Shengfeng Chen
Papers
3
Total Citations
144
H-Index
3
About
Shengfeng Chen is a leading researcher in intelligent robotic welding and industrial vision inspection, with a focus on automating quality control in manufacturing. His major contributions lie in developing computer vision and deep learning methods for real-time weld joint recognition, classification, and positioning. Notably, his 2021 work on universal fillet weld joint recognition using structured light has garnered 83 citations, establishing a foundational approach for robotic welding automation. Chen further advanced the field in 2022 by integrating modified YOLOv5 for automatic weld type classification and tacked spot recognition, a paper cited 56 times for its practical impact on improving welding efficiency. Beyond welding, Chen has applied stereo vision and grid pattern projection to measure the flatness of platform screen door system assemblies for subway infrastructure, addressing critical safety and installation requirements. His research bridges the gap between theoretical computer vision and industrial application, offering scalable solutions for precision manufacturing. Chen’s work is highly regarded for its direct relevance to smart factories and has influenced subsequent studies in automated welding and non-destructive testing.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3