摘要
长期带电运行的金属氧化物避雷器仅靠定期维修或在线监测方法无法识别其潜伏性缺陷,因此,文章结合避雷器的典型运行参量,提出了一种多源异构数据融合的设备运行状态评价方法。从避雷器的带电检测信息、在线监测信息、现场运检信息、投运前信息中挑选特征参量,组成缺陷特征量数据库;利用半梯形模型对定量参量进行归一化处理,利用自然语言处理技术对定性参量进行归一化处理,并提出基于随机森林优化的数据融合方法;利用一变电站的所有避雷器数据进行分析。算例显示本模型的评价准确率为93.12%,且与决策树模型与支持向量机模型相比,有更优的泛化能力。
Metal oxide arrester with electric charge runs for a long time,and the latent defects cannot be identified by regular maintenance or online monitoring method.Therefore,this paper proposes a multi-source heterogeneous data fusion method to assess the operating condition of the arrester with the typical operating parameters.Firstly,the characteristic parameters from the lightning detection,online monitoring,on-site inspection,and pre-operation information of arresters are selected and formed a defect feature quantity database.Then,the semi-trapezoidal model is adopted to normalize the quantitative parameters,and the natural language processing technology is introduced to normalize the qualitative parameters.Meanwhile,a data fusion method based on random forest optimization is proposed in this paper.Finally,all of the arrester data for a substation are adopted for analysis.The example shows that the assessment accuracy of the proposed model is 93.12%,and it has better generalization ability than the decision tree model and the support vector machine model.
作者
王燕
蒋逸雯
李黎
魏东亮
薛峰
谢建容
Wang Yan;Jiang Yiwen;Li Li;Wei Dongliang;Xue Feng;Xie Jianrong(School of Electrical and Electronic Engineering,Huazhong University of Science&Technology,Wuhan 430074,China;Dongguan Power Supply Bureau,Guangdong Power Grid Co.,Ltd.,Dongguan 523008,Guangdong,China)
出处
《电测与仪表》
北大核心
2020年第19期132-139,共8页
Electrical Measurement & Instrumentation
基金
广东省电力公司重大科技项目(GDKJXM20162460)。
关键词
避雷器
状态评价
数据挖掘
随机森林
自然语言处理
arrester
condition assessment
data mining
random forest
natural language processing
