祁炜雯,张俊,吴洋,范强,赵峰,陈建国,王健
QI Weiwen,ZHANG Jun,WU Yang,FAN Qiang,ZHAO Feng,CHEN Jianguo,WANG Jian

• 1:国网浙江省电力有限公司绍兴供电公司
• 2:国网浙江省电力有限公司
• 3:河海大学能源与电气学院

摘要(Abstract)：

针对基于机器学习算法的光伏电站故障诊断方法存在的样本数据失衡问题，提出一种基于改进BP-Bagging算法的光伏电站故障诊断方法。首先，基于BP神经网络构建光伏数据与光伏故障类型的映射关系，实现光伏故障诊断；然后，基于随机欠采样方法改进Bagging算法，解决样本的类不平衡问题；接着，针对BP网络存在的过拟合问题，提出基于改进BP-Bagging算法的光伏电站故障诊断模型，并行训练多个BP网络，根据投票法得出故障诊断结果；最后，设置不同算法对照实验，计算出关于模型准确率的评价指标，证明所提方法具有较高的综合性能，在一定程度上能够解决光伏电站故障诊断中的样本类不平衡问题，提高光伏电站故障诊断的准确率。
In response to the challenge of sample data imbalance in fault diagnosis methods for photovoltaic power plants based on machine learning, the paper proposes a fault diagnosis method leveraging an enhanced BP-Bagging algorithm. Firstly, a mapping relationship between photovoltaic data and fault types is established using a BP neural network to achieve fault diagnosis in photovoltaic systems. Subsequently, the Bagging algorithm is enhanced by utilizing random under-sampling(RUS) to address the issue of class imbalance in samples. Furthermore, to tackle the problem of overfitting in the BP network, the paper introduces a fault diagnosis model for photovoltaic power plants based on the enhanced BP-Bagging. This involves parallel training of multiple BP networks and determining fault diagnosis results through a voting method. Finally, the paper conducts comparative experiments with different algorithms, calculates evaluation metrics related to model accuracy, and validates that the proposed method demonstrates high overall performance. To a certain extent, it effectively mitigates the challenge of sample class imbalance in fault diagnosis of photovoltaic power plants, thereby improving the accuracy of fault diagnosis in such systems.

关键词(KeyWords)： 光伏电站;故障诊断;随机欠采样;集成学习
photovoltaic power station;fault diagnosis;random under-sampling;ensemble learning

Abstract:

Keywords:

基金项目(Foundation): 国网浙江省电力有限公司科技项目（5211SX220001）

作者(Author): 祁炜雯,张俊,吴洋,范强,赵峰,陈建国,王健
QI Weiwen,ZHANG Jun,WU Yang,FAN Qiang,ZHAO Feng,CHEN Jianguo,WANG Jian

DOI: 10.19585/j.zjdl.202403008

参考文献(References)：

• [1]国家能源局.国家能源局发布1-2月份全国电力工业统计数据[J].电力勘测设计，2023(3):7.The National Energy Administration.The National Energy Administration released statistics on the country's power industry in January-February[J].Electric Power Survey and Design,2023(3):7.
• [2]夏杰锋，唐武勤，杨强.光伏航拍红外图像的热斑自动检测方法[J].浙江大学学报（工学版），2022,56(8):1640-1647.XIA Jiefeng,TANG Wuqin,YANG Qiang.Automatic hot spot detection method for photovoltaic aerial infrared image[J].Journal of Zhejiang University (Engineering Science),2022,56(8):1640-1647.
• [3]蒋琳，苏建徽，李欣，等.基于可见光和红外热图像融合的光伏阵列热斑检测方法[J].太阳能学报，2022,43(1):393-397.JIANG Lin,SU Jianhui,LI Xin,et al.Hot spot detection of photovoltaic array based on fusion of visible and infrared thermal images[J].Acta Energiae Solaris Sinica,2022,43(1):393-397.
• [4]SU Y H,TAO F,JIN J A,et al.Automated overheated region object detection of photovoltaic module with thermography image[J].IEEE Journal of Photovoltaics,2021,11(2):535-544.
• [5]刘强，郭珂，毛明轩，等.一种基于串联等效电阻的光伏故障检测方法[J].太阳能学报，2020,41(10):119-126.LIU Qiang,GUO Ke,MAO Mingxuan,et al A photovoltaic fault detection method based on series equivalent resistance[J].Acta Energiae Solaris Sinica,2020,41(10):119-126.
• [6]陈永辉，熊兰，范禹邑，等.基于互感器电压信号的光伏电弧故障检测方法[J].太阳能学报，2021,42(10):68-75.CHEN Yonghui,XIONG Lan,FAN Yuyi,et al.Photovoltaic arc fault detection method based on transformer voltage signal[J].Acta Energiae Solaris Sinica,2021,42(10):68-75.
• [7]王方政，刘喜泉，陈浈斐，等.基于串联电阻估计的光伏阵列热斑故障诊断方法[J].智慧电力，2022,50(10):61-69.WANG Fangzheng,LIU Xiquan,CHEN Zhenfei,et al.Hot spot failure diagnosis method for photovoltaic array based on series resistance estimation[J].Smart Power,2022,50(10):61-69.
• [8]PLATON R,MARTEL J,WOODRUFF N,et al.Online fault detection in PV systems[J].IEEE Transactions on Sustainable Energy,2015,6(4):1200-1207.
• [9]武文栋，施保华，郑传良，等.基于KPCA-ISSA-KELM的光伏阵列故障诊断方法[J].智慧电力，2022,50(11):69-76.WU Wendong,SHI Baohua,ZHENG Chuanliang,et al.Fault diagnosis method of PV array based on KPCA-ISSA-KELM[J].Smart Power,2022,50(11):69-76.
• [10]孙培胜，陈堂贤，程陈，等.基于SOA-SVM模型的光伏阵列故障诊断研究[J/OL].电源学报：1-13[2023-02-22].http：//kns.cnki.net/kcms/detail/12.1420.TM.20220823.1109.002.html.SUN Peisheng,CHEN Tangxian,CHENG Chen,et al.Research on fault diagnosis of photovoltaic array based on SOA-SVM model[J/OL].Journal of Power Supply:1-13[2023-02-22].http：//kns.cnki.net/kcms/detail/12.1420.TM.20220823.1109.002.html.
• [11]谢琳琳，朱武，崔昊杨.改进遗传优化神经网络的光伏阵列故障诊断[J].电源技术，2022,46(7):802-806.XIE Linlin,ZHU Wu,CUI Haoyang.BP netural network based on improved genetic algorithm for fault diagnosis of photovoltaic array[J].Chinese Journal of Power Sources,2022,46(7):802-806.
• [12]ALI M H,RABHI A,EL HAJJAJI A,et al.Real time fault detection in photovoltaic systems[J].Energy Procedia,2017,111:914-923.
• [13]CHEN Z C,WU L J,CHENG S Y,et al.Intelligent fault diagnosis of photovoltaic arrays based on optimized kernel extreme learning machine and I-V characteristics[J].Applied Energy,2017,204:912-931.
• [14]YU J B,ZHOU X K.One-dimensional residual convolutional autoencoder based feature learning for gearbox fault diagnosis[J].IEEE Transactions on Industrial Informatics,2020,16(10):6347-6358.
• [15]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,2021,11(1):219-231.
• [16]高超，刘泽辉，曹栋，等.基于1DCNN-Bi LSTM的电力电缆故障诊断[J].郑州大学学报（工学版），2023,44(5):86-92.GAO Chao,LIU Zehui,CAO Dong,et al.Fault diagnosis of power cable based on 1DCNN-Bi LSTM[J].Journal of Zhengzhou University (Engineering Science),2023,44(5):86-92.
• [17]李平，胡根铭.基于数据增强型一维改进卷积神经网络的变压器故障诊断方法[J].电网技术，2023,47(7):2957-2967.LI Ping,HU Genming.Transformer fault diagnosis based on data enhanced one-dimensional improved convolutional neural network[J].Power System Technology,2023,47(7):2957-2967.
• [18]顾崇寅，徐潇源，王梦圆，等.基于Cat Boost算法的光伏阵列故障诊断方法[J].电力系统自动化，2023,47(2):105-114.GU Chongyin,XU Xiaoyuan,WANG Mengyuan,et al.CatBoost algorithm based fault diagnosis method for photovoltaic arrays[J].Automation of Electric Power Systems,2023,47(2):105-114.
• [19]周志华.机器学习[M].北京：清华大学出版社，2016:23-95.
• [20]朱显辉，于越，师楠，等.BP神经网络的分层优化研究及其在风电功率预测中的应用[J].高压电器，2022,58(2):158-163.ZHU Xianhui,YU Yue,SHI Nan,et al.Research on hierarchical optimization of BP neural network and its application in wind power prediction[J].High Voltage Apparatus,2022,58(2):158-163.
• [21]ZHU Z J,ZHANG P,LIU Z,et al.Static voltage stability assessment using a random Under Sampling bagging BP method[J].Processes,2022,10(10):1938.
• [22]ZHANG L,WANG F L,SUN T,et al.A constrained optimization method based on BP neural network[J].Neural Computing and Applications,2018,29(2):413-421.
• [23]SHI X F,XU G Q,SHEN F R,et al.Solving the data imbalance problem of P300 detection via Random UnderSampling Bagging SVMs[C]//2015 International Joint Conference on Neural Networks (IJCNN).July 12-17,2015.Killarney,Ireland:IEEE,2015:1-5.
• [24]兰洲，蒋晨威，谷纪亭，等.促进可再生能源发电消纳和碳减排的数据中心优化调度与需求响应策略[J].电力建设，2022,43(4):1-9.LAN Zhou,JIANG Chenwei,GU Jiting,et al.Optimal dispatch and demand response strategies of data centers for promoting accommodation of renewable energy generation and reducing carbon emission[J].Electric Power Construction,2022,43(4):1-9.
• [25]李云飞，许才顺，池招招，等.基于Softmax回归模型的地震灾害损失预测评估研究[J].合肥工业大学学报（自然科学版），2021,44(12):1676-1681.LI Yunfei,XU Caishun,CHI Zhaozhao,et al.Prediction and evaluation of earthquake disaster loss based on Softmax regression model[J].Journal of Hefei University of Technology (Natural Science),2021,44(12):1676-1681.