[1]赵文清,严海,王晓辉.BP神经网络和支持向量机相结合的电容器介损角辨识[J].智能系统学报,2019,14(01):134-140.[doi:10.11992/tis.201805034]
 ZHAO Wenqing,YAN Hai,WANG Xiaohui.Capacitor dielectric loss angle identification based on a BP neural network and SVM[J].CAAI Transactions on Intelligent Systems,2019,14(01):134-140.[doi:10.11992/tis.201805034]
点击复制

BP神经网络和支持向量机相结合的电容器介损角辨识(/HTML)
分享到:

《智能系统学报》[ISSN:1673-4785/CN:23-1538/TP]

卷:
第14卷
期数:
2019年01期
页码:
134-140
栏目:
出版日期:
2019-01-05

文章信息/Info

Title:
Capacitor dielectric loss angle identification based on a BP neural network and SVM
作者:
赵文清 严海 王晓辉
华北电力大学 控制与计算机工程学院, 河北 保定 071003
Author(s):
ZHAO Wenqing YAN Hai WANG Xiaohui
School of Control and Computer Engineering, North China Electric Power University, Baoding 071003, China
关键词:
电容器介质损耗正向求解频率介损角BP神经网络支持向量机深度学习
Keywords:
capacitorsdielectric lossforward solutionfrequencydielectric loss angleBP neural networksupport vector machinedeep learning
分类号:
TP18
DOI:
10.11992/tis.201805034
摘要:
针对电力电容器介质损耗的计算方法稳定性较差,频率波动对介损角的辨识有较大影响的问题,提出了BP神经网络和支持向量机(support vector machine, SVM)相结合(BP-SVM)的辨识方法,并且首次应用于电容器介损角的辨识。在辨识过程中,首先,对电容器工作一段时间的信号进行采样和预处理,预处理后的信号作为训练集训练BP-SVM模型;然后,使用训练好的BP-SVM模型对预处理后新的采样信号进行辨识,判断介损角的变化量。此外,给出了基于BP-SVM模型的介损角表示信号Dδt)的计算过程,同时分析了在讨论域内信号Dδt)的幅值即是介损角δ。仿真分析结果表明,提出的BP神经网络和SVM相结合的电容器介损角辨识方法比基于深度学习的辨识方法具有更高的辨识准确率,并且频率变化对BP-SVM方法的辨识性能无明显影响。
Abstract:
The stability of the calculation method for dielectric capacitor loss is poor, and the frequency fluctuation has a great influence on the identification of dielectric loss angle. To overcome this limitation, an identification method in combination with a back propagating (BP) neural network and support vector machine (SVM), BP-SVM, is proposed. For the first time, BP-SVM is applied to the identification of capacitor dielectric loss angle. In the identification process, first, the signal of a capacitor working for a period of time was sampled and preprocessed, and these signals were used as a training set to train the BP-SVM model. Then, the trained BP-SVM model was used to preprocess the newly sampled signal. The sampled signal was identified to determine the amount of change in the dielectric loss angle. In addition, the calculation process of the dielectric loss angle representation signal, Dδ(t), based on the BP-SVM model, is given. At the same time, the amplitude of the signal, Dδ(t), in the discussion section, is the dielectric loss angle δ. The simulation analysis results showed that the proposed method for identifying the dielectric loss angle of capacitors combined with a BP neural network and SVM had a higher recognition accuracy than the deep learning-based identification method, and the frequency variation had no significant effect on the identification performance of BP-SVM.

参考文献/References:

[1] 李天云, 袁明哲, 蔡国伟, 等. 基于随机子空间和最小二乘法的介质损耗角检测方法[J]. 高电压技术, 2011, 37(4):828-833 LI Tianyun, YUAN Mingzhe, CAI Guowei, et al. Measurement algorithm of dielectric loss angle based on SSI-LS[J]. High voltage engineering, 2011, 37(4):828-833
[2] 王晓辉, 朱永利, 王艳, 等. 基于深度学习的电容器介损角在线辨识[J]. 电工技术学报, 2017, 32(15):145-152 WANG Xiaohui, ZHU Yongli, WANG Yan, et al. Online Identification method of power capacitor dielectric loss angle based on deep learning[J]. Transactions of China electrotechnical society, 2017, 32(15):145-152
[3] 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
[4] WANG P, RGHUVEER M R, MCDERMID W, et al. A digital technique for the on-line measurement of dissipation factor and capacitance[J]. IEEE transactions on dielectrics and electrical insulation, 2001, 8(2):228-232.
[5] 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, 34 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, 34
[6] 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):233-236, 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 and control, 2010, 18(1):233-236, 242
[7] 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
[8] 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
[9] 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):3-5, 8 WANG Nan, LV Fangcheng, LIANG Ying, et al. Digital measurement of dielectric loss based on high accuracy DFT algorithm[J]. High voltage engineering, 2003, 29(4):3-5, 8
[10] 王微乐, 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(自然科学版), 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 (science and technology), 2001, 41(9):5-8
[11] 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
[12] LI Q, ZHAO T, SIEW W H. Definition and digital algorithms of dielectric loss factor for condition monitoring of high-voltage power equipment with harmonics emphasis[J]. IEE proceedings-generation, transmission and distribution, 2005, 152(3):309-312.
[13] 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):327-329, 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):327-329, 332
[14] 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
[15] 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
[16] 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
[17] 陈楷, 胡志坚, 王卉, 等. 介损角的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
[18] WANG Kang, TENG Zhaosheng, WEN He, et al. Fast measurement of dielectric loss angle with time-domain quasi-synchronous algorithm[J]. IEEE transactions on instrumentation and measurement, 2015, 64(4):935-942.
[19] 王永, 滕召胜, 李建闽, 等. 基于采样序列重构的高精度介损角测量方法[J/OL]. 电工技术学报,[2018-04-24]. https://doi.org/10.19595/j.cnki.1000-6753.tces.171699. WANG Yong, TENG Zhaosheng, LI Jianmin, et al. High accuracy dielectric loss angle measurement method based on sampling sequence reconstruction[J/OL]. Transactions of China electrotechnical society,[2018-04-24]. https://doi.org/10.19595/j.cnki.1000-6753.tces.171699.

备注/Memo

备注/Memo:
收稿日期:2018-05-23。
基金项目:中央高校基本科研业务专项资金项目(2014MS131).
作者简介:赵文清,女,1973年生,教授,博士,主要研究方向为人工智能与数据挖掘。发表学术论文50余篇,被SCI、EI检索30余篇;严海,男,1992年生,硕士研究生,主要研究方向为机器学习和深度学习目标检测;王晓辉,男,1981年生,博士,主要研究方向为电力系统自动化和深度学习。
通讯作者:赵文清.E-mail:jbzwq@126.com
更新日期/Last Update: 1900-01-01