Treffer: GDS-Detector: A lightweight defect detection model for solar cells.

Solar cell performance is critically dependent on structural integrity. Minor defects introduced during manufacturing or operation can significantly reduce energy conversion efficiency. Furthermore, these defects may shorten the lifespan of solar panels. To ensure efficient and stable operation, accurate and timely defect detection is essential. This paper presents GDS-Detector, a lightweight model for high-precision solar cell defect detection on edge devices. Built upon YOLOv8(You Only Look Once v8), GDS-Detector incorporates the GHGNetv2(GhostConv-HGNetv2) backbone for enhanced feature extraction and computational efficiency. The DEGCSP(DEConv-GhostNet Cross Stage Partial Block) module further improves feature capture and reduces computational cost through reparameterization. Additionally, the PSEDH optimizes parameter utilization and computational efficiency. Evaluated on the PVEL-AD dataset, GDS-Detector reduces parameters by 51.5%, GFLOPs(giga floating-point operations per second) by 39.5%, while increasing mAP(mean average precision) by 2.3% compared to YOLOv8n. Deployed on Jetson Nano, the pruned GDS-Detector achieves 27.9 FPS(frames per second), meeting real-time requirements for practical application. [ABSTRACT FROM AUTHOR]

Copyright of Energy Sources Part A: Recovery, Utilization & Environmental Effects is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)