褚若波;张认成;杨凯;肖金超;

• 1:机电装备过程监测及系统优化福建省高校重点实验室(华侨大学)
• 2:中国科学院沈阳自动化研究所广州分所

摘要(Abstract)：

低压配电网的电弧故障是诱发电气火灾的重要原因之一。配电网发生串联电弧故障时的电流一般较小,其有效值达不到过电流保护装置的整定值,而且在某些负载工况下,正常工作状态电流与串联电弧故障电流波形特征非常相似,导致串联电弧难以识别。针对串联电弧故障的识别难点,提出了一种基于多层卷积神经网络的时域可视化识别方法。使用高频耦合滤波电路和高速数据采集系统来采集串联电弧故障的高频信号。通过构建多层卷积神经网络,提取电弧图像高维特征。以时域灰度值图像的形式直观展示了卷积神经网络算法对故障电弧数据的抽象特征提取情况。通过与前沿机器学习预测算法进行对比分析,所提出的算法具有对典型负载的串联电弧进行特征学习和识别的良好特性,并且在其他故障诊断领域也具有重要的借鉴意义。

关键词(KeyWords)： 卷积神经网络;串联电弧故障;高频耦合滤波电路

Abstract:

Keywords:

基金项目(Foundation): 福建省自然科学基金项目(2018J05082);; 福建省产学合作重大科技项目(2016H6014);; 广州市珠江科技新星专项资助(201710010023);; 华侨大学研究生科研创新基金项目~~

作者(Author): 褚若波;张认成;杨凯;肖金超;

Email:

DOI: 10.13335/j.1000-3673.pst.2019.2489

参考文献(References)：

• [1]应急管理部消防救援局．数说2018年全国火灾及出警情况[EB/OL]．北京：应急管理部消防救援局，2018.Http://www.119.gov.cn/xiaofang/hztj/36306.htm[2019-10-14]．
• [2]杨凯，张认成，杨建红，等．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,et al.Series arc fault diagnostic method based on fractal dimension and support vector machine[J].Transactions of China Electrotechnical Society,2016,31(2):70-77(in Chinese)．
• [3]刘官耕，杜松怀，苏娟，等．低压电弧故障防护技术研究与发展趋势[J]．电网技术，2017,41(1):321-329.Liu Guangeng,Du Songhuai,Su Juan,et al.Research on LV arc fault protection and its development trends[J].Power System Technology,2017,41(1):321-329(in Chinese)．
• [4]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(in Chinese)．
• [5]周念成，周川，王强钢，等．基于改进拉普拉斯分值的开关柜故障特征选择和诊断方法[J]．电网技术，2015,39(3):850-855.Zhou Niancheng,Zhou Chuan,Wang Qianggang,et al.Improved Laplacian score based fault feature selection of switchgear cabinet and its diagnosis[J].Power System Technology,2015,39(3):850-855(in Chinese)．
• [6]Sidhu T S,Singh G,Sachdev M S.Microprocessor based instrument for detecting and locating electric arcs[J].IEEE Transactions on Power Delivery,1998,13(4):1079-1085．
• [7]卢其威，王涛，李宗睿，等．基于小波变换和奇异值分解的串联电弧故障检测方法[J]．电工技术学报，2017,32(17):208-217.Lu Qiwei,Wang Tao,Li Zongrui,et al.Detection method of series arcing fault based on wavelet transform and singular value decomposition[J].Transactions of China Electrotechnical Society,2017,32(17):208-217(in Chinese)．
• [8]Artale G,Cataliotti A,Nuccio V C S,et al.A set of indicators for arc faults detection based on low frequency harmonic analysis[C]//2016IEEE International Instrumentation and Measurement Technology Conference (I2MTC).IEEE,2016．
• [9]Hadziefendic N,Kostic M,Radakovic Z.Detection of series arcing in low-voltage electrical installations[J].European Transactions on Electrical Power,2009,19(3):423-432．
• [10]高艳艳，张认成，杨建红，等．采用高频特性的低压电弧故障识别方法[J]．电力系统及其自动化学报，2016,28(6):49-55.Gao Yanyan,Zhang Rencheng,Yang Jianhong,et al.Method of low-voltage arc fault recognition using high frequency feature[J].Proceedings of the CSU-EPSA,2016,28(6):49-55(in Chinese)．
• [11]Wang Y,Zhang F,Zhang S.A new methodology for identifying arc fault by sparse representation and neural network[J].IEEETransactions on Instrumentation&Measurement,2018,PP(99):1-12．
• [12]郭凤仪，邓勇，王智勇，等．基于灰度-梯度共生矩阵的串联故障电弧特征[J]．电工技术学报，2018,33(1):71-81.Guo Fengyi,Deng Yong,Wang Zhiyong,et al.Series arc fault characteristics based on gray level-gradient co-occurrence matrix[J].Transactions of China Electrotechnical Society,2018,33(1):71-81(in Chinese)．
• [13]Kai Y,Rencheng Z,Jianhong Y,et al.A novel arc fault detector for early detection of electrical fires[J].Sensors,2016,16(4):500-522．
• [14]Rumelhart D E,Hintion G E,Williams R J.Learning representations by back-propagating errors[J].Nature,1986,323(6088):533-536．
• [15]徐舒玮，邱才明，张东霞，等．基于深度学习的输电线路故障类型辨识[J]．中国电机工程学报，2019,39(1):67-76+323.Xu Shuwei,Qiu Caiming,Zhang Dongxia,et al.A deep learning approach for fault type identification of transmission line[J].Proceedings of the CSEE,2019,39(1):67-76+323(in Chinese)．
• [16]Goodfellow I,Bengio Y,Courville A.Deep learning[M].Cambridge,MA,USA:MIT,2016．
• [17]Srivastava N,Hinton G,Krizhevsky A,et al.Dropout:a simple way to prevent neural networks from overfitting[J].Journal of Machine Learning Research,2014,15(1):1929-1958．
• [18]Duchi J,Hazan E,Singer Y.Adaptive subgradient methods for online learning and stochastic optimization[J].Journal of Machine Learning Research,2011,12(7):257-269．
• [19]Kingma D P,Ba J.Adam:a method for stochastic optimization[J].Computer Science,2014．
• [20]Lecun Y,Bengio Y,Hinton G.Deep learning[J].Nature,2015,521(7553):436．
• [21]Laurens V D M,Hinton G.Visualizing data using t-SNE[J].Journal of Machine Learning Research,2008,9(2605):2579-2605．
• [22]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+302.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+302(in Chinese).