模式识别,电气设备故障诊断。苑津莎男,1957年生,教授,博士生导师,研究方向为智能信息处理,电磁场理论及应用。

引用本文:

王瑜,苑津莎,尚海昆,靳松. 组合核支持向量机在放电模式识别中的优化策略[J]. 电工技术学报, 2015, 30(2): 229-236. Wang Yu,Yuan Jinsha,Shang Haikun,Jin Song. Optimization Strategy Research on Combined-Kernel Support Vector Machine for Partial Discharge Pattern Recognition. Transactions of China Electrotechnical Society, 2015, 30(2): 229-236.

链接本文:

http://dgjsxb.ces-transaction.com/CN/Y2015/V30/I2/229

[1] 王国利, 郝艳捧, 李彦明. 电力变压器局部放电检测技术的现状和发展[J]. 电工电能新技术, 2001, 20(2): 52-57. Wang Guoli, Hao Yanpeng, Li Yanming. Present and future development of partial discharge detection in power transformers[J]. Advanced Technology of Electrical Engineering and Energy, 2001, 20(2): 52-57.
[2] 满玉岩, 高文胜, 高凯, 等. 发电机局部放电的统计特征识别[J]. 电工技术学报, 2006, 21(4): 41-45. Man Yuyan, Gao Wensheng, Gao Kai, et al. Statis- tical recognition of discharge patterns in power generator[J]. Transactions of China Electrotechnical Society, 2006, 21(4): 41-45.
[3] 胡文堂, 高胜友, 余绍峰, 等. 统计参数在变压器局部放电模式识别中的应用[J]. 高电压技术, 2009, 35(2): 277-281. Hu Wentang, Gao Shengyou, Yu Shaofeng, et al. Application of statistic parameters in recognition of partial discharge in transformers[J]. High Voltage Engineering, 2009, 35(2): 277-281.
[4] 刘双宝, 吕超, 于继来, 等. 希尔伯特-黄变换在变压器局部放电脉冲识别中的应用[J]. 中国电机工程学报, 2008, 28(31): 114-119. Liu Shuangbao, Lü Chao, Yu Jilai, et al. Application of hilbert-huang transform in pattern recognition for partial discharge of transformers[J]. Proceedings of the CSEE, 2008, 28(31): 114-119.
[5] 李剑, 孙才新, 杜林, 等. 局部放电灰度图象分维数的研究[J]. 中国电机工程学报, 2002, 22(8): 123- 127. Li Jian, Sun Caixin, Du Lin, et al. Study on fractal dimension of PD gray intensity image[J]. Proceedings of the CSEE, 2002, 22(8): 123-127.
[6] Dey D, Chatterjee B, Chakravorti S, et al. Cross- wavelet transform as a new paradigm for feature extraction from noisy partial discharge pulses[J]. IEEE Transactions on Dielectrics and Electrical Insulation, 2010, 17(1): 157-166.
[7] Wang Manghui. Partial discharge pattern recogni- tion of current transformers using an ENN[J]. IEEE Transactions on Power Delivery, 2005, 20(3): 1984- 1990.
[8] 司文荣, 李军浩, 袁鹏, 等. 气体绝缘组合电器多局部放电源的检测与识别[J]. 中国电机工程学报, 2009, 29(16): 119-126. Si Wenrong, Li Junhao, Yuan Peng, et al. Detection and identification techniques for multi-PD source in GIS[J]. Proceedings of the CSEE, 2009, 29(16): 119- 126.
[9] 荣海娜, 张葛祥, 金炜东. 系统辨识中支持向量机核函数及其参数的研究[J]. 系统仿真学报, 2006, 18(11): 3204-3209. Rong Haina, Zhang Gexiang, Jin Weidong. Selection of kernel functions and parameters for support vector machines in system identification[J]. Journal of System Simulation, 2006, 18(11): 3204-3209.
[10] Lee Y, Lin Y, Wahba G. Multicategory support vector machines: theory and application to the classification of microarray data and satellite radiance data[J]. Journal of the American Statistical Association, 2004, 99(3): 67-81.
[11] Kennedy J. Bare bones particle swarms[C]. Proceedings of IEEE Swarm Intelligence Symposium, Indiana, USA, 2003: 80-87.
[12] 王国利, 郝艳捧, 李彦明. 油中典型局部放电模型放电波形特征参数的提取[J]. 电网技术, 2001, 25(10): 34-37, 46. Wang Guoli, Hao Yanpeng, Li Yanming. Pulse current parameter evaluation of typical partial discharge models in oil[J]. Power System Technology, 2001, 25(10): 34-37, 46.
[13] 梁帅伟, 廖瑞金, 杨丽君, 等. 油纸绝缘老化的超宽频带局部放电信号时频域特性逐步判别分析[J]. 电网技术, 2007, 31(22): 38-43. Liang Shuaiwei, Liao Ruijin, Yang Lijun, et al. Stepwise discriminant analysis on time-domain and frequency-domain characteristics of ultra-wideband partial discharge signals for oil-paper insulation ageing [J]. Power System Technology, 2007, 31(22): 38-43.
[14] Gulski E, Kreuger F H. Computer-aided recognition of discharge sources[J]. IEEE Transactions on Electrical Insulation, 1992, 27(1): 82-92.
[15] Evagorou D, Kyprianou A, Lewin P L, et al. Feature extraction of partial discharge signals using the wavelet packet transform and classiﬁcation with a probabilistic neural network[J]. IET Science, Measure- ment and Technology, 2010, 4(3): 177-192.