半月刊

ISSN 1000-1026

CN 32-1180/TP

+高级检索 English
基于改进关联规则的直流换流站典型运维事件集诊断方法
作者:
作者单位:

1.昆明理工大学电力工程学院,云南省昆明市 650500;2.中国南方电网有限责任公司超高压输电公司昆明局,云南省昆明市 650000;3.昆明理工大学信息工程与自动化学院,云南省昆明市 650500

摘要:

随着中国特高压交直流电网的大规模运行,直流换流站一、二次设备复杂程度不断增高,使得直流系统发生状态转换或故障时,换流站顺序事件记录(SER)系统短时间产生大量SER事件,SER事件集中的特征事件丢失难以被运维人员及时察觉。针对此问题,文中提出了一种基于改进关联规则的直流换流站典型运维事件集诊断方法。首先,分析了换流站原始SER特征类型并筛选SER事件的主要特征类型,实现数据降维与换流站SER事件模型构建;然后,通过改进关联规则算法挖掘换流站相似故障与状态转换的SER强关联事件组与SER关联事件;最后,基于数据挖掘结果诊断SER事件集中是否存在特征事件缺失的情况。结合昆柳龙直流工程工程换流站试运行数据进行算例分析,结果表明所提方法可以从海量异构、多态SER事件集中挖掘关联规则,为辅助运维人员诊断换流站状态转换与故障发生下SER事件集的缺失情况提供参考。

关键词:

基金项目:

国家自然科学基金资助项目(51907084);中国南方电网有限责任公司科技项目(CGYKJXM20180212);云南省应用基础研究计划资助项目(202101AT070080)。

通信作者:

作者简介:


Diagnosis Method for Typical Operation and Maintenance Event Set of DC Converter Station Based on Improved Association Rule
Author:
Affiliation:

1.Faculty of Electric Power Engineering, Kunming University of Science and Technology, Kunming 650500, China;2.Kunming Bureau of EHV Power Transmission Company, China Southern Power Grid Co., Ltd., Kunming 650000, China;3.Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, China

Abstract:

With the large-scale operation of China's ultra high voltage AC/DC power grids, the complexity of primary and secondary equipment of DC converter station is increasing, so that in case of state transition or failure of DC system, the converter station sequential events recording (SER) system generates a large number of SER events in a short time, and the loss of characteristic events in the SER event set is difficult to be detected by the operation and maintenance personnel in time. To solve this problem, a typical operation and maintenance event set diagnosis method of DC converter station based on improved association rules is proposed in this paper. Firstly, the original SER characteristic types of converter station are analyzed and the main characteristic types of SER events are selected to realize data dimensionality reduction and the construction of SER event model of converter station. Then, the SER strong correlation event groups and SER correlation events of similar faults and state transitions in converter stations are mined by the improved association rule algorithm.Finally, based on the data mining results, whether thereare missing characteristic events in SER event set is diagnosed. Combined with the trial operation data of converter station of Kunliulong DC Project, the results show that the proposed method can mine association rules from a large number of heterogeneous and polymorphic SER events, and provide a reference for assisting operation and maintenance personnel to diagnose the loss of SER event set under the state transition and fault of converter station.

Keywords:

Foundation:
This work is supported by National Natural Science Foundation of China (No. 51907084), China Southern Power Grid Co., Ltd. (No. CGYKJXM20180212), and Applied Basic Research Foundation of Yunnan Province of China (No. 202101AT070080).
引用本文
[1]刘可真,林铮,骆钊,等.基于改进关联规则的直流换流站典型运维事件集诊断方法[J/OL].电力系统自动化,http://doi. org/10.7500/AEPS20210506006.
LIU Kezhen, LIN Zheng, LUO Zhao, et al. Diagnosis Method for Typical Operation and Maintenance Event Set of DC Converter Station Based on Improved Association Rule[J/OL]. Automation of Electric Power Systems, http://doi. org/10.7500/AEPS20210506006.
复制
分享
历史
  • 收稿日期:2021-05-06
  • 最后修改日期:2021-09-15
  • 录用日期:2021-08-14
  • 在线发布日期: 2021-09-22
  • 出版日期:
相关附件