.png){kind=icon}
.png){kind=icon}
Return
Multi-pass cutting parameters optimisation with causal reinforcement learning for deformation control of thin-walled parts
.png){kind=icon}
PRE
AI
F
G
C
F
M
DOI：10.1016/j.rcim.2026.103317.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Revealing causalities among parameters, machining states and workpiece quality. • Proposing a CRL-driven dynamic framework for cutting-parameter optimisation. • Developing a shared CGAT in CRL that makes the agent’s exploration interpretable. • The proposed method is well suited to manufacturing with high accuracy demands.
Keywords:
causal reinforcement learning
cutting parameter optimisation
thin-walled parts
deformation control
shared CGAT
Journal
R
IF:
11.4
Papers:
3.3K
Citations:
1.3W
Organization
Cited Papers