.png){kind=icon}
.png){kind=icon}
Return
Dynamic bead width control in robotic wire arc additive manufacturing: A machine learning approach
.png){kind=icon}
PRE
AI
N
A
A
DOI：10.1016/j.cirpj.2026.05.015.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• An ML-assisted control system is proposed to improve bead width control in WAAM. • Travel speed is predicted online by proposed ML models to achieve the target widths. • Mean pixel intensity as an added input to the model enhances prediction performance. • Control system adapts to dynamic targets with an average processing time of ∼100 ms. • Near-net shape turbine blade profile is demonstrated using the proposed system.
Journal
IF:
5.4
Papers:
283
Citations:
4.8K
Organization
No organization information available
Cited Papers