| About this Abstract |
| Meeting |
2024 Annual International Solid Freeform Fabrication Symposium (SFF Symp 2024)
|
| Symposium
|
2024 Annual International Solid Freeform Fabrication Symposium (SFF Symp 2024)
|
| Presentation Title |
Reinforcement Learning for Energy-Efficient Toolpath Generation in Additive Manufacturing |
| Author(s) |
George Edem Duke, David Kolawole Somade, Niechen Chen |
| On-Site Speaker (Planned) |
George Edem Duke |
| Abstract Scope |
Toolpath design can significantly impact this Additive Manufacturing process’s efficiency. Traditional toolpath optimization methods frequently depend on empirical methods, which may not adequately account for the complex dynamics of the printing process. This study introduces a novel synergy of Reinforcement Learning (RL) algorithms to optimize toolpath design, specifically aiming to reduce energy consumption. In this work, a custom-built environment is developed to simulate the toolpath planning scenario as a discrete grid space where an agent, the printing nozzle, learns to navigate optimally. Utilizing Proximal Policy Optimization (PPO), a state-of-the-art RL algorithm, the reinforcement learning agent dynamically interacts with the simulated environment, learning to navigate complex geometries while adhering to energy constraints implemented using a custom energy model. Ultimately, the energy efficiency of the toolpath generated would be analyzed by comparing its energy consumption to that of traditional toolpath generation algorithms. |
| Proceedings Inclusion? |
Definite: Post-meeting proceedings |