Yujie Zeng
Papers
3
Total Citations
48
H-Index
2
About
Yujie Zeng’s research focuses on intelligent power grid inspection, combining computer vision, deep learning, and robotics to enhance the safety and efficiency of transmission line maintenance. His major contributions lie in addressing the critical challenge of insufficient fault image data for transmission line components. He pioneered a synthetic dataset generation method paired with an improved YOLOv5 architecture, achieving a breakthrough in fault detection accuracy—his 2024 paper on this topic has already garnered 37 citations, reflecting its immediate impact. Zeng further advanced the field by integrating depth-attention mechanisms into YOLOv5 for more robust fitting recognition in complex environments, and he developed a three-dimensional path-following control method using an improved line-of-sight algorithm for a novel flying–walking power line inspection robot. His work directly tackles real-world operational hurdles, such as misdetections and robot instability during line landing. With a growing citation record and a focus on deployable AI-driven solutions, Zeng is establishing himself as a key innovator in autonomous power infrastructure monitoring.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3