摘要
为提高电流互感器状态评估的准确性,提出了基于贝叶斯网络的电流互感器的状态评估方法,通过分析大量电流互感器台账及缺陷分析,得到影响因素和故障损坏特征的关联关系,建立基于贝叶斯网络的电流互感器故障概率预测模型,结合实际运行数据对模型进行验证。采用k均值聚类法对电流互感器故障预测概率值进行综合聚类分析,得到13812台电流互感器的故障概率区间,并提出了运维建议。
In order to improve the accuracy of the state evaluation of current transformers,a state evaluation method of current transformers based on Bayesian network is proposed,and the correlation between influencing factors and fault damage characteristics is obtained by analyzing a large number of current transformer ledgers and defect analysis,and a probability prediction model of current transformer based on Bayesian network is established,and the model is verified by combining actual operation data.The k-means clustering method is used to comprehensively analyze the probability value of the current transformer fault prediction,and the fault probability interval of 13812 current transformers is obtained,and the operation and maintenance suggestions are proposed.
作者
陈云浩
彭兆裕
杨凯越
罗六洋
史玉清
李昭
王浩州
Chen Yunhao;Peng Zhaoyu;Yang Kaiyue;Luo Liuyang;Shi Yuqing;Li Zhao;Wang Haozhou(Pu'er Power Supply Bureau of Yunnan Power Grid Co.,Ltd.,Pu'er 665000,China;Chuxiong Power Supply Bureau of Yunnan Power Grid Co.,Ltd.,Chuxiong 675000,China;Yuxi Power Supply Bureau of Yunnan Power Grid Liability Co.,Ltd.,Yuxi 653100,China;Kunming Power Supply Bureau of Yunnan Power Grid Liability Co.,Ltd.,Kunming 650217,China;Electric Power Research Institute of Yunnan Power Grid Co.,Ltd.,Kunming 650217,China)
出处
《云南电力技术》
2022年第2期74-78,83,共6页
Yunnan Electric Power
关键词
电流互感器
贝叶斯网络
状态评估
聚类分析
故障预测
current transformers
Bayesian networks
state evaluation
clustering analysis
fault prediction
