GMD-YOLO: A Dual-Modality Framework with Multi-Scale Enhancement and Adaptive Fusion for PV Fault Detection
Zhichao Lin, Xiuling Wang, Yuyang Guo · 2026
Read GMD-YOLO: A Dual-Modality Framework with Multi-Scale Enhancement and Adaptive Fusion for PV Fault Detection by Zhichao Lin, Xiuling Wang, Yuyang Guo (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13258882.txt.
Description
Zhichao Lin, Xiuling Wang, and Yuyang Guo combine visible and heat images to find solar panel faults in a 2026 study. Faults such as hotspots and shorted diodes cut power output and raise safety risk. Single camera methods struggle under changing light and weak heat signals.
Gradient aware fusion aligned features from both image types before detection. Accuracy rose while model size, parameter count, and computing cost all fell. Recall improved notably once a shape aware training loss was added. Separate tests on a public thermal dataset showed consistent gains. Plant operators gain a lighter inspection model that still catches more real faults.
Catalog record
| CREATOR | Zhichao Lin, Xiuling Wang, Yuyang Guo |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 82 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |