一种基于ICA‑FNN的多模型高压网络保护设备异常状态风险预警方法
CSTR:
作者:
作者单位:

(1.国网北京市电力公司电力科学研究院,北京 100075;2. 国网北京市电力公司,北京 100041;3.上海泽鑫电力科技股份有限公司,上海 201206)

通讯作者:

闻 宇(1988—),女,硕士,工程师,主要从事电力系统继电保护与控制方面的研究;E?mail:edwardsy@126.com

中图分类号:

TM507

基金项目:

国网北京市电力公司电力科学研究院科技项目(26020120001M).


An ICA‑FNN‑based multi‑model early warning approach for the abnormal state risks in high‑voltage network protection devices
Author:
Affiliation:

(1.State Grid Beijing Electric Power Research Institute,Beijing 100075,China; 2.State Grid Beijing Electric Power Company,Beijing 100041,China; 3.Shanghai Zexin Electric Power Technology Co., Ltd.,Shanghai 201206,China)

  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [15]
  • |
  • 相似文献
  • |
  • 引证文献
  • | |
  • 文章评论
    摘要:

    继电保护自动设备是确保高压网络安全稳定运行的主要防线之一。但基于当前主网拓扑结构复杂、线路架构繁多、分布跨度较大的应用场景环境下,保护设备的潜在运行异常甚至故障难以完全避免;同时,保护设备种类、功能、分布的多样化也对设备的缺陷管理与检修反措提出了挑战。故亟待研究兼顾时效性与全面性的设备异常状态风险自动预警技术。为此,针对继电保护自动设备,提出一种基于数据挖掘的异常状态风险实时检测模型。其中,首先采用独立成分分析方法,生成独立分量的线性组合以面向海量异构监测数据实施降噪,能够有效提升高维数据条件下的运算效率;其次,构建深度学习前馈神经网络,使用端到端的训练方法以实现时间序列的异常检测,能够有效缓解多类别时序条件下的运算复杂度。最后,以某地区主网保护系统设备异常数据作为仿真实例,实验结果验证了所设计模型的异常检测性能,能够助推设备安全风险的自动识别和及时应对。

    Abstract:

    Protection relay system is one of the main defense lines to ensure the stable operation of high-voltage networks. However, within the scenarios with the more complex network topology, the line architecture and the distribution, it is difficult to eliminate the potential operating anomalies or even failures. Also, the diversification of the protection equipment types, functions and locations poses new challenges to the defect management and equipment maintenance. Therefore, the automatic early warning technology of equipment abnormal state risk which considers both the timeliness and comprehensiveness should be studied. To this end, a real-time detection model of abnormal state risk based on data mining is proposed in this paper. Firstly, the independent component analysis is used for mass heterogeneous monitoring data to implement noise reduction. This can effectively improve the computational efficiency under high-dimensional data conditions. Secondly, the feed-forward neural network deep learning method which deploys the end-to-end training process to achieve time series anomaly detections is utilized. This can effectively alleviate the multi-category timing conditions of computational complexity. Finally, the protection system equipment in one area is exploited as empirical study, the results verify the abnormal detection performance of the designed model, which can promote the automatic identification and timely response of the protection relay system.

    参考文献
    [1] 王文焕,郭鹏,祝洁,等.基于故障树及贝叶斯网络的继电保护系统风险评估及故障定位方法[J].电力科学与技术学报,2021,36(4):81-90. WANG Wenhuan,GUO Peng,ZHU Jie,et al.Fault positioning and risk assessment method of relay protection based on fault tree and Bayesian network[J].Journal of Electric Power Science and Technology,2021,36(4):81-90.
    [2] 杨超,伏晓燕.智能变电站继电保护设备全防误状态监测技术研究[J].电网与清洁能源,2023,39(7):73-79. YANG Chao,FU Xiaoyan.Research on the full error prevention state monitoring technology of relay protection equipment in intelligent substations[J].Power System and Clean Energy,2023,39(7):73-79.
    [3] REZAEI N,UDDIN M N.An analytical review on state-of-the-art microgrid protective relaying and coordination techniques[J].IEEE Transactions on Industry Applications,2021,57(3):2258-2273.
    [4] 郑玉平,吕鹏飞,李斌,等.新型电力系统继电保护面临的问题与解决思路[J].电力系统自动化,2023,47(22):3-15. ZHENG Yuping,Lü Pengfei,LI Bin,et al.Problems faced by relay protection in new power system and their solution ideas[J].Automation of Electric Power Systems,2023,47(22):3-15.
    [5] 马红明,李倩,陶鹏,等.基于贝叶斯与数据驱动的智能电能表状态感知技术研究[J].电测与仪表,2022,59(2):176-182+188. MA Hongming,LI Qian,TAO Peng,et al.Research on the state perception technology of smart meters based on Bayesian and data-driven[J].Electrical Measurement & Instrumentation,2022,59(2):176-182+188.
    [6] LIM S T,LIM S H.Analysis on protective coordination between over-current relays with voltage component in a power distribution system with SFCL[J].IEEE Transactions on Applied Superconductivity,2020,30(4):5601706.
    [7] 李梅,唐菊生.基于综合制动判据的变压器差动保护研究[J].电力科学与技术学报,2020,35(2):135-141. LI Mei,TANG Jusheng.Transformer differential protection method based on the comprehensive braking criterion[J].Journal of Electric Power Science and Technology,2020,35(2):135-141.
    [8] 谢庆,张煊宇,王春鑫,等.新一代人工智能技术在输变电设备状态评估中的应用现状及展望[J].高压电器,2022,58(11):1-16. XIE Qing,ZHANG Xuanyu,WANG Chunxin,et al.Application status and prospect of the new generation artificial intelligence technology in the state evaluation of power transmission and transformation equipment[J].High Voltage Apparatus,2022,58(11):1-16.
    [9] VLAHINI? S,FRANKOVI? D,JURI?A B,et al.Back up protection scheme for high impedance faults detection in transmission systems based on synchrophasor measurements[J].IEEE Transactions on Smart Grid,2021,12(2):1736-1746.
    [10] 闫晨光,张芃,徐雅,等.换流变压器有载分接开关级间短路故障差动保护动作特性[J].电工技术学报,2023,38(21):5878-5888+5912. YAN Chenguang,ZHANG Peng,XU Ya,et al.Differential protection performance for converter transformer intertap short-circuit faults in on-load tap changers[J].Transactions of China Electrotechnical Society,2023,38(21):5878-5888+5912.
    [11] 栾洪洲,殷伟,周飞,等.直流控保设备互感器数据异常快速识别策略[J].电网技术,2019,43(8):2853-2859. LUAN Hongzhou,YIN Wei,ZHOU Fei,et al.A fast recognition strategy for abnormal transformer data in DC protection and control device[J].Power System Technology,2019,43(8):2853-2859.
    [12] 安海清,李振动,金海望,等.张北柔直电网直流分压器二次电压测量异常引起误闭锁机理分析及改进措施[J].电力自动化设备,2021,41(8):156-160+168. AN Haiqing,LI Zhendong,JIN Haiwang,et al.Mechanism analysis and improvement measures of error block caused by abnormal secondary voltage measurement of DC voltage divider in Zhangbei flexible DC grid[J].Electric Power Automation Equipment,2021,41(8):156-160+168.
    [13] 韩平平,陈思远,张楠,等.考虑分布式光伏的低压台区线损异常辨识方法[J].电力系统保护与控制,2023,51(8):140-148. HAN Pingping,CHEN Siyuan,ZHANG Nan,et al.Line loss anomaly identification method for low-voltage station area considering distributed PV[J].Power System Protection and Control,2023,51(8):140-148.
    [14] 贾梦瑶,王玉玮,宋明浩.基于时间生成对抗网络的风电随机场景预测[J].智慧电力,2023,51(8):59-66. JIA Mengyao,WANG Yuwei,SONG Minghao.Stochastic scenario prediction of wind power based on time generative adversarial networks[J].Smart Power,2023,51(8):59-66.
    [15] FAWCETT T.An introduction to ROC analysis[J].Pattern Recognition Letters,2006,27(8):861-874.
    相似文献
    引证文献
引用本文

闻 宇,陈艳霞,李 菁,等.一种基于ICA‑FNN的多模型高压网络保护设备异常状态风险预警方法[J].电力科学与技术学报,2024,39(4):78-83,101.
WEN Yu, CHEN Yanxia, LI Jing, et al. An ICA‑FNN‑based multi‑model early warning approach for the abnormal state risks in high‑voltage network protection devices[J]. Journal of Electric Power Science and Technology,2024,39(4):78-83,101.

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 在线发布日期: 2024-09-10
文章二维码