.png){kind=icon}
.png){kind=icon}
Return
Process Optimization with Flexible Pulse Bursts using Bayesian Optimization
.png){kind=icon}
PRE
AI
DOI：10.2961/jlmn.2026.01.2011.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
This study addresses the challenges associated with scaling ablation rates while minimizing surface roughness for copper. By employing tailored flexible bursts, the temporal spacing and energy of individual pulses can be precisely manipulated, creating a high-dimensional parameter space for optimization. Traditional optimization methods are labor-intensive and time-consuming. Thus, we propose an automated Bayesian optimization approach that integrates advanced sensors and a microservice-based software platform for real-time adjustments. Our results demonstrate a multi-objective optimization of removal rates and surface quality, achieving efficiencies of up to 0.16 mm3/minW while reducing surface roughness to as low as 0.33 & micro;m. The findings indicate that effective process optimization by Bayesian optimization is plausible, with the potential for significant advancements in laser processing design. This work underscores the importance of combining Bayesian optimization with expert knowledge to enhance research efficiency and foster further investigations into optimal laser processing conditions.
Keywords:
USP
ultrashort pulse laser
ablation
burst
Bayesian optimization
AI
artificial intelligence
Journal
J
IF:
0.9
Papers:
38
Citations:
676