A PV cell defect detector combined with transformer and attention
This paper presents a novel PV defect detection algorithm that leverages the YOLO architecture, integrating an attention mechanism and the Transformer module.
This paper presents a novel PV defect detection algorithm that leverages the YOLO architecture, integrating an attention mechanism and the Transformer module.
The vast size of existing models causes issues in meeting recognition needs, which led to the invention of a compact target detection algorithm based on YOLOv10, named CEMP-YOLOv10n,
In this study, an innovative approach was adopted to visualize and analyze the performance of the YOLOv8s model in photovoltaic (PV) panel fault detection through heat maps
Transfer learning is introduced, and a training method involving freezing and unfreezing the model is employed to enhance the network''s ability to detect small target defects. The proposed
Solar photovoltaic panel defect detection is an important part of solar photovoltaic panel quality inspection. Aiming at the problems of chaotic distribution of defect targets on photovoltaic panels,
In this article, a novel defect detection method for photovoltaic (PV) panels is proposed by improving the YOLOv8 baseline model. The research speci fically addresses the challenges in accurately detecting
Based on the experiences of the aforementioned researchers and the summary of existing photovoltaic module defect detection methods, this paper proposes ST-YOLO, specifically
This work introduces new effective methodologies for the detection, analysis, and classification of diverse defects that may occur throughout the production process of photovoltaic panels
To objectively assess the effectiveness of our proposed method for photovoltaic panel defect detection, we conducted both quantitative and qualitative comparisons against established...
To tackle these issues, a new machine-learning model will be presented. This model can accurately identify and categorize defects by analyzing various fault types and using electrical and
PDF version includes complete article with source references. Suitable for printing and offline reading.