中国电力 ›› 2023, Vol. 56 ›› Issue (11): 121-127.DOI: 10.11930/j.issn.1004-9649.202306047

• 新型电力系统低碳规划与运行 • 上一篇    下一篇

基于数字孪生的在运安控系统故障诊断方法

韩伟1(), 段文岩1, 杜兴伟2, 姚峰2, 马伟东1, 刘磊1   

  1. 1. 国网河南省电力公司电力科学研究院,河南 郑州 450052
    2. 国网河南省电力公司电力调度控制中心,河南 郑州 450018
  • 收稿日期:2023-06-14 出版日期:2023-11-28 发布日期:2023-11-28
  • 作者简介:韩伟(1975—),男,高级工程师(教授级),从事电力系统继电保护与控制技术研究,E-mail: hanwei1975103@163.com
  • 基金资助:
    国家电网有限公司科技项目(5100-202240012A-1-1-ZN)。

Fault Diagnosis Method for Operational Security Control System Based on Digital Twins

Wei HAN1(), Wenyan DUAN1, Xingwei DU2, Feng YAO2, Weidong MA1, Lei LIU1   

  1. 1. Electric Power Research Institute of State Grid Henan Electric Power Company, Zhengzhou 450052, China
    2. Electric Power Dispatching Control Center of State Grid Henan Electric Power Company, Zhengzhou 450018, China
  • Received:2023-06-14 Online:2023-11-28 Published:2023-11-28
  • Supported by:
    This work is supported by Science and Technology Project of SGCC (No.5100-202240012A-1-1-ZN).

摘要:

数字孪生技术旨在打破虚实界墙,通过虚-实信息链接实现物理实体与虚拟空间的有机融合,模拟出物理实体的实时状态。安全稳定控制系统(简称安控系统)作为保证电网安全稳定运行的第二道防线,一旦发生故障将会给电网的运行造成严重危害。为此,提出一种基于数字孪生的在运安控系统故障诊断方法。首先,通过分析安控系统的一般运行策略和可能存在的故障环节,提出安控系统的数字孪生体系;其次,建立基于海洋捕食者算法优化支持向量机的安控系统故障诊断模型;最后,利用安控系统的运行数据构建样本数据集,验证了所提方法的有效性和正确性。

关键词: 安控系统, 数字孪生, 故障诊断, 支持向量机, 海洋捕食者算法

Abstract:

The digital twin technology aims to break through the boundary between virtual and real, achieve organic integration of physical entities and virtual space through virtual real information links, and simulate the real-time state of physical entities. The security and stability control system (security control system) is the second line of defense to ensure the safe and stable operation of the power grid. If it refuses to act or malfunction due to a fault, it will cause serious harm to the operation of the power grid. Therefore, this paper proposes a fault diagnosis method for operational security control system based on digital twins. By analyzing the general operation strategies and possible failure links of the security control system, the digital twin system of the security control system is proposed. And a fault diagnosis model for security control system based on MPA-SVM is established. Finally, the validity and correctness of the proposed method is verified by using the operational data of the security control system to construct the sample datasets.

Key words: security control system, digital twin, fault diagnosis, support vector machine, marine predator algorithm