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

doi:10.19595/j.cnki.1000-6753.tces.242073

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (3876 KB)
输出: BibTeX | EndNote (RIS)

摘要

为提高光伏系统自动化运维水平,提出一种基于I-V曲线全局特征提取的光伏组串Swin-Transformer故障诊断方法,实现准确可靠的智能化光伏状态监测。首先通过校正与归一化预处理提升I-V曲线数据的规范性。随后采用格拉姆角场、递归图和相对位置矩阵多维度刻画I-V曲线的动态特性,提取表征光伏组串状态信息的全局I-V特征。针对特征图的局部区域周期性重复等特点,提出Swin Transformer故障诊断模型,采用分层结构聚合局部特征实现层次化表示,设计移位窗口机制融合局部与全局特征,通过局部自注意力计算实现高效故障诊断。3.75kW光伏系统的仿真和现场实验表明,所提方法在相对位置矩阵特征变换下性能最佳,可精确诊断不同条件和严重程度的多种故障。在每类样本数低至25个时模型准确率为99.67%,在30dB噪声干扰下模型准确率为99.56%。采用多种特征数据与不同算法进行消融实验,验证了所提特征提取法与故障诊断模型的优越性。这项研究为光伏组串稳定运行提供了可靠的技术支持。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	昌千琳
	罗永捷
	王强钢
	任博
	周念成

关键词 ：光伏组串, 故障诊断, I-V曲线, 全局特征, Swin-Transformer

Abstract：

The installed capacity of grid-connected photovoltaic power generation has grown rapidly, and the healthy operation of PV strings is crucial to the safety and stability of the PV power plant system. However, with the construction of PV bases in deserts, Gobi wastelands, and mountainous areas, the harsh outdoor operating environment has led to frequent failures, resulting in a decline in the overall power and even fire accidents. Therefore, fast and accurate PV fault diagnosis is crucial to ensure the reliable and safe operation of PV bases. In order to improve the automated operation and maintenance level of PV system, a Swin-Transformer fault diagnosis method for PV strings based on global feature extraction of I-V curves is proposed to realize accurate and reliable intelligent PV condition monitoring.
Firstly, global I-V feature extraction is carried out to make full use of the dynamic characteristics of the I-V curve, which is greatly affected by the environment, and in order to avoid misidentifying the changes in the curve caused by environmental factors as fault characteristics, the curve needs to be calibrated to the standard test conditions (STC). After calibration, normalization preprocessing is performed due to the different sampling points and uneven distribution. The normality of the I-V curve data is improved by the correction and normalization preprocessing. Then, the dynamic characteristics of I-V curves are portrayed multidimensionally using the Gram angle field (GAF), recurrence plot (RP) and relative position matrix (RPM) feature transformations, and the global I-V features characterizing the state information of PV arrays are extracted.
The GAF, RP and RPM feature extraction methods transform the data into images for processing and analysis using models in the field of computer vision, and for the characteristics of periodicity and repetitiveness of local areas of the image, a fault diagnosis model based on Swin Transformer is proposed, which adopts a hierarchical structure to progressively aggregate the local features, and then represents the global features, and the hierarchical feature extraction is more suitable for dealing with the image data; a shift window is designed to extract global I-V features characterizing the state information of PV arrays. The hierarchical feature extraction method is more suitable for processing image data; a shift window mechanism is designed to fuse local and global features across the window, which has strong image processing capability; local self-attention computation using the shift window can adapt to image inputs with different resolutions without providing a large number of samples, which effectively reduces the amount of computation and improves the efficiency of the model, and realizes high-precision fault diagnosis.
Simulations and field experiments on a 3.75kW PV system show that the proposed method performs best under the relative position matrix feature transformation, and can accurately diagnose multiple faults with different conditions and severities. The model accuracy is 99.67% with as low as 25 samples per class and 99.56% with 30dB noise interference. Ablation experiments using multiple feature data with different algorithms validate the superiority of the proposed feature extraction method and fault diagnosis model. This study provides reliable technical support for the stable operation of PV strings.

Key words： PV strings fault diagnosis I-V curve global feature swin-transformer

收稿日期: 2024-11-17

PACS:

TM615

基金资助:

国家自然科学基金集成项目资助（U22B6006）

通讯作者: 王强钢男,1987年生,博士,教授,博士生导师,研究方向为电力系统保护与控制、电能质量、新能源发电运行与控制。E-mail：qianggang1987@cqu.edu.cn

作者简介: 昌千琳女,2001年生,硕士研究生,研究方向为直流保护、故障检测与诊断、人工智能在新能源系统中的应用。E-mail：qianlinchang@stu.cqu.edu.cn

引用本文:

昌千琳, 罗永捷, 王强钢, 任博, 周念成. 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, 0, (): 250431-. Chang Qianlin, Luo YongJie, Wang Qianggang, Ren Bo, Zhou Niancheng. Fault Diagnosis Method for Photovoltaic String Based on Global I-V Curve Feature Extraction Using Swin Transformer. Transactions of China Electrotechnical Society, 0, (): 250431-.

链接本文:

https://dgjsxb.ces-transaction.com/CN/10.19595/j.cnki.1000-6753.tces.242073 https://dgjsxb.ces-transaction.com/CN/Y0/V/I/250431

[1] 吴春华, 易苑, 李智华, 等. 考虑参数权重与分层映射的光伏组件健康程度检测[J]. 电工技术学报, 2024, 39(15): 4856-4867.
Wu Chunhua, Yi Yuan, Li Zhihua, et al.Health detection of photovoltaic modules considering parameter weights and hierarchical mapping[J]. Transactions of China Electrotechnical Society, 2024, 39(15): 4856-4867.
[1] 吴春华, 易苑, 李智华, 等. 考虑参数权重与分层映射的光伏组件健康程度检测[J]. 电工技术学报, 2024, 39(15): 4856-4867.
Wu Chunhua, Yi Yuan, Li Zhihua, et al.Health detection of photovoltaic modules considering parameter weights and hierarchical mapping[J]. Transactions of China Electrotechnical Society, 2024, 39(15): 4856-4867.
[2] 王小宇, 刘波, 孙凯, 等. 光伏阵列故障诊断技术综述[J]. 电工技术学报, 2024, 39(20): 6526-6543.
Wang Xiaoyu, Liu Bo, Sun Kai, et al.A review of photovoltaic array fault diagnosis technology[J]. Transactions of China Electrotechnical Society, 2024, 39(20): 6526-6543.
[3] Zhang Zhixiang, Ma Mingyao, Ma Wenting, et al.A data-driven photovoltaic string current mismatch fault diagnosis method based on I-V curve[J]. Microelectronics Reliability, 2022, 138: 114705.
[4] 刘恒, 马铭遥, 张志祥, 等. 热斑晶硅光伏组件I-V曲线分析及特征模拟研究[J]. 太阳能学报, 2021, 42(4): 239-246.
Liu Heng, Ma Mingyao, Zhang Zhixiang, et al.Study on i-v curve analysis and characteristic simulation of silicon photovoltaic module with hot spot[J]. Acta Energiae Solaris Sinica, 2021, 42(4): 239-246.
[5] Huang Junming, Wai R J, Gao Wei.Newly-designed fault diagnostic method for solar photovoltaic generation system based on IV-curve measurement[J]. IEEE Access, 2019, 7: 70919-70932.
[6] Dhimish M, Chen Zhicong.Novel open-circuit photovoltaic bypass diode fault detection algorithm[J]. IEEE Journal of Photovoltaics, 2019, 9(6): 1819-1827.
[7] Bonsignore L, Davarifar M, Rabhi A, et al.Neuro-fuzzy fault detection method for photovoltaic systems[J]. Energy Procedia, 2014, 62: 431-441.
[8] 王尧, 马桐桐, 赵宇初, 等. 基于电磁辐射时延估计的串联光伏直流电弧故障定位方法[J]. 电工技术学报, 2023, 38(8): 2233-2243.
Wang Yao, Ma Tongtong, Zhao Yuchu, et al.Series DC arc-fault location method based on electromagnetic radiation delay estimation for photovoltaic systems[J]. Transactions of China Electrotechnical Society, 2023, 38(8): 2233-2243.
[9] Ren Bo, Wang Qianggang, Zhou Niancheng, et al.Fault diagnosis of photovoltaic strings based on SiamMN networks and panoramic I-V features[J]. IEEE Transactions on Industrial Electronics, 2025, 72(3): 3172-3182.
[10] 涂彦昭, 高伟, 杨耿杰. 一种基于卷积神经网络和长短期记忆网络的光伏系统故障辨识方法[J]. 电气技术, 2022, 23(2): 48-54.
Tu Yanzhao, Gao Wei, Yang Gengjie.A photovoltaic system fault identification method based on convolutional neural network and long short-term memory network[J]. Electrical Engineering, 2022, 23(2): 48-54.
[11] 赵靖英, 吴晶晶, 张雪辉, 等. 基于萤火虫扰动麻雀搜索算法-极限学习机的光伏阵列故障诊断方法研究[J]. 电网技术, 2023, 47(4): 1612-1625.
Zhao Jingying, Wu Jingjing, Zhang Xuehui, et al.Fault diagnosis of photovoltaic arrays based on sparrow search algorithm with firefly perturbation-extreme learning machine[J]. Power System Technology, 2023, 47(4): 1612-1625.
[12] 顾崇寅, 徐潇源, 王梦圆, 等. 基于CatBoost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.
[13] 陈凌, 韩伟, 张经炜. 基于数据融合的光伏组件故障诊断[J]. 电网技术, 2017, 41(6): 1864-1873.
Chen Ling, Han Wei, Zhang Jingwei.PV module fault diagnosis based on data fusion[J]. Power System Technology, 2017, 41(6): 1864-1873.
[14] Huang Junming, Wai R J, Yang Gengjie.Design of hybrid artificial bee colony algorithm and semi-supervised extreme learning machine for PV fault diagnoses by considering dust impact[J]. IEEE Transactions on Power Electronics, 2019, 35(7): 7086-7099.
[15] Liu Yongjie, Ding Kun, Zhang Jingwei, et al.Intelligent fault diagnosis of photovoltaic array based on variable predictive models and I-V curves[J]. Solar Energy, 2022, 237: 340-351.
[16] Chen Zhicong, Chen Yixiang, Wu Lijun, et al.Deep residual network based fault detection and diagnosis of photovoltaic arrays using current-voltage curves and ambient conditions[J]. Energy Conversion and Management, 2019, 198: 111793.
[17] Li Baojie, 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.
[18] 曾祥超, 张鹤仙, 王水威, 等. 双面光伏组件I-V测试方法研究[J]. 太阳能学报, 2021, 42(3): 370-374.
Zeng Xiangchao, Zhang Hexian, Wang Shuiwei, et al.Research on testing methods of i-v characteristics of bifacial pv modules[J]. Acta Energiae Solaris Sinica, 2021, 42(3): 370-374.
[19] Standard IEC 60891. Photovoltaic Devices. Procedures for Temperature and Irradiance Corrections to Measured IV Characteristics IEC 60891. Photovoltaic Devices. Procedures for Temperature and Irradiance Corrections to Measured IV Characteristics[S]. International Electrotechnical Commission, 2009.
[20] Wang Zhiguang, Oates T, Wang Zhiguang, et al.Imaging time-series to improve classification and imputation[C]//Proceedings of the 24th International Conference on Artificial Intelligence, Buenos Aires, Argentina, 2015: 3939-3945.
[21] Zhiguang Wang, Tim Oates.Encoding time series as images for visual inspection and classification using tiled convolutional neural networks[C]//Workshops at the twenty-ninth AAAI conference on artificial intelligence. 2015.
[22] Marwan N, Carmen Romano M, Thiel M, et al.Recurrence plots for the analysis of complex systems[J]. Physics Reports, 2007, 438(5/6): 237-329.
[23] Chen Wei, Shi Ke.A deep learning framework for time series classification using Relative Position Matrix and Convolutional Neural Network[J]. Neurocomputing, 2019, 359: 384-394.
[24] Liu Ze, Lin Yutong, Cao Yue, et al.Swin transformer: hierarchical vision transformer using shifted windows[C]//2021 IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada, 2021: 9992-10002.
[25] Ashish Vaswani, Noam Shazeer, Niki Parmar, et al.Attention is all you need[J]. Advances in Neural Information Processing Systems, 2017, 30: 5998-6008
[26] Hu Han, Zhang Zheng, Xie Zhenda, et al.Local relation networks for image recognition[C]//2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Korea (South), 2019: 3464-3473.
[27] Dosovitskiy Alexey.An image is worth 16x16 words: Transformers for image recognition at scale[C]//The Ninth International Conference on Learning Representations, 2021.
[28] Dirnberger D, Kräling 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.
[29] Pvps I, Driesse A, Razongles G, et al.Uncertainties in PV system yield predictions and assessments[R]. Report IEA-PVPS T13-12, 2018.
[30] Eskandari A, Milimonfared J, Aghaei M.Fault detection and classification for photovoltaic systems based on hierarchical classification and machine learning technique[J]. IEEE Transactions on Industrial Electronics, 2021, 68(12): 12750-12759.