中国电力 ›› 2025, Vol. 58 ›› Issue (11): 186-192, 204.DOI: 10.11930/j.issn.1004-9649.202412036

• 新型电网 • 上一篇    下一篇

数据驱动的柔性直流继电保护自适应测试方法

刘丽萍1(), 刘德坤1(), 邓搏1(), 范登博2, 辛光明3(), 张新远1, 李博通1(), 任翔3(), 吝梦媛1   

  1. 1. 天津大学 电气自动化与信息工程学院,天津 300072
    2. 国网冀北电力有限公司,北京 100052
    3. 国网冀北电力有限公司电力科学研究院,北京 100045
  • 收稿日期:2024-12-09 修回日期:2025-09-03 发布日期:2025-12-01 出版日期:2025-11-28
  • 作者简介:
    刘丽萍(1979),女,教授,从事网络控制研究,E-mail:lipingliu@tju.edu.cn
    刘德坤(2002),男,博士研究生,从事电力系统故障分析研究,E-mail:liu_dk_02@tju.edu.cn
    李博通(1981),通信作者,男,教授,博士生导师,从事电力系统故障分析与继电保护等研究,E-mail:libotong@tju.edu.cn
  • 基金资助:
    国家电网有限公司科技项目(5100-202314007A-1-1-ZN)。

A Data-driven Adaptive Testing Method for Flexible DC Relay Protection

LIU Liping1(), LIU Dekun1(), DENG Bo1(), FAN Dengbo2, XIN Guangming3(), ZHANG Xinyuan1, LI Botong1(), REN Xiang3(), LIN Mengyuan1   

  1. 1. School of Electrical Automation and Information Engineering, Tianjin University, Tianjin 300072, China
    2. State Grid Jibei Electric Power Co., Ltd., Beijing 100052, China
    3. State Grid Jibei Electric Power Co., Ltd. Electric Power Science Research Institute, Beijing 100045, China
  • Received:2024-12-09 Revised:2025-09-03 Online:2025-12-01 Published:2025-11-28
  • Supported by:
    This work is supported by Science and Technology Project of SGCC (No.5100-202314007A-1-1-ZN).

摘要:

柔性直流输电系统复杂的运行环境对继电保护性能测试提出了更高要求。为提高测试效率,提出数据驱动的柔性直流继电保护自适应测试方法,挖掘保护评价关键测试场景进行测试。采用均值漂移法对测试历史数据进行聚类分析,基于典型场景利用神经网络建立测试预测模型。通过仿真算例验证了所提方法的有效性,与此同时,仿真结果表明,所提方法有利于提升测试效率及准确性,有效降低了测试时间和资源成本。

关键词: 柔性直流输电系统, 继电保护测试, 聚类分析

Abstract:

The flexible direct current transmission system's complex operation environment has put forward higher requirements for relay protection performance testing. In order to improve the testing efficiency, data-driven self-adaptive testing method for flexible direct current relay protection is proposed. The key testing scenarios for protection evaluation are tested by mining. The mean drift method is used to the historical testing data, and a testing prediction model based on typical scenarios and neural networks is established. The effectiveness of the proposed method is verified by simulation examples. At the same, the simulation results show that the proposed method is conducive to improving the efficiency and accuracy of testing, and effectively reducing the time and resource cost of testing.

Key words: flexible DC transmission system, relay protection testing, mean drift clustering


AI


AI小编
您好!我是《中国电力》AI小编,有什么可以帮您的吗?