Reinforcement Learning on Reconfigurable Hardware: Overcoming Material Variability in Laser Material Processing
This work addresses automation and optimization in laser processes for industries like manufacturing, though it is incremental as it applies an existing RL paradigm to a specific hardware and domain problem.
The paper tackled the challenge of inconsistent laser processing quality due to material variability by developing a real-time reinforcement learning method on reconfigurable hardware, achieving up to 23% better performance on rougher surfaces compared to hand-engineered strategies.
Ensuring consistent processing quality is challenging in laser processes due to varying material properties and surface conditions. Although some approaches have shown promise in solving this problem via automation, they often rely on predetermined targets or are limited to simulated environments. To address these shortcomings, we propose a novel real-time reinforcement learning approach for laser process control, implemented on a Field Programmable Gate Array to achieve real-time execution. Our experimental results from laser welding tests on stainless steel samples with a range of surface roughnesses validated the method's ability to adapt autonomously, without relying on reward engineering or prior setup information. Specifically, the algorithm learned the correct power profile for each unique surface characteristic, demonstrating significant improvements over hand-engineered optimal constant power strategies -- up to 23% better performance on rougher surfaces and 7% on mixed surfaces. This approach represents a significant advancement in automating and optimizing laser processes, with potential applications across multiple industries.