Dynamic Extruder Speed Control in Large Format Additive Manufacturing via EAPPO

Abstract

Large Format Additive Manufacturing (LFAM) utilizes a fused filament fabrication technique, where an extruder continuously deposits melted thermoplastic material layer by layer. Since the temperature of the base layer significantly impacts the quality of the final product, dynamically controlling the extruder’s speed becomes essential, as it enables precise temperature management, ultimately enhancing both efficiency and product quality. To effectively control the extruder speed, it is essential to understand the thermodynamic behavior of the part’s surface during printing. This paper employs a Transformer architecture to analyze the spatiotemporal relationships among cooling profiles across different locations on the part’s surface, providing accurate temperature predictions. Previous methods largely relied on nonlinear mixed-integer programming (MIP) for extruder speed control. However, when practical factors such as extruder acceleration are considered, these models often become unsolvable or computationally prohibitive. This paper addresses this challenge by training an agent with the environment-aware Proximal Policy Optimization (EAPPO) algorithm in a custom-designed environment that simulates the LFAM printing process. This setup enables the agent to iteratively explore the feasible region to identify an optimal solution. The proposed approach is validated in a hexagon case study, with results showing it can find better solutions when MIP fails in complex scenarios, thereby improving printing efficiency and quality.