基于SV-CBDE模型的光伏阵列故障诊断方法

李洋; 郭春梅; 唐俊浩; 由玉文; 贺中禄; 汪磊磊

doi:doi:10.19912/j.0254-0096.tynxb.2024-0993

English Version Reader LoginJournal Login

您当前的位置：

首页 >

文章列表页 >

基于SV-CBDE模型的光伏阵列故障诊断方法

更新时间：2025-12-17

- 基于SV-CBDE模型的光伏阵列故障诊断方法
- Issue 10, Pages: 227-236(2025)
- 作者机构：
- 作者简介：
- 基金信息：
- DOI：doi:10.19912/j.0254-0096.tynxb.2024-0993
  CLC： M615
- Published Online：31 October 2025，
  
  Published：31 October 2025
- 稿件说明：
移动端阅览
李洋, 郭春梅, 唐俊浩, et al. 基于SV-CBDE模型的光伏阵列故障诊断方法[J]. 2025, (10): 227-236.
DOI：

李洋, 郭春梅, 唐俊浩, et al. 基于SV-CBDE模型的光伏阵列故障诊断方法[J]. 2025, (10): 227-236. DOI： doi:10.19912/j.0254-0096.tynxb.2024-0993.

摘要

为精确诊断光伏阵列故障以提高系统发电效率以及避免造成损失

该文提出一种卷积神经网络与双向门控循环单元网络混合模型和深度置信网络与极限学习机混合模型以软投票算法集成的SV-CBDE诊断模型。以光伏阵列的P-V曲线数据作为输入

利用两种模型分别对样本进行诊断

再对两种诊断模型分别输出的诊断结果概率进行加权平均

得出最终诊断结果从而确定故障类型

以此来提高阵列故障诊断的准确率。使用同一数据集对所提出的模型与CNN、CNN-LSTM、CNN-BiGRU以及DBN-ELM 4种故障诊断模型进行对比评估。结果表明：所提集成模型在对组串间开路、组件局部产生阴影、组件间短路、阵列老化以及3类并发故障诊断的准确率、召回率、精确度和F1-Score均优于其他4种模型

具有更强的故障识别能力。

Abstract

In order to achieve accurate fault diagnosis and improve the power generation efficiency of photovoltaic array systems

this paper proposes a SV-CBDE diagnosis model that integrates a hybrid model of convolutional neural network and bidirectional gated recurrent unit network

and a hybrid model of deep belief network and extreme learning machine with a soft voting method. Taking the- curve data of the photovoltaic array as input

the two models are used to diagnose the samples separately

and then the probabilities of the diagnostic results output from the two diagnosis models are weighted and averaged to derive the final diagnostic results and thus the type of faults are determined

so as to improve the accuracy of the photovoltaic array fault diagnosis. The proposed model is evaluated on the same dataset against four fault diagnosis models （CNN

CNN-LSTM

CNN-BiGRU

and DBN-ELM）. The results indicate that the integrated model proposed in this paper exhibits higher accuracy

recall

precision

and F1-score compared to the other four models in diagnosing inter-string open circuits

locally generated shadows in components

inter-component short circuits

photovoltaic array aging

and three types of concurrent faults

demonstrating its superior fault identification capability.

关键词

Keywords

references

陈诗一, 林伯强. 中国能源环境与气候变化经济学研究现状及展望: 首届中国能源环境与气候变化经济学者论坛综述[J]. 经济研究, 2019, 54(7): 203-208.

HONG Y Y, PULA R A.Methods of photovoltaic fault detection and classification: a review[J]. Energy reports, 2022, 8: 5898-5929.

任惠, 夏静, 卢锦玲, 等. 基于红外图像和改进MobileNet-V3的光伏组件故障诊断方法[J]. 太阳能学报, 2023, 44(8): 238-245.

张猛, 尹丽菊, 周辉, 等. 基于SimAM-Ada YOLOv5的太阳能电池表面缺陷检测[J]. 电子测量技术, 2023, 46(22): 17-25.

KELLIL N, AISSAT A, MELLIT A.Fault diagnosis of photovoltaic modules using deep neural networks and infrared images under Algerian climatic conditions[J]. Energy, 2023, 263: 125902.

CHEN S Q, YANG G J, GAO W, et al.Photovoltaic fault diagnosis via semisupervised ladder network with string voltage and current measures[J]. IEEE journal of photovoltaics, 2020, 11(1): 219-231.

张晓娜, 高德东, 刘海雄, 等. 一种新型光伏阵列多传感器故障检测定位方法[J]. 可再生能源, 2016, 34(2): 166-172.

ABD EL-GHANY H A, ELGEBALY A E, TAHA I B M. A new monitoring technique for fault detection and classification in PV systems based on rate of change of voltage-current trajectory[J]. International journal of electrical power & energy systems, 2021, 133: 107248.

程起泽, 陈泽华, 张雲钦, 等. 基于CNN-LSTM的太阳能光伏组件故障诊断研究[J]. 电子技术应用, 2020, 46(4): 66-70.

高伟, 黄俊铭. 基于SSELM的光伏组件故障智能诊断方法[J]. 太阳能学报, 2021, 42(12): 465-470.

李斌, 郭自强, 高鹏. 改进北方苍鹰算法在光伏阵列中应用研究[J]. 电子测量与仪器学报, 2023, 37(7): 131-9.

BADR M M, ABDEL-KHALIK A S, HAMAD M S, et al. Intelligent fault identification strategy of photovoltaic array based on ensemble self-training learning[J]. Solar energy, 2023, 249: 122-138.

ESKANDARI A, AGHAEI M, MILIMONFARED J, et al.A weighted ensemble learning-based autonomous fault diagnosis method for photovoltaic systems using genetic algorithm[J]. International journal of electrical power & energy systems, 2023, 144: 108591.

张希康, 李泽滔. 光伏阵列故障诊断算法研究综述[J]. 智能计算机与应用, 2022, 12(2): 143-147.

林俊亭, 王帅, 刘恩东, 等. 基于模糊聚类和CNN-BIGRU的轨道电路故障预测[J]. 振动测试与诊断, 2023, 43(3): 500-507, 619-620.

司涌波, 张国瑞, 陈光武, 等. 基于深度置信网络的道岔故障智能诊断方法[J]. 重庆大学学报, 2023, 46(7): 75-85.

王永平, 张蕾, 张晓琳, 等. 基于CNN-BiGRU的风机叶片故障诊断[J]. 内蒙古科技大学学报, 2022, 41(2): 173-179.

武洋名, 宗学军, 何戡. 基于数据增强的DBN-ELM入侵检测方法[J]. 科学技术与工程, 2022, 22(34): 15195-15202.

黄富幸, 韩文花. 基于Voting机制的IMA-BP不平衡数据分类算法[J]. 科学技术与工程, 2023, 23(27): 11698-11705.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

基于HPO-CatBoost的光伏阵列故障诊断模型

A FAULT DIAGNOSIS METHOD FOR PHOTOVOLTAIC ARRAY VIA BOA-SAE-EELM

基于改进布谷鸟搜索-支持向量机的光伏阵列接地故障诊断

基于改进MW-KECA算法的风电齿轮箱故障诊断研究

风速分布差异对双馈发电机绕组不对称故障特性影响分析

Related Author

彭自然

许怀顺

肖伸平

肖满生

Chen Shiqun

Yang Gengjie

Gao Wei

赵靖英

Related Institution

College of Electrical Engineering and Automation, Fuzhou University

National Energy Group Science and Technology Research Institute Co., Ltd.

Department of Civil and Airport Engineering, Nanjing University of Aeronautics and Astronautics

Jiangsu Medium Voltage Electrical Engineering Group Co., Ltd.

School of Information Engineering, Lanzhou City University

AI问答

⁰