基于随机森林算法的低压系统漏电检测技术研究
CSTR:
作者:
作者单位:

(1.国网湖南省电力有限公司,湖南 长沙 410004;2.智能电气量测与应用技术湖南省重点实验室,湖南 长沙 410004;3.长沙理工大学电气与信息工程学院,湖南 长沙 410114)

通讯作者:

肖湘奇(1989—),男,工程师,主要从事电能计量及用电安全技术等研究;E?mail:84578610@qq.com

中图分类号:

TM588

基金项目:

国家电网有限公司总部科技项目(5700?202155204A?0?0?00)


Research on leakage detection technology of low‑voltage power system based on random forest algorithm
Author:
Affiliation:

(1.State Grid Hunan Electric Power Co., Ltd., Changsha 410004, China; 2.Hunan Provincial Key Laboratory of Intelligent Electrical Measurement and Application Technology, Changsha 410004, China; 3.School of Electrical & Information Engineering, Changsha University of Science & Technology, Changsha 410114, China)

  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [26]
  • | | | |
  • 文章评论
    摘要:

    随着低压配电系统规模及用户需求量迅速增加,用户线路与家庭电气设备漏电故障频发,极易发生人体触电及电气火灾事故。剩余电流保护器作为检测低压漏电故障的常用手段,近年来因线路(或设备)存在对地泄漏电流而频频误动,极大降低了保护设备投运率与可靠性。为此,本文提出一种基于随机森林(random forest,RF)算法的低压配电系统漏电检测技术,为最大程度贴近真实漏电故障场景,充分考虑实际故障场景存在的正常泄漏电流过大、故障邻近支路负荷投切频繁等干扰因素以获得贴近真实故障场景的原始剩余电流数据;通过对原始剩余电流数据进行数据预处理,分析掌握剩余电流的频域与时域特性并利用傅里叶变换算法提取时频域特征,完成低压系统漏电检测模型的建立与训练;在施加多种干扰因素情况下对漏电检测模型进行深度测试,其漏电故障的检测准确率可达99.97%,实现了多种干扰因素情况下的低压配电系统漏电故障检测;最后将支持向量机(support vector machine,SVM)算法、K最近邻(K?nearest neighbor,KNN)算法与本文基于RF算法的漏电故障检测模型的准确性进行对比,以此验证了基于RF算法的低压系统漏电检测模型的准确性与可行性。

    Abstract:

    With the rapid increase in the scale of low-voltage distribution system and user demand, leakage faults of user lines and household electrical equipment occur frequently, which increase the risk of electric shock and electrical fire accidents. Residual current protector is a common method to detect low-voltage leakage fault. In recent years, due to the existence of leakage current to ground of lines (or equipment), it also frequently false operates, which greatly reduces the operation rate and reliability of protective equipment. To overcome these issues, this paper proposes a leakage detection technology for low-voltage distribution system based on random forest (RF) algorithm. In order to closely simulate the real leakage fault scenario, the original residual current data close to the real fault scenario can be obtained by fully considering the interference factors such as excessive normal leakage current and frequent switching of load in the adjacent branch of the fault scenario. Through data preprocessing of the original residual current data, the frequency domain and time domain characteristics of the residual current are analyzed, and the time-frequency characteristics are extracted using the Fourier transform algorithm to complete the establishment and training of the low-voltage system leakage detection model. The leakage detection model is tested under the condition of multiple interference factors, and the results show that the detection accuracy of the leakage fault can reach 99.98%, realizing the leakage fault detection of low-voltage distribution system under the condition of multiple interference factors. Finally, support vector machine (SVM) algorithm, K?nearest neighbor (KNN) algorithm and the leakage fault detection accuracy based on random forest algorithm are compared to verify the accuracy and feasibility of the proposed leakage fault detection model of low-voltage system.

    参考文献
    [1] 朱领军.漏电检测的研究与分析[D].杭州:浙江大学, 2018.ZHU Lingjun.Research and analysis of leakage detection[D].Hangzhou:Zhejiang University,2018.
    [2] 汪倩,陈思磊,刘家欣,等.低压直流系统剩余电流检测技术研究综述[J].高压电器,2023,59(6):1-12. WANG Qian,CHEN Silei,LIU Jiaxin,et al.Review on research of residual current detection technology in low voltage DC systems[J].High Voltage Apparatus,2023,59(6):1-12.
    [3] 韩晓慧.低压配电网剩余电流保护优化算法研究[D].北京:中国农业大学,2017. HAN Xiaohui.Research on the optimization algorithm of residual current protection for low-voltage distribution network[D].Beijing:China Agricultural University,2017.
    [4] 余磊,贾科,温志文,等.计及量测数据丢失的主动配电网电流保护自适应整定方法[J].电力系统自动化,2022,46(15):145-152. YU Lei,JIA Ke,WEN Zhiwen,et al.Adaptive setting method of over current protection in active distribution network considering measurement data missing[J].Automation of Electric Power Systems,2022,46(15):145-152.
    [5] 吴行健,石晶,陈红坤,等.基于短路电流小半波特征的短路故障快速检测方法[J].电力系统保护与控制,2022,50(16):86-94. WU Xingjian,SHI Jing,CHEN Hongkun,et al.Fast short-circuit fault detection method based on a small half-wave feature[J].Power System Protection and Control,2022,50(16):86-94.
    [6] 张福良,蔡志远.鉴幅鉴相式剩余电流保护方法的研究[J].低压电器,2014(8):17-19. ZHANG Fuliang,CAI Zhiyuan.Research on amplitude and phase discrimination method of residual current protection[J].Low Voltage Apparatus,2014(8):17-19.
    [7] 武一,李奎,岳大为,等.消除剩余电流保护动作死区的理论与方法[J].电工技术学报,2008,23(6):44-49. WU Yi,LI Kui,YUE Dawei,et al.Theory and method of eliminating operating dead zone of residual current protection[J].Transactions of China Electrotechnical Society,2008,23(6):44-49.
    [8] 李奎,郝运佥,赵成晨,等.基于马尔可夫过程的漏电保护器服役状态及其可靠性分析[J].电工技术学报,2023,38(18):5061-5076. LI Kui,HAO Yunqian,ZHAO Chengchen,et al.Service states and reliability analysis of residual current device based on Markov process[J].Transactions of China Electrotechnical Society,2023,38(18):5061-5076.
    [9] 韩晓慧,杜松怀,苏娟,等.触电信号暂态特征提取及故障类型识别方法[J].电网技术,2016,40(11):3591-3596. HAN Xiaohui,DU Songhuai,SU Juan,et al.Fault transient feature extraction and fault type identification for electrical shock signals[J].Power System Technology,2016,40(11):3591-3596.
    [10] 王金丽,刘永梅,杜松怀,等.基于剩余电流固有模态能量特征的生物触电故障诊断模型[J].农业工程学报,2016,32(21):202-208.WANG Jinli,LIU Yongmei,DU Songhuai,et al.Fault diagnosis model for biological electric shock based on residual current intrinsic mode function energy features[J].Transactions of the Chinese Society of Agricultural Engineering,2016,32(21):202-208.
    [11] 赵凤展,杨仁刚.基于短时傅里叶变换的电压暂降扰动检测[J].中国电机工程学报,2007,27(10):28-34+109. ZHAO Fengzhan,YANG Rengang.Voltage sag disturbance detection based on short time Fourier transform[J].Proceedings of the CSEE,2007,27(10):28-34+109.
    [12] 邓志祥,潘建兵,黄灿英,等.基于傅里叶变换与最大关联距离相结合的配电网故障选线新方法[J].电网与清洁能源,2022,38(4):95-103. DENG Zhixiang,PAN Jianbing,HUANG Canying,et al.A novel fault line selection method of distribution network based on FFT and maximum correlation distance[J].Power System and Clean Energy,2022,38(4):95-103.
    [13] 王健,易姝慧,刘俊杰,等.基于随机森林算法和稳态波形的非介入式工业负荷辨识[J].中国电力,2022,55(2):82-89. WANG Jian,YI Shuhui,LIU Junjie,et al.Non-intrusive industrial load identification based on random forest algorithm and steady-state waveform[J].Electric Power,2022,55(2):82-89.
    [14] 岳首志,洪海生,邓祺,等.基于曲线特征聚类与信息聚合的电力负荷预测[J].长沙理工大学学报(自然科学版),2023,20(6):128-139. YUE Shouzhi,HONG Haisheng,DENG Qi,et al.Power load forecasting based on curve feature clustering and information aggregation[J].Journal of Changsha University of Science & Technology (Natural Science),2023,20(6):128-139.
    [15] JURADO F,SAENZ J R.Comparison between discrete STFT and wavelets for the analysis of power quality events[J].Electric Power Systems Research,2002,62(3):183-190.
    [16] 邰能灵,侯志俭,李涛,等.基于小波分析的电力系统短期负荷预测方法[J].中国电机工程学报,2003,23(1):45-50. TAI Nengling,HOU Zhijian,LI Tao,et al.New principle based on wavelet transform for power system short-term load forecasting[J].Proceedings of the CSEE,2003,23(1):45-50.
    [17] CHUI C K.Wavelets:a tutorial in theory and applications[M].Boston:Academic Press,1992.
    [18] 袁晓龙,梅雪,黄嘉爽,等.基于随机森林算法的特征选择及在fMRI数据中的应用[J].微电子学与计算机,2014,31(8):132-135. YUAN Xiaolong,MEI Xue,HUANG Jiashuang,et al.Feature selection based on random forest algorithm and the applications in fMRI data[J].Microelectronics & Computer,2014,31(8):132-135.
    [19] 王晓佩.基于随机森林的冷水机组典型故障诊断方法研究[D].广州:华南理工大学,2020. WANG Xiaopei.Study on the fault diagnosis method of chiller based on random forest[D].Guangzhou:South China University of Technology,2020.
    [20] 李志强,高大兵,苏盛,等.基于大数据的智能电表入侵检测方法[J].电力科学与技术学报,2016,31(1):121-126. LI Zhiqiang,GAO Dabing,SU Sheng,et al.Big data based intrusion detection method of smart meters[J].Journal of Electric Power Science and Technology,2016,31(1):121-126.
    [21] 乔黎伟,王静怡,郭炜,等.基于随机森林算法的中短期用电量预测[J].电力科学与技术学报,2020,35(2):150-156. QIAO Liwei,WANG Jingyi,GUO Wei,et al.Medium and short-term electricity demand prediction based on random forests algorithm[J].Journal of Electric Power Science and Technology,2020,35(2):150-156..
    [22] 徐明林.基于小波降噪和经验模态分解的滚动轴承故障诊断[D].哈尔滨:哈尔滨工业大学,2013. XU Minglin.Fault diagnosis of rolling element bearing based on wavelet denoising and empirical mode decomposition[D].Harbin:Harbin Institute of Technology,2013.
    [23] 李静,徐路路.基于机器学习算法的研究热点趋势预测模型对比与分析:BP神经网络、支持向量机与LSTM模型[J].现代情报,2019,39(4):23-33. LI Jing,XU Lulu.Comparison and analysis of research trend prediction models based on machine learning algorithm—BP neural network,support vector machine and LSTM model[J].Journal of Modern Information,2019,39(4):23-33.
    [24] 耿丽娟,李星毅.用于大数据分类的KNN算法研究[J].计算机应用研究,2014,31(5):1342-1344+1373. GENG Lijuan,LI Xingyi.Improvements of KNN algorithm for big data classification[J].Application Research of Computers,2014,31(5):1342-1344+1373.
    [25] 范昕炜.支持向量机算法的研究及其应用[D].杭州:浙江大学,2003. FAN Xinwei.Support vector machine and its applications[D].Hangzhou:Zhejiang University,2003.
    [26] 孔英会,景美丽.基于混淆矩阵和集成学习的分类方法研究[J].计算机工程与科学,2012,34(6):111-117. KONG Yinghui,JING Meili.Research of the classification method based on confusion matrixes and ensemble learning[J].Computer Engineering & Science,2012,34(6):111-117.
    相似文献
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

肖湘奇,肖 宇,黄 瑞,等.基于随机森林算法的低压系统漏电检测技术研究[J].电力科学与技术学报,2024,(3):38-47,115.
XIAO Xiangqi, XIAO Yu, HUANG Rui, et al. Research on leakage detection technology of low‑voltage power system based on random forest algorithm[J]. Journal of Electric Power Science and Technology,2024,(3):38-47,115.

复制
分享
文章指标
  • 点击次数:229
  • 下载次数: 308
  • HTML阅读次数: 0
  • 引用次数: 0
历史
  • 在线发布日期: 2024-07-25
文章二维码