Papers
2
Total Citations
3
H-Index
1
About
Peilin Han is a researcher at the forefront of intelligent power equipment diagnostics, specializing in computer vision, deep learning, and non-destructive inspection for high-voltage transformers. Their major contributions lie in developing advanced image-enhancement and segmentation models to detect internal insulation defects—specifically carbon traces—within oil-immersed and metal-enclosed transformers. Han’s work addresses the critical challenge of visually inspecting sealed transformers by integrating micro-robotic platforms with cutting-edge AI algorithms. Notably, their 2024 paper introduced an improved MSRCR image-enhancement algorithm combined with the YOLOv8 model for carbon-trace detection, while their 2025 study proposed DCMC-UNet, a novel segmentation model featuring dynamic feature fusion and adaptive illumination enhancement. Although recent, these publications have already garnered citations, signaling growing impact in the field. Han’s research bridges robotics and deep learning, offering practical solutions for predictive maintenance and safety in power systems. Their innovative approach to automating internal transformer inspections is paving the way for more reliable, AI-driven condition monitoring in the energy sector.
Research Focus
Key Achievements
Top Papers
- 1
- 2