[1]陈钦柱,张 涵,赵海龙,等.基于FSWT—SSAEs的配电网内部过电压自动提取与分类识别[J].高压电器,2020,56(07):166-172.[doi:10.13296/j.1001-1609.hva.2020.07.024]
 CHEN Qinzhu,ZHANG Han,ZHAO Hailong,et al.Automatically Extracting and Classification Recognition Internal Overvoltage Measured in Distribution Networks Based on FSWT-SSAEs[J].High Voltage Apparatus,2020,56(07):166-172.[doi:10.13296/j.1001-1609.hva.2020.07.024]
点击复制

基于FSWT—SSAEs的配电网内部过电压自动提取与分类识别()
分享到:

《高压电器》[ISSN:1001-1609/CN:61-11271/TM]

卷:
第56卷
期数:
2020年07期
页码:
166-172
栏目:
研究与分析
出版日期:
2020-07-31

文章信息/Info

Title:
Automatically Extracting and Classification Recognition Internal Overvoltage Measured in Distribution Networks Based on FSWT-SSAEs
作者:
陈钦柱1 张 涵2 赵海龙1 袁 涛2 姚 冬1 司马文霞2
(1. 海南省电网理化分析重点实验室, 海口 570311; 2. 重庆大学输配电装备及系统安全与新技术国家重点实验室, 重庆 400030)
Author(s):
CHEN Qinzhu1 ZHANG Han2 ZHAO Hailong1 YUAN Tao2 YAO Dong1 SIMA Wenxia2
(1. Key Laboratory of Physical and Chemical Analysis for Electric Power of Hainan Province, Haikou 570311, China; 2. State Key Laboratory of Power Transmission Equipment & System Security and New Technology, Chongqing University, Chongqing 400030, China)
关键词:
实测过电压 时频分布图 九宫图 多层稀疏自编码 分类识别
Keywords:
measured overvoltage time-frequency distribution Lo Shu Square stacked sparse autoencoders classification recognition
DOI:
10.13296/j.1001-1609.hva.2020.07.024
摘要:
过电压是造成电网绝缘损坏的主要原因,对电气设备绝缘可靠性、系统绝缘配合、继电保护以及运行控制均产生重要影响。研究配电网过电压的特征提取与分类识别对于电网运行事故溯源以及设备绝缘风险评估等均具有难以替代的现实意义。文中基于频率切片小波变换(FSWT)时频分析方法构建过电压时频分布九宫图,完成实测过电压整体与细节信息的完全提取;改进多层稀疏自编码算法(SSAEs),实现实测过电压特征的自动提取与分类识别;分析改进多层稀疏自编码网络中关键参数(卷积块大小、卷积特征数量以及稀疏性参数)的影响,确定最优参数,实现最佳分类识别效果。结果表明,过电压时频分布九宫图与改进多层稀疏自编码算法相结合能够高效的自动提取和分类实测过电压波形,分类精度良好。
Abstract:
The overvoltage is the main cause of insulation damage in power grid, it has an important impact on the insulation reliability of electrical equipment, system insulation coordination, relay protection and operation control. It is of great practical significance to study the feature extraction and classification of the measured overvoltage in the distribution network for tracing the source of power grid operation accidents and risk assessment of equipment insulation, etc. This paper constructed the band of time-frequency distribution of overvoltage in Lo Shu Square based on FSWT and completed the overall and detail information of overvoltage extraction. The measured overvoltage feature automatically extraction and classification is achieved based on modified SSAEs. The influence of key parameters, namely, the size of convolutional patches, the number of convolutional maps and sparsity parameter in modified SSAEs are analyzed respectively, and the best optimization parameters are determined, the best classification and recognition effect is achieved. The results show that the combination of the Lo Shu Square of the time-frequency distribution of overvoltage and the modified SSAEs algorithm can automatically extract and classify the measured overvoltage waveform with good classification accuracy.

参考文献/References:

[1] YANG M, SIMA W X. Suppressing ferroresonance in potential transformers using a model-free active-resistance controller[J]. International Journal of Electrical Power & Energy Systems, 2018,95(2): 384-393.
[2] 黄艳玲,司马文霞,杨 庆,等. 基于实测数据的电力系统过电压分类识别[J]. 电力系统自动化,2012,36(4):85-90.
HUANG Yanling, SIMA Wenxia,YANG Qing,et al. Classification and identification of power system overvoltages based on measured data[J]. Automation of Electric Power Systems, 2012, 36(4): 85-90.
[3] 司马文霞,王 荆,杨 庆,等. Hilbert-Huang变换在电力系统过电压识别中的应用[J]. 高电压技术,2010,36(6):1480-1486.
SIMA Wenxia, WANG Jing, YANG Qing,et al. Application of hilbert-huang transform to power system over-voltage recognition[J]. High Voltage Engineering, 2010,36(6): 1480-1486.
[4] 司马文霞,冉 锐,袁 涛,等. 采用数学形态学的弧光接地过电压识别方法[J]. 高电压技术,2010,36(4) : 835-841.
SIMA Wenxia, RAN Rui, YUAN Tao,et al. Identification of arc grounding over-voltage using mathematical morphology transform[J]. High Voltage Engineering,2010,36(4): 835-841.
[5] 杜 林,李 欣,王丽蓉,等. 电力系统暂时过电压多级支持向量机分层识别[J]. 电力系统保护与控制,2012,40(4):26-36.
DU Lin, LI Xin, WANG Lirong,et al. Temporary overvoltage layered pattern identification based on multistage support vector machine in power system[J]. Power System Protection and Control,2012, 40(4): 26-36.
[6] DEOKAR S A, WAGHMARE L M. Integrated DWT-FFT approach for detection and classification of power quality disturbances[J]. International Journal of Electrical & Power System, 2015,61(1):594-605.
[7] YANG M, SIMA W, YANG Q,et al. Non-linear characteristic quantity extraction of ferroresonance overvoltage time series[J]. IET Generation, Transmission & Distribution, 2017; 11(6): 1427-1433.
[8] YAN Z H, MIYAMOTO A, JIANG Z W. Frequency slice wavelet transform for transient vibration response analysis[J]. Mechanical Systems and Signal Processing, 2009, 23(5): 1474-1489.
[9] YAN Z H, MIYAMOTO A, JIANG Z W, et al. An overall theoretical description of frequency slice wavelet transform[J]. Mechanical Systems and Signal Processing, 2010, 24(2): 491-507.
[10] 赵国彦,邓青林,马 举. 基于FSWT 时频分析的矿山微震信号分析与识别[J]. 岩土工程学报,2015,37(2):306-312.
ZHAO Guoyan, DENG Qinglin, MA Ju. Recognition of mine microseismic signals based on FSWT time-frequency analysis[J]. Chinese Journal of Geotechnical Engineering,2015,37(2):306-312.
[11] HINTON G E, SALAKHUTDINOV R R. Reducing the dimensionality of data with neural network[J]. Science,2006,313(5786):504-507.
[12] NG A. Sparse autoencoder[J]. CS294A Lecture,2011(72):1-19.
[13] CHEN K, HU J,HE J L, A framework for automatically extracting overvoltage features based on sparse autoencoder[EB/OL]. 2016-05-25.http://dx.doi.org/10.1109/TSG.
[14] SIMA W X, ZHANG H,YANG M,et al. A framework for automatically cleansing overvoltage data measured from transmission and distribution systems[J]. International Journal of Electrical Power & Energy Systems,2018,101(35): 482-490.
[15] MARTINEZ A M,KAK A C. PCA versus LDA[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001,23(2):228-233.
[16] GOODFELLOW I,BENGIO Y,COURVILLE A. Deep
learning[M]. Boston:the MIT Press,2016:179-193.
[17] 郑含博,王 伟,李晓纲,等. 基于多分类最小二乘支持向量机和改进粒子群优化算法的电力变压器故障诊断方法[J].高电压技术,2014,40(11) : 3424-3429.
ZHENG Hanbo,WANG Wei,LI Xiaogang,et al. Fault diagnosis method of power transformers using multi-class LS-SVM and improved PSO[J]. High Voltage Engineering, 2014, 40(11) : 3424-3429.
[18] 赵文清,李庆良,王德文, 基于多模型的变压器故障组合诊断研究[J]. 高电压技术,2013,39(2):302-309.
ZHAO Wenqingm, LI Qingliang, WANG Dewen. Combinational diagnosis for transformer faults based on multi-models[J]. High Voltage Engineering,2013,39(2):302-309.
[19] 白翠粉,高文胜,金 雷,等, 基于3层贝叶斯网络的变压器综合故障诊断[J]. 高电压技术,2013,39(2):330-335.
BAI Cuifen,GAO Wensheng,JIN Lei,et al. Integrated diagnosis of transformer faults based on three-layer bayesian network[J]. High Voltage Engineering,2013,39(2):330-335.
[20] 周志华. 机器学习[M]. 北京:清华大学出版社,2016.
ZHOU Zhihua. Machine learning[M]. Beijing:Tsinghua University Press,2016.

备注/Memo

备注/Memo:
收稿日期:2020-01-20; 修回日期:2020-03-14 基金项目:国家重点研发计划(2017YFB0902701);海南电网有限责任公司科技项目(073000KK52170006);国家自然科学基金(51837002)。 Project Supported by National Key Research and Development Program of China(2017YFB0902701), Technology Program of Hainan Power Grid Co., Ltd.(073000KK52170006), National Natural Science Foundation of China(51837002).陈钦柱(1983—),男,高级工程师,主要从事高电压技术、设备状态监测、电网灾害预警防御等方面的工作。
更新日期/Last Update: 2020-07-25