|
|
|
| Series Arc Fault Identification Method Based on Energy Produced by Wavelet Transformation and Neural Network |
| Zhang Shiwen , Zhang Feng , Wang Zijun , Gu Haoying , Ning Qing |
| Shanghai Jiao Tong University Shanghai 200240 China |
|
|
|
|
Abstract Because of the low current value in AC circuits where series arc fault happens, traditional circuit protecting devices could hardly detect the arc faults effectively. A novel arc fault identification method based on energy produced by wavelet transformation and neural network is proposed. Current samples of six different kinds of loads are collected by a self-made series arc generating and wave data acquisition device. These samples are decomposed by wavelet every 5-consecutive-cycle and the average value and standard deviation of high-frequency energy in each layer are obtained. With these data, a wavelet neural network is constructed to detect serial arc faults of different kinds of loads. Particle swarm optimization algorithm is applied to optimize the initial value of neural network and adaptive learning rate is used to improve the learning speed. The algorithm gives the definite YES or NO output with an acceptable training speed. The availability of the extracted characteristics in the input layer of the neural network is confirmed by mean impact value method. The recognition of the test samples shows nearly 95 percent accuracy rate.
|
|
Received: 11 July 2012
Published: 05 November 2014
|
|
|
|
|
|
[1] 戴隽文, 郝瑞祥, 游小杰. 一种用于大功率电弧加热器的等离子电弧模型[J]. 电工技术学报, 2011, 26(1): 129-134. Dai Junwen, Hao Ruixiang, You Xiaojie. A plasma arc model used in high power arc heater[J]. Transactions of China Electrotechnical Society, 2011, 26(1): 129-134.
[2] 王育飞, 姜建国. 用于电能质量研究的新型交流电弧炉混沌模型[J]. 中国电机工程学报, 2008, 28(10): 106-110. Wang Yufei, Jiang Jianguo. A novel chaotic model of AC electric arc furnace for power quality study[J]. Proceedings of the CSEE, 2008, 28(10): 106-110.
[3] Gregory G D, Scott G W. The arc-fault circuit interrupter: an emerging product[C]. Industrial and Commercial Power Systems Technical Conference, 1998: 48-55.
[4] Gregory G D, Kon W, Dvorak R F. More about arc-fault circuit interrupters[C]. The 38th IAS Annual Meeting, Industry Applications Conference, 2003, 2: 1306-1313.
[5] Kim C J. Electromagnetic radiation behavior of low-voltage arcing fault[J]. IEEE Transactions on Power Delivery, 2009, 24(1): 416-423.
[6] 杨建红, 张认成, 房怀英. Duffing振子信号探测在故障电弧短路保护中的应用[J]. 电力系统自动化, 2006, 30(24): 69-72. Yang Jianhong, Zhang Rencheng, Fang Huaiying. Application of duffing oscillator signal detection to arcing faults protection[J]. Automation of Electric Power Systems, 2006, 30(24): 69-72.
[7] 王静红, 刘教民. 基于双目立视技术的开关电弧图像处理[J]. 电工技术学报, 2011, 26(1): 86-91. Wang Jinghong, Liu Jiaomin. Switching arc image processing based on binocular stereo vision[J]. Transactions of China Electrotechnical Society, 2011, 26(1): 86-91.
[8] 邹云峰, 吴为麟, 李智勇. 基于自组织映射神经网络的低压故障电弧聚类分析[J]. 仪器仪表学报, 2010, 31(3): 571-576. Zou Yunfeng, Wu Weilin, Li Zhiyong. Cluster analysis of art fault in low-voltage based on SOM neural network[J]. Chinese Journal of Scientific Instrument, 2010, 31(3): 571-576.
[9] 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.
[10] 孙鹏, 郑志成, 闫荣妮, 等. 采用小波熵的串联型故障电弧检测方法[J]. 中国电机工程学报, 2010, 30(S1): 232-236. Sun Peng, Zheng Zhicheng, Yan Rongni, et al. Detection method of arc fault in series with wavelet entropy[J]. Proceedings of the CSEE, 2010, 30(S1): 232-236.
[11] Underwriter Laboratories Inc. UL1699, Standard for safety for arc fault circuit interrupters[S]. 2nd Ed, April 7, 2006.
[12] Burrus C S, 程正兴. 小波与小波变换导论[M]. 北京: 机械工业出版社, 2007.
[13] 田景文, 高美娟. 人工神经网络算法研究及应用[M]. 北京: 北京理工大学出版社, 2006.
[14] 高宁, 杨静宇. 群智能算法及其应用[M]. 北京: 中国水利水电出版社, 2006.
[15] 史峰, 王小川, 郁磊, 等. MATLAB神经网络30个案例分析[M]. 北京: 北京航空航天大学出版社, 2010. |
|
|
|
2014, Vol. 29 
