In order to address the challenges posed by complex background interference,high miss-detection rates of micro-scale defects,and limited model deployment efficiency in photovoltaic(PV)module defect detection,this pape...In order to address the challenges posed by complex background interference,high miss-detection rates of micro-scale defects,and limited model deployment efficiency in photovoltaic(PV)module defect detection,this paper proposes an efficient detection framework based on an improved YOLOv11 architecture.First,a Re-parameterized Convolution(RepConv)module is integrated into the backbone to enhance the model’s sensitivity to fine-grained defects—such as micro-cracks and hot spots—while maintaining high inference efficiency.Second,a Multi-Scale Feature Fusion Convolutional Block Attention Mechanism(MSFF-CBAM)is designed to guide the network toward critical defect regions by jointly modeling channel-wise and spatial attention.This mechanism effectively strengthens the specificity and robustness of feature representations.Third,a lightweight Dynamic Sampling Module(DySample)is employed to replace conventional upsampling operations,thereby improving the localization accuracy of small-scale defect targets.Experimental evaluations conducted on the PVEL-AD dataset demonstrate that the proposed RMDYOLOv11 model surpasses the baseline YOLOv11 in terms of mean Average Precision(mAP)@0.5,Precision,and Recall,achieving respective improvements of 4.70%,1.51%,and 5.50%.The model also exhibits notable advantages in inference speed and model compactness.Further validation on the ELPV dataset confirms the model’s generalization capability,showing respective performance gains of 1.99%,2.28%,and 1.45%across the same metrics.Overall,the enhanced model significantly improves the accuracy of micro-defect identification on PV module surfaces,effectively reducing both false negatives and false positives.This advancement provides a robust and reliable technical foundation for automated PV module defect detection.展开更多
The hybrid photovoltaic solar-assisted heat pump are primarily used to generate electricity and provide thermal energy for heating applications.This study investigates the performance enhancement of a hybrid Photovolt...The hybrid photovoltaic solar-assisted heat pump are primarily used to generate electricity and provide thermal energy for heating applications.This study investigates the performance enhancement of a hybrid Photovoltaic Thermal Solar-Assisted Heat Pump(PV/T-SAHP)system integrated with a solar tracking mechanism.The system was simulated using TRNSYS to evaluate its monthly electrical output and coefficient of performance(COP)of the heat pump system over a year.The results showed a significant improvement in energy generation and efficiency compared to a conventional PV/T system without SAHP system.Overall,the solar tracking configuration of the PV/T-SAHP generated 10%–40%more electricity than the fixed system.The system for the tracking mode achieved a maximum monthly average electrical energy output of 634.349 kWh in June.Throughout the year,the tracking mode consistently outperformed the fixed mode.During the winter months of January and December,the tracking system produced 328.7 and 323.6 kWh,respectively,compared to 297.8 and 299.7 kWh for the fixed mode.The highest COP of 5.65 occurred in July,indicating a strong seasonal correlation with solar irradiance.In contrast,the minimum COP of 4.55 was observed in the months,February and March,reflecting reduced solar availability.The solar tracking feature consistently maintained an optimal panel angle,increasing energy gains and improving system efficiency.Overall,the integration of a heat pump and tracking control significantly improved system performance,making the hybrid PV/T-SAHP configuration a promising solution for year-round renewable energy generation.展开更多
Optimizing photovoltaic(PV)power utilization in battery systems is challenging due to solar intermittency,battery efficiency,and lifespan management.This paper proposes a novel forecast-based battery charging manageme...Optimizing photovoltaic(PV)power utilization in battery systems is challenging due to solar intermittency,battery efficiency,and lifespan management.This paper proposes a novel forecast-based battery charging management(BCM)strategy to enhance PV power utilization.A string of Li-ion battery cells with diverse capacities and states of charge(SOC)is contemplated in this constant current/-constant voltage(CC/CV)battery-charging scheme.Significant amounts of PV power are often wasted because the CC/CV mode cannot fully exploit the available power to maintain appropriate charging rates.To address this issue,the proposed BCM algorithm selects an optimal set of battery cells for charging at any given time based on forecasted PV power generation,ensuring maximum power is obtained from the PV system.Additionally,a support vector regression(SVR)-based forecasting model is developed to predict PV power generation precisely.The results indicate that the anticipated BCM strategy achieves an overall utilization rate of 87.47%of the PVgenerated power for battery charging under various weather conditions.展开更多
基金supported by the Gansu Provincial Department of Education Industry Support Plan Project(2025CYZC-018).
文摘In order to address the challenges posed by complex background interference,high miss-detection rates of micro-scale defects,and limited model deployment efficiency in photovoltaic(PV)module defect detection,this paper proposes an efficient detection framework based on an improved YOLOv11 architecture.First,a Re-parameterized Convolution(RepConv)module is integrated into the backbone to enhance the model’s sensitivity to fine-grained defects—such as micro-cracks and hot spots—while maintaining high inference efficiency.Second,a Multi-Scale Feature Fusion Convolutional Block Attention Mechanism(MSFF-CBAM)is designed to guide the network toward critical defect regions by jointly modeling channel-wise and spatial attention.This mechanism effectively strengthens the specificity and robustness of feature representations.Third,a lightweight Dynamic Sampling Module(DySample)is employed to replace conventional upsampling operations,thereby improving the localization accuracy of small-scale defect targets.Experimental evaluations conducted on the PVEL-AD dataset demonstrate that the proposed RMDYOLOv11 model surpasses the baseline YOLOv11 in terms of mean Average Precision(mAP)@0.5,Precision,and Recall,achieving respective improvements of 4.70%,1.51%,and 5.50%.The model also exhibits notable advantages in inference speed and model compactness.Further validation on the ELPV dataset confirms the model’s generalization capability,showing respective performance gains of 1.99%,2.28%,and 1.45%across the same metrics.Overall,the enhanced model significantly improves the accuracy of micro-defect identification on PV module surfaces,effectively reducing both false negatives and false positives.This advancement provides a robust and reliable technical foundation for automated PV module defect detection.
文摘The hybrid photovoltaic solar-assisted heat pump are primarily used to generate electricity and provide thermal energy for heating applications.This study investigates the performance enhancement of a hybrid Photovoltaic Thermal Solar-Assisted Heat Pump(PV/T-SAHP)system integrated with a solar tracking mechanism.The system was simulated using TRNSYS to evaluate its monthly electrical output and coefficient of performance(COP)of the heat pump system over a year.The results showed a significant improvement in energy generation and efficiency compared to a conventional PV/T system without SAHP system.Overall,the solar tracking configuration of the PV/T-SAHP generated 10%–40%more electricity than the fixed system.The system for the tracking mode achieved a maximum monthly average electrical energy output of 634.349 kWh in June.Throughout the year,the tracking mode consistently outperformed the fixed mode.During the winter months of January and December,the tracking system produced 328.7 and 323.6 kWh,respectively,compared to 297.8 and 299.7 kWh for the fixed mode.The highest COP of 5.65 occurred in July,indicating a strong seasonal correlation with solar irradiance.In contrast,the minimum COP of 4.55 was observed in the months,February and March,reflecting reduced solar availability.The solar tracking feature consistently maintained an optimal panel angle,increasing energy gains and improving system efficiency.Overall,the integration of a heat pump and tracking control significantly improved system performance,making the hybrid PV/T-SAHP configuration a promising solution for year-round renewable energy generation.
文摘Optimizing photovoltaic(PV)power utilization in battery systems is challenging due to solar intermittency,battery efficiency,and lifespan management.This paper proposes a novel forecast-based battery charging management(BCM)strategy to enhance PV power utilization.A string of Li-ion battery cells with diverse capacities and states of charge(SOC)is contemplated in this constant current/-constant voltage(CC/CV)battery-charging scheme.Significant amounts of PV power are often wasted because the CC/CV mode cannot fully exploit the available power to maintain appropriate charging rates.To address this issue,the proposed BCM algorithm selects an optimal set of battery cells for charging at any given time based on forecasted PV power generation,ensuring maximum power is obtained from the PV system.Additionally,a support vector regression(SVR)-based forecasting model is developed to predict PV power generation precisely.The results indicate that the anticipated BCM strategy achieves an overall utilization rate of 87.47%of the PVgenerated power for battery charging under various weather conditions.
