过渡电阻对微电网故障识别的影响研究  

Research on influence of transition resistance on microgrid fault detection

作　　者：周艳芳 王颖 黄涛 毛威军 胡哲晟 ZHOU Yanfang;WANG Ying;HUANG Tao;MAO Weijun;HU Zhesheng(College of Mechanical and Electrical Engineering,China Jiliang University,Hangzhou 310018,China;Economic and Technical Research Institute of State Grid Zhejiang Electric Power Co.,Ltd.,Hangzhou 310000,China)

机构地区：[1]中国计量大学机电工程学院,浙江杭州310018 [2]国网浙江省电力有限公司经济技术研究院,浙江杭州310000

出　　处：《现代电子技术》2022年第17期157-162,共6页Modern Electronics Technique

基　　金：浙江省基础公益研究计划项目(LGG20E070003);国网浙江省电力公司科技项目(SGZJJY00PSJS1900085)。

摘　　要：由于微电网的故障特性区别于传统的配网,传统的保护无法适用于微电网。为检验不同过渡电阻阻值对微电网故障识别准确率的影响,构建以小波变换、BP神经网络和RBF神经网络为基础的故障检测模型。在该模型中,对原始故障信号进行小波分解与重构,提取能量值作为故障数据库,采用BP神经网络和RBF神经网络进行故障检测并进行比较。利用PSCAD搭建仿真模型,采集样本数据通过小波变换进行预处理,将处理后的数据输入到BP神经网络和RBF神经网络中进行训练,利用训练好的模型进行故障检测。结果表明,不同的过渡电阻阻值对微电网故障判断准确率影响不一,在某些过渡电阻值下能呈现较高准确率,采用优化后的RBF神经网络使系统故障识别准确率大幅提高。Because the fault characteristics of microgrid are different from the traditional distribution network,the traditional protection is far away from being appropriate for the microgrid.With the development of intelligent detection methods,a fault detection model based on wavelet transform,BP(back propagation)neural network and RBF(radial basis function)neural network is built to test the influence of different transition resistance values on the fault identification accuracy of microgrid.In this model,the wavelet decomposition and reconstruction are conducted for original fault signals,energy values are extracted as the fault database,and BP neural network and RBF neural network are used for fault detection and comparison.PSCAD(power system computer-aided design)is used to build a simulation model,and sample data are preprocessed by wavelet transform.The processed data are input into BP neural network and RBF neural network for training,and the trained model is used for fault detection.The results show that the different transition resistance values have different effects on the fault identification accuracy of the microgrid,and the higher accuracy can be presented at some transition resistance values.The optimized RBF neural network can greatly improve the fault identification accuracy of the system.

关 键 词：微电网故障 过渡电阻 小波变换 BP神经网络 RBF神经网络 故障检测 PSCAD 小波分解 

分 类 号：TN711-34[电子电信—电路与系统] TM615[电气工程—电力系统及自动化]