Jing Zhu
Papers
1
Total Citations
4
H-Index
1
About
Jing Zhu is a researcher at the forefront of nuclear safety and intelligent robotics, with a primary focus on developing advanced detection and automation systems for hazardous environments. Their most cited work introduces S-YOLOv5s, a lightweight deep learning model designed for real-time dust detection and cleanliness assessment on nuclear power plant (NPP) reactor containment walls. This innovation addresses a critical safety gap: wall-climbing cleaning robots previously operated blindly, risking incomplete removal of radioactive dust that endangers staff and the environment. By integrating ShuffleNetV2 into YOLOv5s, Zhu’s approach enables efficient, accurate detection even in constrained computational settings, achieving 4 citations since 2024. This contribution not only enhances robotic autonomy in high-risk nuclear facilities but also sets a precedent for applying computer vision to contamination control. Zhu’s work stands out for its practical impact, directly improving occupational safety and environmental protection in the nuclear industry. Their research bridges robotics, deep learning, and nuclear engineering, offering a scalable solution for cleaner, safer reactor maintenance.
Research Focus
Key Achievements
Top Papers
- 1