Thermal Control of Laser Powder Bed Fusion using Deep Reinforcement Learning
ThermalControlLPBF-DRL
Code implementation of the paper “Thermal Control of Laser Powder Bed Fusion using Deep Reinforcement Learning”.
This repository is the implementation of the paper “Thermal Control of Laser Powder Bed Fusion Using Deep Reinforcement Learning”, linked here. The project makes use of the Deep Reinforcement Library stable-baselines3 to derive a control policy that maximizes melt pool depth consistency.
Simulation Framework
The Repeated Usage of Stored Line Solutions (RUSLS) method proposed by Wolfer et al. is used to simulate the temperature dynamics in this work. More detail can be found in the following paper:
- Fast solution strategy for transient heat conduction for arbitrary scan paths in additive manufacturing, Additive Manufacturing, Volume 30, 2019 (link)
Prerequisites
The following packages are required in