Lightweight smoke area recognition method and system based on improved YOLO for photovoltaic factory
By improving the YOLO model and combining it with a multi-level learning architecture of visual and thermal imaging image streams, the accuracy and real-time performance issues of smoke recognition in photovoltaic plant areas were resolved, enabling accurate and reliable smoke area recognition in complex environments.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- CHINA POWER CONSTR NEW ENERGY GRP CO LTD GUIZHOU BRANCH
- Filing Date
- 2026-02-02
- Publication Date
- 2026-06-26
AI Technical Summary
In the complex and vast environment of photovoltaic plant areas, the accuracy, real-time performance and reliability of smoke area identification are low.
This paper presents a lightweight method for identifying smoke areas in photovoltaic plants based on YOLO. It utilizes a multi-level learning architecture to combine visual and thermal imaging image streams for smoke probability detection, and achieves accurate and reliable smoke area identification by monitoring attention configuration graphs and temporal dependency aggregation.
It achieves accurate, reliable, and adaptive real-time smoke identification in photovoltaic plant areas, improving identification accuracy and real-time performance, and adapting to changing weather conditions and complex environments.
Smart Images

Figure CN122289882A_ABST