Multi-Head Attention-Based Feature Extractor Integration with Soft Actor-Critic for Porosity Prediction and Process Parameter Optimization in Additive Manufacturing
A new research paper introduces an enhanced Soft Actor-Critic (SAC) algorithm for additive manufacturing. This approach integrates a multi-head attention mechanism to improve the agent's ability to identify subtle feature variations, leading to more effective parameter optimization and defect prediction, specifically for porosity in laser powder bed fusion. The study demonstrates that this novel architecture achieves faster convergence and higher rewards compared to standard reinforcement learning methods like DQN, PPO, and TD3, reaching a convergence value of 322.79 within 14 episodes. AI
IMPACT Enhances precision and efficiency in additive manufacturing processes by improving defect prediction and parameter optimization.