电能计量装置异常状态监测方法研究
Research on Abnormal State Monitoring Method of Electric Energy Metering Device
刘卫新 1胡春华2
作者信息
- 1. 国网新疆电力有限公司电力科学研究院,新疆 乌鲁木齐 830000
- 2. 烟台东方威思顿电气有限公司,山东 烟台 264000
- 折叠
摘要
电能计量装置计量过程中,受功率谱谐波震颤强度影响,其状态指标数据呈现高度混沌状态,导致监测性能较差.为此,提出基于改进聚类分析的电能计量装置异常状态监测方法.通过构建电能计量装置状态评估体系,选取具有评估价值的技术指标及其对应的参数指标,并将相关指标参数视为待分类对象,以获取电能计量装置运行状态的混沌样本数据.利用蚁群算法优化K-Means聚类方法的聚类指标数据,实现电能计量装置状态监测.试验结果表明:该方法应用后的电能计量装置异常状态检出率较高,并且预测值与实际值的拟合率、准确率均较高.该方法监测性能较好.
Abstract
During the metering process of electric energy metering device,affected by the power spectrum harmonic tremor strength,its state index data presents a highly chaotic state,resulting in poor monitoring performance.For this reason,the abnormal state monitoring method of electric energy metering device based on improved cluster analysis is proposed.By constructing the state assessment system of electric energy metering device,selecting the technical indicators with assessment value and their corresponding parameter indicators,and considering the relevant indicators parameter as objects to be categorized,the chaotic sample data of the operating state of electric energy metering device are obtained.Ant colony algorithm is used to optimize the clustering index data of K-Means clustering method to realize the state monitoring of electric energy metering device.The test results show that the detection rate of abnormal state of electric energy metering device after the application of this method is high,the fitting rate and accuracy of the predicted value and the actual value are high.The method has good monitoring performance.
关键词
电能计量装置/谐波震颤强度/互感器/功率谱/状态监测/多变量相空间重构/特征向量/K-Means聚类Key words
Electric energy metering device/Harmonic tremor intensity/Transformer/Power spectrum/State monitoring/Multivariate phase space reconstruction/Eigenvectors/K-Means clustering引用本文复制引用
出版年
2024
NETL
NSTL
万方数据