基于小波神经网络的光伏并网逆变器故障自动检测方法  

Automatic Fault Detection Method for Photovoltaic Grid Connected Inverters Based on Wavelet Neural Network

作　　者：黄永胜 HUANG Yongsheng(Wuxi Suzhou Branch,State Power Investment Group Jiangsu Electric Power Co.,Ltd.,Suzhou,Jiangsu 215000,China)

机构地区：[1]国家电投集团江苏电力有限公司无锡苏州分公司,江苏苏州215000

出　　处：《自动化应用》2024年第19期112-114,129,共4页Automation Application

摘　　要：为提高光伏并网逆变器运行质量、保障其运行的安全性,利用小波神经网络展开了光伏并网逆变器故障自动检测方法研究。首先,配置数据采集系统,采集光伏并网逆变器的数据;然后,利用所收集的运行数据进行逆变电源的故障特征提取,输出提取到的特征参数;最后,以此为基础,构建小波神经网络,设计诊断函数,根据网络的输出判断逆变器是否存在故障。结果表明,应用所提方法后,不同故障状态类型的逆变器输出电压与输出电流检测结果基本与实际值一致,具有较高的检测精度,能准确识别逆变器运行状态,可检测出具体的故障类型。In order to improve the operational quality and ensure the safety of photovoltaic grid connected inverters,a research on automatic fault detection method for photovoltaic grid connected inverters was carried out using wavelet neural networks.Firstly,configure a data acquisition system to collect data from photovoltaic grid connected inverters.Then,use the collected operational data to extract fault features of the inverter power supply and output the extracted feature parameters.Finally,based on this,a wavelet neural network is constructed,and a diagnostic function is designed to determine whether there is a fault in the inverter according to the output of the network.The results show that after applying the proposed method,the detection results of output voltage and output current of inverters with different fault state types are basically consistent with the actual values,with high detection accuracy.It can accurately identify the operating status of inverters and detect specific fault types.

关 键 词：小波神经网络 光伏 并网逆变器 故障 自动检测 

分 类 号：TM464[电气工程—电器]