基于深度学习的电容器介损角在线辨识

doi:10.19595/j.cnki.1000-6753.tces.160864

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (2436 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract Most of the algorithm of calculating dielectric loss factor are positive solving process, which include sampling capacitor current and voltage, and calculating the dielectric loss factor of these signals by harmonic analysis. These methods have poor robustness when there are unidentified distortions in the sampling signal. This paper proposes a capacitor dielectric loss factor identification algorithm based on the deep learning. The algorithm proposed in this paper trains a feed-forward multilayer artificial neural network with a period of online sampling signals, and identify the dielectric loss angle from new monitoring data with resolution of 0.001%. The computation of dielectric loss factor identification signal D_δ(t) is proposed, and verify the amplitude of D_δ(t) is the dielectric loss angle. And the shape of its waveform includes the interference of the monitoring device. The validity of the method has been proved by simulation. The method can achieve better ability to resist noise than hanning windows harmonic analysis method. The calculation results based on actual online monitoring data shows better robustness than hanning windows harmonic analysis method, its results is also not affected by the angle error of potential transformer.

Key words： Deep learning power capacitor dielectric loss angle online monitoring

Received: 03 June 2016 Published: 18 August 2017

PACS:

TM835.4

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Wang Xiaohui
	Zhu Yongli
	Wang Yan
	Guo Fengjuan

Cite this article:

Wang Xiaohui,Zhu Yongli,Wang Yan等. Online Identification Method of Power Capacitor Dielectric Loss Angle Based on Deep Learning[J]. Transactions of China Electrotechnical Society, 2017, 32(15): 145-152.

URL:

http://dgjsxb.ces-transaction.com/EN/10.19595/j.cnki.1000-6753.tces.160864 OR http://dgjsxb.ces-transaction.com/EN/Y2017/V32/I15/145

[1] 董爽,李天云,王永,等.在线检测介质损耗角的矩阵束方法[J].电工技术学报,2015,30(18):229-236.
Dong Shuang,Li Tianyun,Wang Yong,et al.An on-line detection method of dielectric loss angle based on matrix pencil algorithm[J].Transactions of China Electrotechnical Society,2015,30(18):229-236.
[2] Wang P,Raghuveer M R,McDermid W,et al.A digital technique forthe online measurement of dissipation factor and capacitance[J].IEEE Transactions on Dielectric Electrical Insulation,2001,8(2):228-232.
[3] 尚勇,杨敏中,王晓蓉,等.谐波分析法介质损耗因数测量的误差分析[J].电工技术学报,2002,17(3):67-71.
Shang Yong,Yang Minzhong,Wang Xiaorong,et al.Error analysis for the dielectric loss factor measurement based on harmonic analysis[J].Transactions of China Electrotechnical Society,2002,17(3):67-71.
[4] 刘伟,黄新波,章云.电容型高压设备介损在线监测系统的现场采集单元设计[J].计算机测量与控制,2010,18(1):233-242.
Liu Wei,Huang Xinbo,Zhang Yun.Design of field sampling unit of an on-line monitoring system of dielectric loss in capacitive high-voltage apparatus[J].Computer Measurement & Control,2010,18(1):233-242.
[5] 陈晓宇,郑建勇,梅军.基于LC振荡频率变化量的电容器组早期故障在线智能预警方法及其实现[J].电力系统保护与控制,2015,43(5):144-149.
Chen Xiaoyu,Zheng Jianyong,Mei Jun.Power capacitor banks failure warning method based online intelligence LC oscillation frequency variation and its implementation[J].Power System Protection and Control,2015,43(5):144-149.
[6] 徐志钮,律方成,李和明.采样时间和采样频率对基于加窗插值算法介损角测量的影响[J].华北电力大学学报,2007,34(4):7-10.
Xu Zhiniu,Lü Fangcheng,Li Heming.Influence of sampling time and sampling frequency on dielectric loss angle measurement based on windowed interpolation algorithm[J].Journal of North China Electric Power University,2007,34(4):7-10.
[7] 谢华,张会平.电压互感器角差对介损在线监测的影响分析[J].高电压技术,2003,29(5):26-28.
Xie Hua,Zhang Huiping.The influence of angle error of CVT on on-line tan δ monitoring[J].High Voltage Engineering,2003,29(5):26-28.
[8] 李振华,李红斌,张秋雁,等.一种高压电子式电流互感器在线校验系统[J].电工技术学报,2014,29(7):229-236.
Li Zhenhua,Li Hongbin,Zhang Qiuyan,et al.An online calibration system for high voltage electronic current transformers[J].Transactions of China Electrotechnical Society,2014,29(7):229-236.
[9] 蔡国雄,甄为红,杨晓洪,等.测量介质损耗的数字化过零点电压比较法[J].电网技术,2002,26(7):15-18.
Cai Guoxiong,Zhen Weihong,Yang Xiaohong,et al.A digitized zero cross point voltage method of comparison for measurement of dielectric losses[J].Power System Technology,2002,26(7):15-18.
[10]袁飞,杨震男,卢毅.一种基于相对比较法测量容性设备介质损耗的滤波算法[J].电力系统保护与控制,2015,43(19):95-100.
Yuan Fei,Yang Zhennan,Lu Yi.A filtering algorithm for measuring capacitive device dielectric loss based on relative comparison method[J].Power System Protection and Control,2015,43(19):95-100.
[11]王楠,律方成,梁英,等.基于高精度 DFT 的介损数字测量方法[J].高电压技术,2003,29(4):3-8.
Wang Nan,Lü Fangcheng,Liang Ying,et al.Digital measurement of dielectric loss based on high accuracy DFT algorithm[J].High Voltage Engineering,2003,29(4):3-8.
[12]王徽乐,李福祺,谈克雄.测量介质损耗角的高阶正弦拟合算法[J].清华大学学报,2001,41(9):5-8.
Wang Weile,Li Fuqi,Tan Kexiong.Higher-order sine fitting algorithm for dielectric loss measurement[J].Journal of Tsinghua University,2001,41(9):5-8.
[13]陈楷,胡志坚,王卉,等.介损角非同步采样算法及其应用[J].电网技术,2004,28(18):58-61.
Chen Kai,Hu Zhijian,Wang Hui,et al.Algorithm and application of dielectric loss angle based on asynchronous sampling[J].Power System Technology,2004,28(18):58-61.
[14]冯小华,张承学.修正的谐波分析法可提高介损在线测量准确度[J].高电压技术,2004,30(8):36-37.
Feng Xiaohua,Zhang Chengxue.Modified harmonics analysis approach for increasing precision in on-line measuring tan δ[J].High Voltage Engineering,2004,30(8):36-37.
[15]Li Q,Zhao T,Siew W H.Definition and digital algorithms ofdielectric loss factor for condition monitoring of high-voltage powerequipment with harmonics emphasis[J].IEEE Proceedings on Generation,Transmission and Distribution,2005,152(3):309-312.
[16]张忠蕾,李庆民,陈鹏.谐波条件下高压电气设备介质损耗因数的定义和数字化算法[J].高压电器,2004,40(5):327-332.
Zhang Zhonglei,Li Qingmin,Chen Peng.Definition and digital algorithms for dielectric loss factor of high voltage power apparatus under harmonics condition[J].High Voltage Apparatus,2004,40(5):327-332.
[17]张介秋,梁昌洪,韩峰岩,等.介质损耗因数的卷积窗加权算法[J].电工技术学报,2005,20(3):100-104.
Zhang Jieqiu,Liang Changhong,Han Fengyan,et al.Convolution window weighted algorithm for dielectric loss factor[J].Transactions of China Electrotechnical Society,2005,20(3):100-104.
[18]徐志钮,律方成,赵丽娟.基于加汉宁窗插值的谐波分析法用于介损角测量的分析[J].电力系统自动化,2006,30(2):81-85.
Xu Zhiniu,Lü Fangcheng,Zhao Lijuan,et al.Analysis of dielectric loss angle measurement by Hanning windowing interpolation algorithm based on FFT[J].Automation of Electric Power Systems,2006,30(2):81-85.
[19]段大鹏,江秀臣,孙才新,等.基于正交分解的介质损耗因数数字测量算法[J].中国电机工程学报,2008,28(7):127-133.
Duan Dapeng,Jiang Xiuchen,Sun Caixin,et al.A novel algorithm of dielectric loss measurement based on orthogonal decomposition[J].Proceedings of the CSEE,2008,28(7):127-133.
[20]温和,滕召胜,王一,等.基于三角自卷积窗的介损角高精度测量算法[J].电工技术学报,2009,24(3):203-208.
Wen He,Teng Zhaosheng,Wang Yi,et al.High accuracy dielectric loss angle measurement algorithm based on triangular self-convolution window[J].Transactions of China Electrotechnical Society,2009,24(3):203-208.
[21]李天云,祝磊,康玉芳,等.基于总体最小二乘-旋转矢量不变技术的介损角测量算法[J].电网技术,2009,33(18):171-175.
Li Tianyun,Zhu Lei,Kang Yufang,et al.Dielectric loss angle measurement algorithm based on TLS-ESPRIT[J].Power System Technology,2009,33(18):171-175.
[22]曾博,唐求,卿柏元,等.基于Nuttall自卷积窗的改进FFT谱分析方法[J].电工技术学报,2014,29(7):59-65.
Zeng Bo,Tang Qiu,Qing Baiyuan,et al.Spectral analysis method based on improved FFT by Nuttall self-convolution window[J].Transactions of China Electrotechnical Society,2014,29(7):59-65.
[23]黄冬梅,龚仁喜,焦凤昌,等.莱夫-文森特窗三谱线插值的电力谐波分析[J].电力系统保护与控制,2014(2):28-34.
Huang Dongmei,Gong Renxi,Jiao Fengchang,et al.Power harmonic analysis based on Rife-Vincent window and triple-spectral-line interpolation[J].Power System Protection and Control,2014,42(2):28-34.
[24]余凯,贾磊,陈雨强,等.深度学习的昨天、今天和明天[J].计算机研究与发展,2013,50(9):1799-1804.
Yu Kai,Jia Lei,Chen Yuqiang,et al.Deep learning:yesterday,today,and tomorrow[J].Journal of Computer Research & Development,2013,50(9):1799-1804.
[25]孙志军,薛磊,许阳明,等.深度学习研究综述[J].计算机应用研究,2012,29(8):2806-2810.
Sun Zhijun,Xue Lei,Xu Yangming,et al.Overview of deep learning[J].Application Research of Com-puters,2012,29(8):2806-2810.
[26]胡洋.基于马尔可夫链蒙特卡罗方法的RBM学习算法改进[D].上海:上海交通大学,2012.
[27]陈宇,郑德权,赵铁军.基于Deep Belief Nets的中文名实体关系抽取[J].软件学报,2012,23(10):2572-2585.
Chen Yu,Zheng Dequan,Zhao Tiejun.Chinese relation extraction based on deep belief nets[J].Journal of Software,2012,23(10):2572-2585.
[28]Chen Yushi,Zhao Xing,Jia Xiuping.Spectral-spatial classification of hyperspectral data based on deep belief network[J].IEEE Journal of Selected Topics in Applied Earth Observations & Remote Sensing,2015,8(6):1-12.
[29]李岳云,许悦雷,马时平,等.深度卷积神经网络的显著性检测[J].中国图象图形学报,2016,21(1):53-59.
Li Yueyun,Xu Yuelei,Ma Shiping,et al.Saliency detection based on deep convolutional neural network[J].Journal of Image and Graphics,2016,21(1):53-59.
[30]林颖,郭志红,陈玉峰.基于卷积递归网络的电流互感器红外故障图像诊断[J].电力系统保护与控制,2015,43(16):87-94.
Lin Ying,Guo Zhihong,Chen Yufeng,et al.Convolutional-recursive network based current transformer infrared fault image diagnosis[J].Power System Protection and Control,2015,43(16):87-94.