基于CNN-GRU的光伏阵列故障诊断方法

卢万杰; 马磐

doi:10.13296/j.1001-1609.hva.2026.05.021

您当前的位置：

首页 >

文章列表页 >

基于CNN-GRU的光伏阵列故障诊断方法

研究与分析 | 更新时间：2026-05-13

- 基于CNN-GRU的光伏阵列故障诊断方法
- Fault Diagnosis Method of Photovoltaic Array Based on CNN-GRU
- 高压电器 2026年62卷第5期页码：180-185
- 作者机构：
  
  辽宁工程技术大学，辽宁葫芦岛 125105
- 作者简介：
  
  卢万杰（1979—），女，博士，副教授，研究方向为人工智能控制、设备故障诊断（通信作者）（E-mail：luwanjie0912@126.com）。
  马磐（1999—），男，硕士研究生，研究方向为电力系统故障诊断（E-mail：1326309303@qq.com）。
- 基金信息：
  
  国家自然科学基金项目;National Natural Science Foundation of China(51974151);辽宁省高等学校基本科研项目;Basic Research Projects of Higher Education Institutions in Liaoning Province(LJ242410147033)
- DOI：10.13296/j.1001-1609.hva.2026.05.021
  中图分类号：
- 收稿：2025-10-05，
  
  修回：2025-12-20，
  
  纸质出版：2026-05-16
- 稿件说明：
移动端阅览
卢万杰, 马磐. 基于CNN-GRU的光伏阵列故障诊断方法[J]. 高压电器, 2026,62(5):180-185.

LU Wanjie, MA Pan. Fault Diagnosis Method of Photovoltaic Array Based on CNN-GRU[J]. High Voltage Apparatus, 2026, 62(5): 180-185.
卢万杰, 马磐. 基于CNN-GRU的光伏阵列故障诊断方法[J]. 高压电器, 2026,62(5):180-185. DOI： 10.13296/j.1001-1609.hva.2026.05.021.

LU Wanjie, MA Pan. Fault Diagnosis Method of Photovoltaic Array Based on CNN-GRU[J]. High Voltage Apparatus, 2026, 62(5): 180-185. DOI： 10.13296/j.1001-1609.hva.2026.05.021.

摘要

针对光伏阵列故障诊断识别率较低的问题，文中提出一种基于卷积神经网络（convolutional neural network）与门控循环单元（gate recurrent unit）相结合的光伏阵列故障诊断方法。首先利用MATLAB/Simulink软件搭建光伏阵列的仿真模型，分别模拟出短路、开路、老化、遮阴4种典型故障，并记录其特征参数的数据；接着将构建好的特征集划分成训练集与测试集输入至CNN-GRU识别模型中进行故障类型的诊断。并分别与CNN、PNN、GRU等识别模型进行对比。通过仿真实验可知，文中提出的诊断模型可以更加准确且快速的完成诊断，诊断率高达99.5%，具有较好的故障识别能力。

Abstract

As for the problem of low fault diagnosis recognition rate of photovoltaic system

in this paper a fault diagnosis method for photovoltaic system based on the combination of convolutional neural network and gate recurrent unit is proposed. First

MATLAB/Simulink software is used to set up the simulation model of photovoltaic system

such four typical faults as short circuit

open circuit

aging and shading are simulated respectively

and the data of its characteristic parameters is recorded. Then

the constructed feature set is classified into the training set and testing set and input into the CNN-GRU recognition model for fault type diagnosis. Comparison with such recognition models as CNN

PNN and GRU is made. It is known through simulation experiments that the diagnostic model proposed in the paper can complete the diagnosis more accurately and quickly

with a diagnosis rate up to 99.5% and also good fault recognition ability.

关键词

Keywords

references

武迪,许春雨,宋建成,等.基于 β 参数的混合控制策略光伏系统MPPT算法研究[J ] .可再生能源,2018,36( 1):8-14.

WU Di,XU Chunyu,SONG Jiancheng,et al.Maximum power point tracking algorithm of photovoltaic system based on β -parameter mixed control strategy[J ] . Renewable Energy Resources,2018,36 (1):8-14.

王跃,白建波,李建.光伏发电系统精细化逐时建模方法与应用案例分析[J].太阳能,2021(5):59-66.

WANG Yue,BAI Jianbo,LI Jian.Refined hourly modeling method of pv power generation system and analysis of application cases[J]. Solar Energy,2021(5):59-66.

何知衡,杨雯,刘加平.低纬度海岛太阳能建筑逆向热工设计方法[J].西安工程大学学报,2024,38(5):70-76.

HE Zhiheng,YA NG Wen,LIU Jiaping.Reverse thermal design method for solar buildings on low-latitude islands[J]. Journal of Xi'an Polytechnic University,2024,38(5):70-76.

董辉,楚帅,葛维春,等.“源—储—荷”多运行域协调控制提升清洁能源消纳能力策略[J].电测与仪表,2024,61(5):119-125.

DONG Hui,CHU Shuai,GE Weichun,et al.Strategy of‘sourcestorage-load'multi-operating domain coordinated controlenhancing clean energy consumption capacity[J]. Electrical Measurement& Instrumentation,2024,61(5):119-125.

蔡阳,黄若楠,何建炜,等.机械辅助式太阳能光催化复合通风室内污染净化分析[J].西安工程大学学报,2025,39(1):72-80.

CAI Yang,HUANG Ruonan,HE Jianwei,et al.Purification analysis of indoor air pollutants by mechanical ventilation-assisted solar photocatalytic natural ventilation[J]. Journal of Xi'an Polytechnic University,2025,39(1):72-80.

刘雅慧,闫伟超,崔鑫,等.太阳能光伏蒸发冷却通风空腔的实验研究[J].西安工程大学学报,2024,38(5):28-35.

LIU Yahui,YAN Weichao,CUI Xin,et al.Experimental study of solar photovoltaic evaporative cooling ventilated cavity[J]. Journal of Xi'an Polytechnic University,2024,38(5):28-35.

周晓华,冯雨辰,胡旭初,等.基于秃鹰搜索算法优化SVM的变压器故障诊断[J].南方电网技术,2023,17(6):99-106.

ZHOU Xiaohua,FENG Yuchen,HU Xuchu,et al. ransformer fault diagnosis based on SVM optimized by bald eagle search algorithm[J]. Southern Power System Technology,2023,17(6):99-106.

刘智宇,郝冬,张妍懿,等.基于GA-ELM算法的燃料电池性能预测模型[J].电池,2023,53(3):243-247.

LIU Zhiyu,HAO Dong,ZHANG Yanyi,et al. Fuel cell performance prediction model based on GA-ELM algorithm[J]. Battery Bimonthly,2023,53(3):243-247.

白雲杰,贾希胜,梁庆海,等.基于PCA-EDT-CNN的柴油发动机故障诊断方法[J].机械强度,2022,44(6):1271-1278.

BAI Yunjie,JIA Xisheng,LIANG Qinghai,et al.Fault diagnosis method of diesel engine based onPCA-EDT-CNN[J]. Journal of Mechanical Strength,2022,44(6):1271-1278.

石怀涛,李宁宁,赵金宝,等.基于压缩采集特征提取与CNN-SVM的滚动轴承的故障诊断[J].沈阳建筑大学学报(自然科学版),2022,38(6):1129-1137.

SHI Huaitao,LI Ningning,ZHAO Jinbao,et al.Rolling bearing fault diagnosis method based on the compressed sampling feature extraction andCNN - SVM[J]. Journal of Shenyang Jianzhu University(Natural Science),2022,38(6):1129-1137.

王燕,梁琦.快速3D-CNN结合深度可分离卷积对高光谱图像分类[J].计算机科学与探索,2022,16(12):2860-2869.

WANG Yan,LIANG Qi.Fast 3D - CNN combined with depth separable convolution for hyperspectral image classification[J]. Journal of Frontiers of Computer Science & Technology,2022,16 (12):2860-2869.

徐少平,林珍玉,陈孝国,等.采用多通道浅层CNN构建的多降噪器最优组合模型[J].自动化学报,2022,48(11):2797-2811.

XU Shaoping,LIN Zhenyu,CHEN Xiaoguo,et al.Optimal combination of image denoisers using multi - channel shallow convolutional neural network[J]. Acta Automatica Sinica,2022,48 (11):2797-2811.

田斌,葛友铖,梁冰,等.基于CNN-LSTM混合模型的工频磁扰动信号预测[J].自动化与仪表,2021,36(11):11-14.

TIAN Bin,GE Youcheng,LIANG Bing,et al.Power frequency magnetic disturbance signal prediction based onCNN - LSTM hybrid model[J]. Automation & Instrumentation,2021,36(11):11-14.

曾亮,狄飞超,兰欣,等.基于CEEMD-CNN-BiGRU-RF模型的短期风电功率预测[J].可再生能源,2022,40(2):190-195.

ZENG Liang,DI Feichao,LAN Xin,et al.Short-term wind power prediction based on CEEMD - CNN - BiGRU - RF model[J]. Renewable Energy Resources,2022,40(2):190-195.

王琦,邓林峰,赵荣珍.基于改进一维卷积神经网络的滚动轴承故障识别[J].振动与冲击,2022,41(3):216-223.

WANG Qi,DENG Linfeng,ZHAO Rongzhen.Fault recognition of rolling bearing based on improved 1D convolutional neural network[J]. Journal of Vibration and Shock,2022,41(3):216-223.

黄悦华,张子豪,陈庆,等.基于多头注意力机制的CNN-BiLSTM高海拔多因素输电线路可听噪声预测[J].高压电器, 2024,60(12):160-169.

HUANG Yuehua,ZHANG Zihao,CHEN Qing,et al.Prediction of audible noise of CNN - BiLSTM high altitude multifactor transmission lines based on multi head attention mechanism[J]. High voltage Apparatus,2024,60(12):160-169.

张天骐,邹涵,杨宗方,等.基于CNN-LSTM的MIMO-OFDM信号盲调制识别算法[J].信号处理,2024,40(4):747-756.

ZHANG Tianqi, ZOU Han, YANG Zongfang, et al.Blind modulation recognition algorithm forMIMO-OFDMsignal based on CNN-LSTM[J]. Journal of Signal Processing,2024,40(4):747-756.

吴家葆,曾国辉,张振华,等.基于K-means分层聚类的TCN-GRU和LSTM动态组合光伏短期功率预测[J].可再生能源, 2023,41(8):1015-1022.

WU Jiabao,ZENG Guohui,ZHANG Zhenhua,et al.Dynamic combination of TCN-GRU and LSTM photovoltaic short-term power prediction based on K-means hierarchical clustering[J]. Renewable Energy Resources,2023,41(8):1015-1022.

崔杨,朱晗,王议坚,等.基于CNN-SAEDN-Res的短期电力负荷预测方法[J].电力自动化设备,2024,44(4):164-170.

CUI Yang,ZHU Han,WANG Yijian,et al.Short-term power load forecasting method based onCNN-SAEDN-Res[J]. Electric Power Automation Equipment,2024,44(4):164-170.

岳有军,吴明沅,王红君,等.基于CNN-GRU-ISSA-XGBoost的短期光伏功率预测[J].南京信息工程大学学报,2024,16(2):231-238.

YUE Youjun,WU Mingyuan,WANG Hongjun,et al.Short term photovoltaic power prediction based onCNN-GRU-ISSA-XGBoost[J]Journal of Nanjing University of Information Science &Technology,2024,16(2):231-238.

石庆兰,束金阳,李道亮,等.基于BiLSTM-GRU融合网络的稻虾养殖溶解氧含量预测[J].农业机械学报,2023,54(10):364-370.

SHI Qinglan,SHU Jinyang,LI Daoliang,et al.Dissolved oxygen prediction in rice and shrimp culture based on BiLSTM-GRU fusion neural networks[J]. Transactions of the Chinese Society for Agricultural Machinery,2023,54(10):364-370.

李志刚,张鑫.CNN-GRU模型预测高炉煤气产生量[J].机械设计与制造,2022,374(4):69-72.

LI Zhigang,ZHANG Xin. CNN-GRU model predicts blast furnace gas production[J]. Machinery Design & Manufacture,2022,374(4):69-72.

门嘉铖,樊玉光,高琳,等.EMD-Attention-GRU天然气管网流量组合预测模型[J].油气储运,2023,42(10):1193-1200.

MEN Jiacheng,FAN Yuguang,GAO Lin,et al.Combined flow prediction model for natural gas pipeline network based on EMD-Attention-GRU[J]. Oil & Gas Storage and Transportation,2023,42 (10):1193-1200.

郭士杰,卢世杰,耿艳利,等.融合VIT与CNN注意力机制的面部疼痛评估算法研究[J]. 计算机工程与应用,2024,60(15):277-283.

GUO Shijie,LU Shijie,GENG Yanli,et al.Facial pain assessment algorithm fusing VIT and CNN attention mechanism[J]. Computer Engineering and Applications,2024,60(15):277-283.

彭瑾坤,武文华,顾乃建,等.基于CNN的卫星内部结构频域响应间接测量方法[J].航天器环境工程,2023,40(4):400-407.

PENG Jinkun,WU Wenhua,GU Naijian,et al.An indirect method for measuring frequency domain response of satellite internal structure based on convolutional neural network[J]. Spacecraft Environment Engineering,2023,40(4):400-407.

王凇瑶,张智晟.基于量子加权GRU神经网络的电力系统短期负荷预测[J].电力系统及其自动化学报,2022,34(1):1-7.

WANG Songyao,ZHANG Zhisheng. Short-term load forecasting of power systems based on quantum weighted GRU neural network[J]. Proceedings of the CSU-EPSA,2022,34(1):1-7.

冯裕祺,李辉,李利娟,等.基于CNN-GRU的光伏电站电压轨迹预测[J].中国电力,2022,55(7):163-171.

FENG Yuqi,LI Hui,LI Lijuan,et al.Voltage trajectory prediction of photovoltaic power station based onCNN-GRU[J]. Electric Power,2022,55(7):163-171.

马立玲,郭建,汪首坤,等.基于改进CNN-GRU网络的多源传感器故障诊断方法[J].北京理工大学学报,2021,41(12):1245-1252.

MA Liling,GUO Jian,WANG Shoukun,et al.Multi-source sensor fault diagnosis method based on improved CNN-GRU network[J]. Transactions of Beijing Institute of Technology,2021,41(12):1245-1252.

周璨,杨栋,魏松杰.融合GRU和CNN的轻量级网络入侵检测模型[J].计算机系统应用,2023,32(8):162-170.

ZHOU Can,YANG Dong,WEI Songjie.Integrating GRU and CNN for light - weighted model in network intrusion detection[J]. Computer Systems & Applications,2023,32(8):162-170.

昌千琳,罗永捷,王强钢,等.基于Ⅰ-Ⅴ曲线全局特征提取的光伏组串Swin-Transformer故障诊断方法[J].电工技术学报,2025, 40(23):7664-7676.

CHANG Qianlin,LUO Yongjie,WANG Qianggang,et al.Fault diagnosis method for photovoltaic string based on global Ⅰ-Ⅴcurve feature extraction using swin transformer[J]. Transactions of China Electrotechnical Society,2025,40(23):7664-7676.

张安安,谢琳惺,杨威.基于CNN-GRU组合神经网络的锂电池寿命预测模型研究[J].电测与仪表,2025,62(7):77-84.

ZHANG An'an,XIE Linxing,YANG Wei.Research on lithium battery life prediction model based on CNN-GRU combined neural network[J]. Electrical Measurement & Instrumentation,2025,62 (7):77-84.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于改进麻雀搜索算法优化KELM的变压器故障诊断方法

基于护套电流的高压电缆金属护套接地系统故障诊断判据综述

基于声音信号的12 kV真空断路器健康状态评估与预测

基于KMME和SVDD的电力变压器故障检测与诊断方法

基于数字孪生的GIS综合监控及状态评估技术研究