Papers
11
Total Citations
93
H-Index
5
About
Shogo Yamane is a pioneering researcher in intelligent robotic welding systems, specializing in the fusion of neural networks, fuzzy logic, and visual sensing to achieve high-quality weld control. His major contributions center on developing real-time methods to sense and control the weld pool—particularly its penetration depth and back bead formation—which are critical for producing defect-free joints. In his most-cited work (35 citations), he proposed a neural network-based approach to estimate weld pool depth indirectly, overcoming the challenge of direct real-time measurement. He further advanced the field by integrating fuzzy-neural networks and neuro arc sensors to simultaneously control torch attitude, seam tracking, and bead geometry in narrow-gap and multi-layer welding. His innovative "switch back welding method" enabled stable back bead formation in one-side welding, a key achievement for thick material joining. With over 90 combined citations across his top papers, Yamane’s work has laid the foundation for intelligent, autonomous welding robots that adapt to changing conditions, significantly improving weld quality and reliability in industrial applications.
Research Focus
Key Achievements
Top Papers
- 1Neural network and fuzzy control of weld pool with welding robot35 citations · 2002
- 2
- 3Sensing and digital control of weld pool with visual welding robot8 citations · 2002
- 4Controlling of torch attitude and seam tracking using neuro arc sensor7 citations · 2002
- 5
- 6Intelligent cooperative control system in visual welding robot5 citations · 2002
- 7Detecting and tracking of welding line in visual plasma robotic welding4 citations · 2014
- 8
- 9
- 10Neuro‐fuzzy control of the weldpool in pulsed MIG welding3 citations · 1995