针对传统的光伏阵列故障诊断方法准确率低、模型性能差以及光伏I-V曲线数据利用率低的问题,提出基于HPO-CatBoost的光伏阵列故障诊断模型。首先,利用光伏阵列模型深入研究短路、开路、老化、阴影遮挡和环境因素（温度、太阳辐照度）对I-V曲线变化的影响,并对其输出特性和故障成因进行系统分析;其次,通过Ordered TS编码来解决CatBoost中目标泄露导致预测偏移的问题,提高诊断模型的泛化能力;最后,CatBoost模型的性能受部分超参数的影响,故提出采用猎人猎物算法（HPO）对模型的关键超参数（树的数量、树的深度和学习率等）进行优化,进一步提升其在故障诊断上的性能表现,并对运行结果和实际光伏平台实验数据进行分析。实验结果表明,该模型的诊断准确率为99.5%,且相较于优化前的CatBoost模型,模型整体的准确率提高3.4%。
Abstract
Aiming at the problems of low accuracy, poor model performance and low utilization of photovoltaic （PV） I-V curve data in traditional PV array fault diagnosis methods, this study proposes a PV array fault diagnosis model based on HPO-CatBoost. Firstly, the PV array model is used to deeply study the effects of short circuit, open circuit, aging, shading and environmental factors （temperature, irradiance） on the changes of I-V curves and systematically analyze their output characteristics and fault causes. Secondly, the problem of prediction bias due to target leakage in CatBoost is solved by Ordered TS coding to improve the generalization ability of the diagnostic model. Finally, the performance of CatBoost model is affected by some hyperparameters, so it is proposed to use hunter-prey optimizer （HPO） to optimize the key hyperparameters of the model （number of trees, tree depth and learning rate, etc.） to further improve its performance in fault diagnosis, and analyze the operation results and the experimental data of the actual PV platform. The experimental results show that the diagnostic accuracy of the model is 99.5%, and the overall accuracy of the model is improved by 3.4% compared to the CatBoost model before optimization..
关键词
光伏阵列 /
故障诊断 /
I-V曲线 /
Catboost /
猎人猎物算法
Key words
photovoltaic array /
fault diagnosis /
I-V curve /
CatBoost /
hunter-prey optimizer
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 孙建民, 梁凌, 李庚达, 等. 光伏组件故障诊断技术综述[J]. 太阳能, 2022(2): 12-22.
SUN J M, LIANG L, LI G D, et al.Overview of PV modules fault diagnosis technology[J]. Solar energy, 2022(2): 12-22.
[2] 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.
ZHANG X K, LI Z T.A survey on photovoltaic array fault diagnosis algorithms[J]. Intelligent computer and applications, 2022, 12(2): 143-147.
[3] 陈世群, 杨耿杰, 高伟. 一种基于BOA-SAE-EELM的光伏阵列故障诊断方法[J]. 太阳能学报, 2022, 43(4): 154-161.
CHEN S Q, YANG G J, GAO W.A fault diagnosis method for photovoltaic array via BOA-SAE-EELM[J]. Acta energiae solaris sinica, 2022, 43(4): 154-161.
[4] MELLIT A, TINA G M, KALOGIROU S A.Fault detection and diagnosis methods for photovoltaic systems: a review[J]. Renewable and sustainable energy reviews, 2018, 91: 1-17.
[5] 程泽, 李兵峰, 刘力, 等. 一种新型结构的光伏阵列故障检测方法[J]. 电子测量与仪器学报, 2010, 24(2): 131-136.
CHENG Z, LI B F, LIU L, et al.A fault detection method for new PV module strufure[J]. Journal of electronic measurement and instrument, 2010, 24(2): 131-136.
[6] PEI T T, LI L, ZHANG J F, et al.Module block fault locating strategy for large-scale photovoltaic arrays[J]. Energy conversion and management, 2020, 214: 112898.
[7] 刘圣洋, 冬雷, 王晓晓, 等. 基于高斯核模糊C均值聚类的光伏阵列故障诊断方法[J]. 太阳能学报, 2021, 42(5): 286-294.
LIU S Y, DONG L, WANG X X, et al.Photovoltaic array fault diagnosis based on GKFCM[J]. Acta energiae solaris sinica, 2021, 42(5): 286-294.
[8] 高剑, 郭倩, 卫东. 基于光伏组件I-V输出特性的典型故障分析与诊断[J]. 中国测试. 2024, 50(12): 163-168.
GAO J, GUO Q, WEI D.Typical fault analysisand diagnosis based on I-V output characteristics of photovoltaic modules[J]. China test2024, 50(12): 163-168.
[9] 彭辉, 田程程, 郑宇锋, 等. 基于深度置信网络的光伏发电阵列的故障诊断方法[J]. 海军工程大学学报, 2024, 36(3): 7-14.
PENG H, TIAN C C, ZHENG Y F, et al.Fault diagnosis method for photovoltaic power arraysbased on deep belief network[J/OL]. Journal of naval university of engineering, 2024, 36(3): 7-14.
[10] LI B J, DELPHA C, MIGAN-DUBOIS A, et al.Fault diagnosis of photovoltaic panels using full I-V characteristics and machine learning techniques[J]. Energy conversion and management, 2021, 248: 114785.
[11] 李东虎, 徐凌桦, 龙道银, 等. 遗传算法优化BP神经网络的光伏阵列故障诊断[J]. 微处理机, 2021, 42(6): 23-26.
LI D H, XU L H, LONG D Y, et al.Photovoltaic array fault diagnosis with genetic algorithm optimized BP neural network[J]. Microprocessors, 2021, 42(6): 23-26.
[12] 戴森柏, 陈志聪, 吴丽君, 等. 利用LSTM和稳态时间序列的光伏阵列故障诊断方法[J]. 福州大学学报(自然科学版), 2022, 50(1): 54-60.
DAI S B, CHEN Z C, WU L J, et al.A photovoltaic array fault diagnosis method using LSTM and steady-state time series[J]. Journal of Fuzhou University (natural science edition), 2022, 50(1): 54-60.
[13] 陈伟, 陈克松, 纪青春, 等. 基于1D-CNN+GRU的光伏阵列故障诊断方法研究[J]. 自动化仪表, 2022, 43(6): 13-17.
CHEN W, CHEN K S, JI Q C, et al.Research on fault diagnosis method of photovoltaic array based on 1D-CNN+GRU[J]. Process automation instrumentation, 2022, 43(6): 13-17.
[14] 段震清, 孙建民, 梁凌, 等. 基于XGBoost算法的光伏阵列故障诊断方法研究[J]. 太阳能, 2023(1): 62-68.
DUAN Z Q, SUN J M, LIANG L, et al.Research on fault diagnosis method for PV array based on XGBoost algorithm[J]. Solar energy, 2023(1): 62-68.
[15] KUMAR U, MISHRA S, DASH K.An IoT and semi-supervised learning-based sensorless technique for panel level solar photovoltaic array fault diagnosis[J]. IEEE transactions on instrumentation and measurement, 2023, 72: 1-12.
[16] 郭步豪. 基于梯度提升机器学习算法的ECG身份识别[D]. 长春: 吉林大学, 2020.
GUO B H.ECG identification based on gradient enhancement machine learning algorithm[D]. Changchun: Jilin University, 2020.
[17] PROKHORENKOVA L, GUSEV G, VOROBEV A, et al. CatBoost: unbiased boosting with categorical features[EB/OL].2017: 1706.09516.https://arxiv.org/abs/1706.09516v5
[18] LI Y L, DING K, ZHANG J W, et al.A fault diagnosis method for photovoltaic arrays based on fault parameters identification[J]. Renewable energy, 2019, 143: 52-63.
[19] 彭自然, 张颖清, 肖伸平. 基于YOLOv5的太阳电池表面缺陷检测[J]. 太阳能学报, 2024, 45(6): 368-375.
PENG Z R, ZHANG Y Q, XIAO S P.Research on surface detection of solar cell with improved YOLOV5 algorithm[J]. Acta energiae solaris sinica, 2024, 45(6): 368-375.
[20] MEHMOOD A, SHER H A, MURTAZA A F, et al.A diode-based fault detection, classification, and localization method for photovoltaic array[J]. IEEE transactions on instrumentation and measurement, 2021, 70: 1-12.
[21] DIRNBERGER D, KRALING U.Uncertainty in PV module measurement: part I: calibration of crystalline and thin-film modules[J]. IEEE journal of photovoltaics, 2013, 3(3): 1016-1026.
基金
国家重点研发计划（2019YFE0122600）; 湖南省教育厅重点科研项目（22A0423）; 湖南省自科科学基金（2023JJ60267; 2022JJ50073）
PDF(2727 KB)
