2025年4月6日 周日
首页 > 过刊浏览>2024年第39卷第2期 >143-151. DOI:10.19781/j.issn.1673-9140.2024.02.016
PDF HTML阅读 XML下载 导出引用 引用提醒
基于多维特征与随机森林的低压用电安全隐患预警方法
CSTR:
[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，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研究，E?mail:84578610@qq.com

中图分类号:

TM501；TP183

基金项目:

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


A warning method for low‑voltage electrical safety hazard based on multi‑dimensional features and random forests
Author:
Affiliation:

(1.State Grid Hunan Electric Power Co., Ltd., Changsha 410004, China; 2. Key Laboratory of Intelligent Electrical Measurement and Application Technology in Hunan Province, 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 [18]
    • |
  • 相似文献
    • | | |
  • 文章评论
    摘要:

    故障电弧作为低压用电常见安全隐患，因存在隐蔽性和随机性，导致难以在故障前夕有效感知，现有保护方法通常于故障发生后采取措施，容易造成电气火灾发生。针对这些问题，提出基于多维特征与随机森林的低压用电安全隐患预警方法。首先，搭建真型实验平台复现多种负载故障电弧真实场景，采集实验数据进行去噪、归一化和样本化等预处理；接着分析故障前、后波形变化情况，进而实行特征有效性分析，提取多维与故障相关程度较高的特征值，提高特征普适性。然后，搭建随机森林模型并进行超参数优化，以最小化节点信息熵为目标完成模型训练，提升模型整体性能和学习效率。最后，通过实验验证表明，所提方法在多种不同负载运行工况下预测准确率可高达99.4%以上，且预测准确率高于4种主流分类预测模型。

    Abstract:

    As a common safety hazard in low-voltage electricity use, fault arcs are difficult to perceive effectively on the eve of failure due to their concealment and randomness. Existing protection methods usually take measures after the occurrence of faults, which can easily cause electrical fires. To address these issues, a warning method for low-voltage electrical safety hazard is proposed on basis of multi-dimensional features and random forests. Next, a random forest model is built and hyper-parameters are optimized, with the goal of minimizing node information entropy to complete model training, so that enhances the overall performance and learning efficiency of the model. Finally, experimental verification shows that the proposed method achieves a prediction accuracy of over 99.4% with different loads, and its prediction accuracy is higher than that of four traditional classification prediction models.

    参考文献
    [1] 高锴.电气火灾监控系统和电气火灾预防[J].建筑电气,2013,32(11): 54-56. GAO Kai. Alarm and monitoring system for electric fire protection and electric fire prevention[J]. Building Electricity,2013, 32(11): 54-56.
    [2] 刘任鹏，朱阳，何畅.考虑材料不确定性的特高压GIS瓷套管地震易损性研究[J].高压电器，2022，58(8)：91-98. LIU Renpeng，ZHU Yang，HE Chang.Study on seismic vulnerability of porcelain bushing for ultra-high-voltage gis considering material uncertainty[J].High Voltage Apparatus，2022，58(8)：91-98.
    [3] 徐云聪,张逸,林才华,等.基于电气特性—物理参数耦合的交流电弧炉模型[J].电工技术学报,2024,39(6):1643-1655. XU Yuncong,ZHANG Yi,LIN Caihua,et al.AC arc furnace model based on coupling of electrical and physical parameters[J].Transactions of China Electrotechnical Society,2024,39 (6): 1643-1655.
    [4] 刘旭晖，朱振宇，郭玥，等.一种电弧引燃电缆的电气火源模拟方法[J].电力工程技术,2022,41(2): 136-142. LIU Xuhui,ZHU Zhenyu,GUO Yue,et al.Electrical fire source simulation for igniting cable[J].Electric Power Engineering Technology,2022,41(2): 136-142.
    [5] 孙宇晗，程永锋，卢智成，等.特高压换流站高压换流变及防火墙上设备减隔震分析研究[J].高压电器，2022，58(8)：204-212. SUN Yuhan，CHENG Yongfeng，LU Zhicheng，et al.Analysis and research on vibration control and isolation of high voltage converter transformer and equipment on firewall in UHV converter station[J].High Voltage Apparatus，2022，58(8)：204-212.
    [6] BAO G H,GAO X Q,JIANG R,et,al.A novel differential high-frequency current transformer sensor for series arc fault detection[J].Sensors,2019,19(17):3649.
    [7] 郭志伟,徐子涛,刘波,等.基于最优特征量选取的开关柜故障判别方法研究[J].电测与仪表,2023,60(8):85-91. GUO Zhiwei,XU Zitao,LIU Bo,et al.Research on switchgear fault judgment method based on optimal feature quantity selection[J].Electrical Measurement & Instrumentation,2023,60(8): 85-91.
    [8] 林奕夫，叶兆平，刘冬晨，等.高压开关柜局部放电TEV信号传播衰减特性[J].电力工程技术，2023，42(5):224-231. LING Yifu,YE Zhaoping,LIU Dongchen,et al.Propagation and attenuation of TEV signals by partial discharge in high voltage switchgear[J].Electric Power Engineering Technology,2023,42(5): 224-231.
    [9] 丁锐,陈羽,孙伶雁,等.基于邻波电流差与随机性的交流串联电弧故障识别[J].电力系统保护与控制,2023,51(8):169-178. DING Rui,CHEN Yu,SUN Lingyan,et al.Series arc fault detection in low-voltage AC power lines based on absolute difference of theneighboring waveform of the current and randomness[J].Power System Protection and Control,2023,51(8):169-178.
    [10] 刁晓虹,董昊,侯磊,等.基于CEEMDAN-HT和SAE的直流故障电弧诊断方法研究[J].电网与清洁能源，2023，39(10)：1-8+18. DIAO Xiaohong，DONG Hao，HOU Lei，et al.Research on the DC fault arc detection method based on CEEMDAN-HT and SAE[J].Power System and Clean Energy，2023，39(9)：1-8+18.
    [11] 巩泉役,彭克,陈羽,等.基于电弧随机性和卷积网络的交流串联电弧故障识别方法[J].电力系统自动化,2022,46(24):162-169. GONG Quanyi,PENG Ke,CHEN Yu,et al.Identification method of AC series arc fault based on randomness of arc and convolutional network[J].Automation of Electric Power Systems,2022,46(24):162-169.
    [12] 李响，张炜祺，赵瑞锋，等.小电阻接地系统弧光接地故障建模与特征计算方法[J].供用电，2022，39（6）：27-32+39. LI Xiang，ZHANG Weiqi，ZHAO Ruifeng，et al.Modeling and characteristic calculation method of arc ground fault in low resistance grounding system[J].Distribution & Utilization，2022，39（6）：27-32+39.
    [13] 余琼芳,路文浩,杨艺.基于深度长短时记忆网络的多支路串联故障电弧检测方法[J].计算机应用,2021,41(S1):321-326. YU Qiongfang LU Wenhao,YANG Yi. Multi-branch series fault arc detection method based on deep long short-term memory network[J].Journal of Computer Applications,2021,41(S1):321-326.
    [14] 苏晶晶,许志红.基于EMD和PNN的故障电弧多变量判据诊断方法[J].电力自动化设备,2019,39(4):106-113. SU Jingjing,XU Zhihong.Diagnosis method of multi-variable criterion based on EMD and PNN for arc fault diagnosis[J].Electric Power Automation Equipment,2019,39(4):106-113.
    [15] 封钰，宋佑斌，金晟,等.基于随机森林算法和粗糙集理论的改进型深度学习短期负荷预测模型[J].发电技术，2023，44(6)：889-895. FENG Yu,SONG Youbin,JIN Sheng,et al.Improved deep learning model for forecasting short-term load based on random forest algorithm and rough set theory[J].Power Generation Technology，2023，44(6)：889-895.
    [16] 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.
    [17] 张静,陶彬彬.基于MATLAB的小波去噪的研究[J].辽宁工业大学学报(自然科学版),2022,42(3):177-182. ZHANG Jing,TAO Binbin.Research on wavelet denoising based on MATLAB[J].Journal of Liaoning University of Technology(Natural Science Edition),2022,42(3):177-182.
    [18] 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 bearings based on wavelet noise reduction and empirical modal decomposition[D].Harbin:Harbin Institute of Technology, 2013.
    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,胡军华,叶 志,等.基于多维特征与随机森林的低压用电安全隐患预警方法[J].电力科学与技术学报,2024,39(2):143-151.
XIAO Xiangqi, HU Junhua, YE Zhi, et al. A warning method for low‑voltage electrical safety hazard based on multi‑dimensional features and random forests[J]. Journal of Electric Power Science and Technology,2024,39(2):143-151.

复制
分享
文章指标
  • 点击次数:169
  • 下载次数: 677
  • HTML阅读次数: 0
  • 引用次数: 0
历史
  • 在线发布日期: 2024-05-29
文章二维码

微信公众号二维码

您是本站第 84110 访问者

通信地址：长沙市（天心区）万家丽南路960号长沙理工大学

电话/传真：0731-85258195 E-mail：dlxb04@163.com

版权所有：电力科学与技术学报 ® 2025 版权所有

京公网安备 11010802026262号