IEEE Journal of Photovoltaics最新文献_第9页

Defective Electroluminescence Image Generation for Data Imbalance in Solar Cell Defect Inspection 太阳能电池缺陷检测中数据不平衡的缺陷电致发光图像生成

IF 3.7 3区工程技术

IEEE Journal of Photovoltaics Pub Date : 2025-11-01 Epub Date: 2025-09-04 DOI: 10.1109/JPHOTOV.2025.3599613

Ziai Zhou;Jiacheng Jiang;Jinxia Zhang

{"title":"Defective Electroluminescence Image Generation for Data Imbalance in Solar Cell Defect Inspection","authors":"Ziai Zhou;Jiacheng Jiang;Jinxia Zhang","doi":"10.1109/JPHOTOV.2025.3599613","DOIUrl":"https://doi.org/10.1109/JPHOTOV.2025.3599613","url":null,"abstract":"The utilization of high-resolution electroluminescence (EL) images for defect inspection in photovoltaic modules has gained significant popularity. However, there are limited works on the imbalance problem in the EL images of the photovoltaic modules, specifically that the number of defective images is substantially less than the number of normal images. To address the above problem, a fast defective EL image generation method is proposed in this article. To accurately extract the defective region, a normal image, which is the most similar to the defective image, needs to be identified. First, an image type classification network is proposed to recognize the normal images with the same type (monocrystalline or polycrystalline) as the defective image. Then, the cosine similarity is further employed to identify the normal image that is most similar to the defective image. After that, the defective template is acquired by comparing the defective image with the identified similar normal image. To quickly generate diverse and rich defective EL images, effective data augmentation methods for EL images are exploited and applied to the defective template. Specifically, small-scale rotation and Gaussian blurring are first introduced to augment the EL images. Finally, the augmented defective templates are merged with any different normal images to produce a large amount of new defective images. The experimental comparison of the proposed defective image generation method with oversampling and data augmentation, which are commonly used for data imbalance, demonstrates that our proposed method can provide richer information and thus outperform other methods with a big gap.","PeriodicalId":445,"journal":{"name":"IEEE Journal of Photovoltaics","volume":"15 6","pages":"908-914"},"PeriodicalIF":3.7,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148484130","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Improving Estimation of Parameters in Photovoltaic Models Using Two-Level Layered Physics-Informed Neural Networks 利用两层物理信息神经网络改进光伏模型参数估计

IF 3.7 3区工程技术

IEEE Journal of Photovoltaics Pub Date : 2025-11-01 Epub Date: 2025-09-17 DOI: 10.1109/JPHOTOV.2025.3604854

Nikta Shamsmohammadi;Giovanni Spagnuolo;José del Campo-Ávila;Esteban José Palomo;Llanos Mora-López

{"title":"Improving Estimation of Parameters in Photovoltaic Models Using Two-Level Layered Physics-Informed Neural Networks","authors":"Nikta Shamsmohammadi;Giovanni Spagnuolo;José del Campo-Ávila;Esteban José Palomo;Llanos Mora-López","doi":"10.1109/JPHOTOV.2025.3604854","DOIUrl":"https://doi.org/10.1109/JPHOTOV.2025.3604854","url":null,"abstract":"Accurate estimation of parameters in photovoltaic models is essential to improve system monitoring, control, and diagnostics. In this study, a novel two-level layered physics-informed neural network (PINN) architecture is proposed to estimate the parameters irradiance (<inline-formula><tex-math>$G$</tex-math></inline-formula>) and temperature (<inline-formula><tex-math>$T$</tex-math></inline-formula>), and junction capacitance (<inline-formula><tex-math>$C_{j0}$</tex-math></inline-formula>) in a dynamic single-diode PV model. In case no noise affects the PV current and voltage waveforms, the proposed method achieves errors equal to <bold>0.25% for <inline-formula><tex-math>$G$</tex-math></inline-formula>, <bold>1.5% for <inline-formula><tex-math>$T$</tex-math></inline-formula>, and <bold>2.1% for <inline-formula><tex-math>$C_{j0}$</tex-math></inline-formula>. Compared to traditional optimization methods, the two-level layered PINN shows a better performance, particularly in learning the nonlinear behavior of <inline-formula><tex-math>$C_{j0}$</tex-math></inline-formula>. Sensitivity analysis under additive Gaussian noise (0% –5% ) confirms the robustness of the approach, with a slight increase of the identification error. The results confirm the effectiveness of incorporating physical knowledge into neural networks for robust and reliable parameter estimation in dynamic photovoltaic systems.","PeriodicalId":445,"journal":{"name":"IEEE Journal of Photovoltaics","volume":"15 6","pages":"858-867"},"PeriodicalIF":3.7,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148484662","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Controllable Methylamine Vapor Treatment for Improving Performance of Vapor-Processed Perovskite Solar Cells 可控甲胺蒸汽处理提高蒸汽处理钙钛矿太阳能电池性能

IF 3.7 3区工程技术

IEEE Journal of Photovoltaics Pub Date : 2025-11-01 Epub Date: 2025-09-16 DOI: 10.1109/JPHOTOV.2025.3604874

Chaiwarut Santiwipharat;Austin G. Kuba;Kevin D. Dobson;Ujjwal K. Das;William N. Shafarman

{"title":"Controllable Methylamine Vapor Treatment for Improving Performance of Vapor-Processed Perovskite Solar Cells","authors":"Chaiwarut Santiwipharat;Austin G. Kuba;Kevin D. Dobson;Ujjwal K. Das;William N. Shafarman","doi":"10.1109/JPHOTOV.2025.3604874","DOIUrl":"https://doi.org/10.1109/JPHOTOV.2025.3604874","url":null,"abstract":"While the development of methylammonium lead iodide (<inline-formula><tex-math>${mathrm{MAPbI}}_{3}$</tex-math></inline-formula>) perovskite in photovoltaic research has matured for solution-based fabrication methods, the growth of high-quality material from vapor processes continues to be difficult due to challenges in vapor chemistry control. Postdeposition methylamine (MA) vapor treatment is an approach to improve the morphology and crystallinity of <inline-formula><tex-math>${mathrm{MAPbI}}_{3}$</tex-math></inline-formula> films, producing highly oriented, large-grain perovskite films. Herein, experiments to characterize the effects of substrate temperature, MA partial pressure, and MA exhaust flow rate on the liquefaction and recrystallization processes that occur during MA treatments are described. Improved morphology and crystallinity following MA treatment indicate that substrate temperature plays a significant role in both processes during treatment. The enhancement in electronic properties after treatment is confirmed by steady-state and time-resolved photoluminescence spectroscopy. The solar cells made from the films treated at the optimal treatment conditions have shown open circuit voltages over 1 V and fill factors up to 70%. The result of this study is a useful pathway for the fabrication of high-quality <inline-formula><tex-math>${mathrm{MAPbI}}_{3}$</tex-math></inline-formula> films via all-vapor process manufacturing.","PeriodicalId":445,"journal":{"name":"IEEE Journal of Photovoltaics","volume":"15 6","pages":"792-800"},"PeriodicalIF":3.7,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148486780","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

New Model for Estimating the Temperature and Solar Irradiance of Photovoltaic Panels Based on Maximum Power Point Tracking Measurements 基于最大功率点跟踪测量的光伏板温度和太阳辐照度估算新模型

IF 3.7 3区工程技术

IEEE Journal of Photovoltaics Pub Date : 2025-11-01 Epub Date: 2025-09-16 DOI: 10.1109/JPHOTOV.2025.3604875

Zine Eddine Touhami Ternifi;Luis Garcia-Gutierrez;Mohammed El Bachir Ghribi;Ghalem Bachir;Michel Aillerie

{"title":"New Model for Estimating the Temperature and Solar Irradiance of Photovoltaic Panels Based on Maximum Power Point Tracking Measurements","authors":"Zine Eddine Touhami Ternifi;Luis Garcia-Gutierrez;Mohammed El Bachir Ghribi;Ghalem Bachir;Michel Aillerie","doi":"10.1109/JPHOTOV.2025.3604875","DOIUrl":"https://doi.org/10.1109/JPHOTOV.2025.3604875","url":null,"abstract":"This article proposes a new method for estimating the temperature and irradiance of a photovoltaic module using current and voltage measurements within a maximum power point tracking (MPPT) control system. Unlike traditional methods that depend on external data, such as those provided by complex irradiance and wind speed sensors and equipment, this approach relies solely on panel-specific <italic>I–<italic>V measurements needed for MPPT, enabling accurate estimations through a simpler and real-time method. A comparative evaluation of various panel temperature estimation techniques confirms that the proposed method outperforms existing ones, resulting in mean absolute estimation errors below 1 °C for temperature and 4 W/m2 for irradiance. The method effectively addresses temperature variations, particularly under low irradiance conditions, where the proportional relationship between current and irradiance becomes less reliable. Results indicate that incorporating the estimated panel temperature significantly enhances irradiance predictions, especially in real-world operating conditions. Furthermore, the method remains valid even as the panel ages, making it a valuable tool for optimizing photovoltaic system performance. Given its simplicity and its low cost, this technique is well suited for real-time monitoring and optimization of solar energy installations.","PeriodicalId":445,"journal":{"name":"IEEE Journal of Photovoltaics","volume":"15 6","pages":"832-839"},"PeriodicalIF":3.7,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148481468","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Using Convolutional Neural Networks to Detect In-Field PV Module Glass Cracks 利用卷积神经网络检测现场光伏组件玻璃裂纹

IF 3.7 3区工程技术

IEEE Journal of Photovoltaics Pub Date : 2025-11-01 Epub Date: 2025-09-29 DOI: 10.1109/JPHOTOV.2025.3605688

Savannah Bennett;Thomas Weber;Rory Bennett;Ernst Wittman;Oleksandr Mashkov;Christoph J. Brabec;Thilo Winkler;Claudia Buerhop-Lutz;Ian Marius Peters

{"title":"Using Convolutional Neural Networks to Detect In-Field PV Module Glass Cracks","authors":"Savannah Bennett;Thomas Weber;Rory Bennett;Ernst Wittman;Oleksandr Mashkov;Christoph J. Brabec;Thilo Winkler;Claudia Buerhop-Lutz;Ian Marius Peters","doi":"10.1109/JPHOTOV.2025.3605688","DOIUrl":"10.1109/JPHOTOV.2025.3605688","url":null,"abstract":"Double-glass photovoltaic modules are being increasingly deployed, and there is a growing concern about glass cracking in these modules. To confirm this phenomenon, to quantify the rates of glass cracking, and to alleviate the laborious task of finding these cracked modules in the field, this article considers the use of convolutional neural networks for glass crack detection. Seven models are tested: a six-layer model, a four-layer model, VGG16, VGG19, ResNet18, ResNet34, and ResNet50. Using a nonstandardized image acquisition method in two photovoltaic (PV) fields with two module types, seven labeled datasets have been created, ranging in size from 3540 to 12 600 images. The six-layer model can achieve crack versus no-crack classification accuracies of up to 97.7%, while the inference time per image using a CPU is 1.5 s. The more complex ResNet50 model achieves classification test accuracies up to 99.7%, but it has an inference time of up to 10.5 s per image. Thus, this article demonstrates that using a relatively simple convolutional neural network is a viable approach to detecting PV glass cracks with low computational cost. In addition, the YOLOv11 instance segmentation model is used to segment the glass cracks, and it achieves up to 95.7% in bounding box precision, mask precision, recall, and mean average precision@50. This demonstrates that segmentation can also be implemented on an automated inspection system without increasing computational costs. Finally, the water index on two modules was measured using a near-infrared absorption spectrometer, and the results suggest that there is higher water ingress along the cracks when compared with the rest of the modules.","PeriodicalId":445,"journal":{"name":"IEEE Journal of Photovoltaics","volume":"15 6","pages":"868-878"},"PeriodicalIF":3.7,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11184131","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147920217","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Enhancing Photovoltaic Power Forecasting Using the LGB Model and Synthetic Features 利用LGB模型和综合特征加强光伏发电预测

IF 3.7 3区工程技术

IEEE Journal of Photovoltaics Pub Date : 2025-11-01 Epub Date: 2025-04-17 DOI: 10.1109/JPHOTOV.2025.3558264

Costanza Luppi;Francesco Lo Franco;Vincenzo Cirimele;Mattia Ricco;Valerio Apicella

{"title":"Enhancing Photovoltaic Power Forecasting Using the LGB Model and Synthetic Features","authors":"Costanza Luppi;Francesco Lo Franco;Vincenzo Cirimele;Mattia Ricco;Valerio Apicella","doi":"10.1109/JPHOTOV.2025.3558264","DOIUrl":"https://doi.org/10.1109/JPHOTOV.2025.3558264","url":null,"abstract":"Over the past decade, the growing demand for sustainable energy has led to significant interest in photovoltaic (PV) power generation. Due to its intermittent nature, accurate PV power forecasting is essential for the efficient management and monitoring of PV systems. In this context, the accuracy of meteorological data is critical. However, it is not always possible to obtain such data on a local basis, and often some information, such as irradiance, is obtained from models whose characteristics are not known in detail. To overcome this limitation, this study evaluates five synthetic features that combine clear-sky global horizontal irradiance and cloudiness data to estimate total irradiance in the absence of direct measurements. A light gradient boosting model is used to evaluate the predictive performance of a model using these synthetic features compared to a model based on conventional meteorological inputs, including irradiance. The results, evaluated over a reference week, show that the feature labeled <bold><inline-formula><tex-math>$chi _{5}$</tex-math></inline-formula> slightly improves model accuracy (passing from an RMSE of 84.013 to 87.232 W/kWp and <inline-formula><tex-math>$R^{2}$</tex-math></inline-formula> from 0.888 to 0.875). These results show that synthetic features can achieve comparable results and in some cases even improve prediction performance.","PeriodicalId":445,"journal":{"name":"IEEE Journal of Photovoltaics","volume":"15 6","pages":"770-775"},"PeriodicalIF":3.7,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148483083","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Statistical Analysis of Fault Detection in Photovoltaics Using Reflectometry 用反射法检测光伏系统故障的统计分析

IF 3.7 3区工程技术

IEEE Journal of Photovoltaics Pub Date : 2025-11-01 Epub Date: 2025-09-29 DOI: 10.1109/JPHOTOV.2025.3608439

Ayobami S. Edun;Cody LaFlamme;Evan J. Benoit;Cynthia Furse;Joel B. Harley

{"title":"A Statistical Analysis of Fault Detection in Photovoltaics Using Reflectometry","authors":"Ayobami S. Edun;Cody LaFlamme;Evan J. Benoit;Cynthia Furse;Joel B. Harley","doi":"10.1109/JPHOTOV.2025.3608439","DOIUrl":"https://doi.org/10.1109/JPHOTOV.2025.3608439","url":null,"abstract":"Spread spectrum time domain reflectometry (SSTDR) has been used to detect different kinds of faults in cables, aircraft wiring, and photovoltaic (PV) setups. One significant problem is that, since most methods that use reflectometry are based on a comparison with a known baseline, variations in the baseline caused by system or environmental variations can overshadow the reflections produced by faults and reduce the probability of detection. The effects of these variations are exacerbated for faults far from the test device. The objective of this work is to statistically estimate the probability that a reflection from a PV array is or is not a fault amid environmental variations, system variations, and at different locations along the line. Our results show the probability of detecting fault presence at different distances from the test device when there are partial and full disconnects over a range of signal-to-noise ratio (SNR). At a distance of 97.54 m (320 ft) from the tester, the probability of detection of a full disconnect is as high as 0.75 with an SNR of about 9 dB, while the probability of detection is nearly zero for partial faults at the same location. We also present scenarios where faults can no longer be detected and how averaging could help improve the probability of detection.","PeriodicalId":445,"journal":{"name":"IEEE Journal of Photovoltaics","volume":"15 6","pages":"915-924"},"PeriodicalIF":3.7,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148484695","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Study of Photovoltaic Parameters of Efficient Bulk-Heterojunction Organic Solar Cells for Indoor Applications Under Varied Intensities and Indoor LED Lighting 不同光强和室内LED照明条件下高效体积异质结有机太阳能电池的光伏参数研究

IF 3.7 3区工程技术

IEEE Journal of Photovoltaics Pub Date : 2025-11-01 Epub Date: 2025-08-13 DOI: 10.1109/JPHOTOV.2025.3592679

Shyam Shankar S;Kanupriya Khandelwal;Gaurav Gupta;Ganesh D. Sharma

{"title":"Study of Photovoltaic Parameters of Efficient Bulk-Heterojunction Organic Solar Cells for Indoor Applications Under Varied Intensities and Indoor LED Lighting","authors":"Shyam Shankar S;Kanupriya Khandelwal;Gaurav Gupta;Ganesh D. Sharma","doi":"10.1109/JPHOTOV.2025.3592679","DOIUrl":"https://doi.org/10.1109/JPHOTOV.2025.3592679","url":null,"abstract":"Bulk-heterojunction devices with D18 and Y12 as active material were fabricated with an inverted ITO/zinc oxide/active material/molybdenum (III) oxide/Ag structure. Donor D18 and acceptor Y12 have complementary absorption spectra covering the visible range (300–800 nm). Furthermore, the energy layer alignment of these materials also makes it easier for charge generation and transport. All these factors lead to exploiting the possibility of using these organic solar cells (OSCs) for indoor photovoltaic (IPV) applications. The devices prepared previously were soaked in light (AM1.5 G) and illuminated under three types of white LED: warm white, standard white, and cool white. The intensities of the lights were varied, and the photovoltaic parameters of the cells were recorded. The variation of photovoltaic parameters with the intensity and color-correlated temperature (CCT) of different lights was thoroughly studied in this work. The external quantum efficiency of devices was also recorded. Here, we obtained cells with a power conversion efficiency (PCE) of 12.88% in AM1.5 G, which went up to 27.58% in indoor lighting. All the devices were prepared without the nitrogen glovebox and were characterized in ambient conditions, which is the first step toward commercializing and integrating the cells in the Internet of Things (IoTs). IPV, being an emerging field, the study of photovoltaic parameters under varied intensity of light and different lights reveals a lot of information about the behavior of cells. Such a study has never been performed before, and the correlation between intensity and CCT of light with photovoltaic parameters and PCE unveils invaluable information about indoor OSCs. The results of this study could potentially aid in optimizing and developing OSC for self-sustaining IoTs in the near future.","PeriodicalId":445,"journal":{"name":"IEEE Journal of Photovoltaics","volume":"15 6","pages":"776-781"},"PeriodicalIF":3.7,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148485284","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

The Challenges of Accurate J0e Determination on Modern Solar Cells: A Sensitivity Study of Input Parameter Uncertainty 现代太阳能电池准确测热的挑战：输入参数不确定性的敏感性研究

IF 3.7 3区工程技术

IEEE Journal of Photovoltaics Pub Date : 2025-11-01 Epub Date: 2025-08-20 DOI: 10.1109/JPHOTOV.2025.3596620

Adrienne L. Blum;Harrison W. Wilterdink;Ronald A. Sinton

引用次数: 0

Wireless Sensor Network-Based Fault Detection and Localization for Solar Stations: An Experimental Approach 基于无线传感器网络的太阳能电站故障检测与定位：一种实验方法

IF 3.7 3区工程技术

IEEE Journal of Photovoltaics Pub Date : 2025-11-01 Epub Date: 2025-08-01 DOI: 10.1109/JPHOTOV.2025.3592680

Raouf Zerrougui;Riad Khenfer;Yacine Boussaadia;Abderrahmane Benabbas;Okba Saidani;Abderrahim Yousfi;Abdelhalim Brahimi;Massinissa Belazzoug

{"title":"Wireless Sensor Network-Based Fault Detection and Localization for Solar Stations: An Experimental Approach","authors":"Raouf Zerrougui;Riad Khenfer;Yacine Boussaadia;Abderrahmane Benabbas;Okba Saidani;Abderrahim Yousfi;Abdelhalim Brahimi;Massinissa Belazzoug","doi":"10.1109/JPHOTOV.2025.3592680","DOIUrl":"https://doi.org/10.1109/JPHOTOV.2025.3592680","url":null,"abstract":"This article introduces a wireless sensor network (WSN) system that enhances photovoltaic (PV) performance during shading through real-time fault detection and adaptive optimisation. The solution employs five strategically placed sensors and a Chipkit Max32-based algorithm that: 1) detects shading faults with 98.2% accuracy via dynamic voltage-current correlation, 2) localises faults at 95.7% precision using impedance mapping, and 3) recommends bypass actions to limit power loss. Experimental results demonstrate a 27.4% improvement in power output under shading versus conventional systems, with 1.8-s response times (60% faster than academic alternatives) at $23/node (62% cheaper than commercial optimisers). Key innovations include a hybrid series-parallel classification matrix and adaptive current weighting, which reduces false alarms by 41%. The system maintains more than 94% of the maximum power point during dynamic shading, as validated through comparative analysis with seven state-of-the-art methods. This work establishes a new standard for cost-effective, real-time PV monitoring while resolving critical WSN limitations in sensor density and shading response.","PeriodicalId":445,"journal":{"name":"IEEE Journal of Photovoltaics","volume":"15 6","pages":"886-895"},"PeriodicalIF":3.7,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148483464","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0