一种考虑气象因素的配电网设备故障关联挖掘模型  

A Model for Mining Association of Equipment Faults in Distribution Network Considering Meteorological Factors

作　　者：李丰君 王子欣 孙芊 彭磊 苗世洪 LI Fengjun;WANG Zixin;SUN Qian;PENG Lei;MIAO Shihong(Electric Power Research Institute of State Grid Henan Electric Power Company,Zhengzhou 450000,Henan Province,China;State Key Laboratory of Advanced Electromagnetic Engineering and Technology(Huazhong University of Science and Technology),Wuhan 430074,Hubei Province,China;Hubei Electric Power Security and High Efficiency Key Laboratory(Huazhong University of Science and Technology),Wuhan 430074,Hubei Province,China;State Grid Henan Electric Power Company,Zhengzhou 450000,Henan Province,China)

机构地区：[1]国网河南省电力公司电力科学研究院,河南省郑州市450000 [2]电气与电子工程学院强电磁工程与新技术国家重点实验室(华中科技大学),湖北省武汉市430074 [3]电力安全与高效湖北省重点实验室(华中科技大学),湖北省武汉市430074 [4]国网河南省电力公司,河南省郑州市450000

出　　处：《现代电力》2023年第4期605-613,共9页Modern Electric Power

基　　金：国网河南省电力公司科技项目(SGHADK00PJJS2100232)。

摘　　要：电网结构日益复杂,故障监测与防范的成本随之增大,而强对流天气的频繁出现使得设备故障与外界条件关联更加紧密,因此挖掘故障设备与故障因素间的关联关系,并对具有较高关联度的设备进行重点监测与防范,对电力系统的安全稳定运行具有重要意义。基于模糊频繁项挖掘算法,提出了1种考虑气象因素的配电网设备故障关联挖掘模型。该模型首先从多元信息库中提取故障特征数据,采用Relief-F算法排除相关程度较小的冗余特征,通过数据预处理与数据整合,构建包含气象因素的故障关联特征库。其次,以故障关联特征库为基础,引入模糊集理论,提出基于模糊频繁项集挖掘算法的故障因素与故障设备关联模型构建方法。最后,基于故障关联模型进行了算例分析,结果验证了所提方法的正确与有效性。The structure of the power grid is becoming more and more complex,and the cost of fault monitoring and prevention will increase.The frequent occurrence of strong convective weather makes equipment failures more closely related to external conditions.Therefore,it is of great significance for the safe and stable operation of the power system to excavate the correlation between the fault equipment and the fault factors,and to focus on the monitoring and prevention of the equipment with high correlation degree.Based on the fuzzy frequent item mining algorithm,a distribution network equipment fault association mining model that considers meteorological factors was proposed.The model first extracts fault characteristic data from a multivariate information database,uses the Relief-F algorithm to eliminate redundant features that are less relevant,and builds a fault associated characteristic database containing meteorological factors through data preprocessing and data integration.Secondly,based on the fault correlation feature database,the fuzzy set theory was introduced,and the method of fault factor and fault equipment association model construction was proposed based on the fuzzy frequent item set mining algorithm.Finally,an example was analyzed based on the fault correlation model,and the results verify the correctness and effectiveness of the proposed method.

关 键 词：关联规则 气象因素 模糊频繁项挖掘 配电网 Relief-F算法 

分 类 号：TM73[电气工程—电力系统及自动化]