基于分形维数和支持向量机的串联电弧故障诊断方法

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (379 KB)
输出: BibTeX | EndNote (RIS)

摘要电弧故障是引起电气火灾的重要原因之一。针对串联电弧故障随机性、多样性和隐蔽性等带来的诊断难题,为提高故障诊断率,设计了一种新的串联电弧故障诊断方法。借助高频电流传感器和高速数据采集系统采集串联电弧故障电流,通过分形维数定量衡量高频电流信号的混沌特性,以便提取串联电弧故障的特征信息,以盒维数和关联维数构造串联电弧故障的特征向量,采用最小二乘支持向量机对电流信号的特征向量进行分类,实现了线路正常与串联电弧故障状态的正确区分。运用所建立的实验平台验证了整个诊断方法的有效性,实验结果表明,串联电弧故障诊断率达到98%以上,所设计的诊断方法具有良好的泛化能力。

	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
	杨凯
	张认成
	杨建红
	杜建华
	陈首虹
	涂然

关键词 ：串联电弧故障, 分形维数, 高频信号, 盒维数, 关联维数, 支持向量机

Abstract：Arc fault is one of the important reasons for electrical fires. Due to the diagnostic difficulties of randomness, diversity and concealment in series arc faults, a new diagnostic method for series arc fault is designed in this paper to raise the fault diagnostic rate. Series arc fault currents were acquired by high frequency current transformers and a high-speed data acquisition system. To extract characteristic information of series arc faults, the chaotic characteristics of high frequency currents were quantitatively described by fractal dimensions. Afterwards, the featured vectors of series arc fault were constructed by the box dimension and the correlation dimension. And current characteristic vectors were classified by least squares support vector machine (LSSVM). Then, the normal state and the series arc fault state were correctly discriminated. Finally, the designed method was verified via the set-up experimental platform. The diagnostic rate of series arc fault is over 98.0%, which shows the designed method has good generalization ability.

Key words： Series arc fault fractal dimension high frequency signal box dimension correlation dimension support vector machine

收稿日期: 2014-08-07 出版日期: 2016-03-03

PACS:

TM501

基金资助:国家自然科学基金（51506059）,福建省科技计划重点项目（2013H0028）,厦门市科技计划（3502Z20143043）和泉州市科技计划（2014Z114）资助项目

通讯作者: 张认成男,1961年生,博士,教授,博士生导师,主要研究方向为机电系统状态监测与故障诊断。E-mail: phzzrc@hqu.edu.cn

作者简介: 杨凯男,1985年生,博士研究生,主要研究方向为电弧故障诊断。E-mail: yangkai1@hqu.edu.cn

引用本文:

杨凯, 张认成, 杨建红, 杜建华, 陈首虹, 涂然. 基于分形维数和支持向量机的串联电弧故障诊断方法[J]. 电工技术学报, 2016, 31(2): 70-77. Yang Kai, Zhang Rencheng, Yang Jianhong, Du Jianhua, Chen Shouhong, Tu Ran. Series Arc Fault Diagnostic Method Based on Fractal Dimension and Support Vector Machine. Transactions of China Electrotechnical Society, 2016, 31(2): 70-77.

链接本文:

https://dgjsxb.ces-transaction.com/CN/Y2016/V31/I2/70

[1] 公安部消防局. 中国消防年鉴(2014)[M]. 昆明: 云南人民出版社, 2014.
[2] Lee R H. The other electrical hazard: electric arc flash[J]. IEEE Transactions on Industry Applications, 1982, IA-18 (3): 246-251.
[3] U. S. Fire Administration National Fire Data Center. Residential building electrical fires[J]. Topical Fire Report Series, 2008, 8(2): 1-9.
[4] 曾元超. 防範住家電氣火災的新技術[J]. 台電月刊, 2008(549): 26-31.
[5] 占友雄, 张认成, 杨建红, 等. 基于Camberra距离的串联电弧故障诊断方法[J]. 电力系统保护与控制, 2014, 42(12): 30-36.
Zhan Youxiong, Zhang Rencheng, Yang Jianhong, et al. Series arcing fault diagnosis based on Camberra distance[J]. Power System Protection and Control, 2014, 42(12): 30-36.
[6] Wu H R, Li X H, Stade D, et al. Arc fault model for low voltage AC systems[J]. IEEE Transactions on Power Delivery, 2005, 20(2): 1204-1205.
[7] 雍静, 桂小智, 牛亮亮, 等. 基于自回归参数模型的低压系统串联电弧故障识别[J]. 电工技术学报, 2011, 26(8): 213-219.
Yong Jing, Gui Xiaozhi, Niu Liangliang, et al. Series arc fault identification in low voltage system based on autoregressive parameter model[J]. Transactions of China Electrotechnical Society, 2011, 26(8): 213-219.
[8] Giuseppe P, Luigi M, Marco L. Simplified arc-fault model: the reduction factor of the arc current[J]. IEEE Transactions on Industry Applications, 2013, 49: 1703-1710.
[9] 杨建红, 张认成, 房怀英. Lyapunov指数法在故障电弧早期探测中的应用[J]. 电工电能新技术, 2008, 27(2): 56-58.
Yang Jianhong, Zhang Rencheng, Fang Huaiying. Early detecting of fault arcs using Lyapunov exponents[J]. Advanced Technology of Electrical Engineering and Energy, 2008, 27(2): 56-58.
[10] 蓝会立, 张认成. 基于小波分析的故障电弧伴生弧声特征提取[J]. 电力系统及其自动化学报, 2008, 20(4): 57-62.
Lan Huili, Zhang Rencheng. Study on the feature extraction of fault arc sound signal based on wavelet analysis[J]. Proceedings of the CSU-EPSA, 2008, 20(4): 57-62.
[11] Charles J K. Electromagnetic radiation behavior of low-voltage arcing fault[J]. IEEE Transactions on Power Delivery, 2009, 24(1): 416-423.
[12] Ko W S, Moon W S, Bang S B, et al. Analysis of ignition time/current characteristics and energy when series arc-fault occurs at rated 220V[J]. The Transactions of the Korean Institute of Electrical Engineers, 2013, 62(8): 1184-1191.
[13] 刘晓明, 徐叶飞, 刘婷, 等. 基于电流信号短时过零率的电弧故障检测[J]. 电工技术学报, 2015, 30(13): 125-133.
Liu Xiaoming, Xu Yefei, Liu Ting, et al. The arc fault detection based on the current signal short time zero crossing rate[J]. Transactions of China Electro- technical Society, 2015, 30(13): 125-133.
[14] Kawady T A, Elkalashy N I, Ibrahim A E, et al. Arcing fault identification using combined Gabor transform-neural network for transmission lines[J]. International Journal of Electrical Power and Energy Systems, 2014, 61: 248-258.
[15] 张士文, 张峰, 王子骏, 等. 一种基于小波变换能量与神经网络结合的串联型故障电弧辨识方法[J]. 电工技术学报, 2014, 29(6): 290-295.
Zhang Shiwen, Zhang Feng, Wang Zijun, et al. Series arc fault identification method based on energy produced by wavelet transformation and neural network[J]. Transactions of China Electrotechnical Society, 2014, 29(6): 290-295.
[16] Carlos E R. Arc fault detection and discrimination methods[J]. IEEE Transaction on Industry Applications, 2007, 43(4): 115-122.
[17] 郝研, 王太勇, 万剑, 等. 分形盒维数抗噪研究及其在故障诊断中的应用[J]. 仪器仪表学报, 2011, 32(3): 540-545.
Hao Yan, Wang Taiyong, Wan Jian, et al. Research on fractal box dimension anti-noise performance and its application in fault diagnosis[J]. Chinese Journal of Scientific Instrument, 2011, 32(3): 540-545.
[18] Grassberger P, Procaccia I. Characterization of strange attractors[J]. Physical Review Letters, 1983, 50(5): 346-349.
[19] 付强, 李晨溪, 张朝曦. 关于G-P算法计算混沌关联维的讨论[J]. 解放军理工大学学报(自然科学版) , 2014, 15(3): 275-282.
Fu Qiang, Li Chenxi, Zhang Zhaoxi. G-P algorithm for evaluating the correlation dimension in chaos[J]. Journal of PLA University of Science and Techno- logy (Natural Science Edition), 2014, 15(3): 275-282.
[20] Suykens J A K, Vandewalle J. Least squares support vector machine classifiers[J]. Neural Processing Letters, 1999, 9(3): 293-300.
[21] 王正齐, 黄学良. 基于支持向量机逆系统的无轴承异步电机非线性解耦控制[J]. 电工技术学报, 2015, 30(10): 164-170.
Wang Zhengqi, Huang Xueliang. Nonlinear decoupling control for bearingless induction motor based on support vector machines inversion[J]. Transactions of China Electrotechnical Society, 2015, 30(10): 164-170.
[22] 王瑜, 苑津莎, 尚海昆, 等. 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, et al. Optimization strategy research on combined-kernel support vector machine for partial discharge pattern recognition[J]. Transactions of China Electro- technical Society, 2015, 30(2): 229-236.
[23] 刘煌煌, 雷金勇, 蔡润庆. 基于SVM-MOPSO混合智能算法的配电网分布式电源规划[J]. 电力系统保护与控制, 2014, 42(10): 46-54.
Liu Huanghuang, Lei Jinyong, Cai Runqing, et al. Distributed generation planning in distribution network based on hybrid intelligent algorithm by SVM-MOPSO[J]. Power System Protection and Control, 2014, 42(10): 46-54.