Multi-Head Attention-Based Feature Extractor Integration with Soft Actor-Critic for Porosity Prediction and Process Parameter Optimization in Additive Manufacturing

2026-06-18

AI Summary

This work addresses the challenge of pore defects in additive manufacturing caused by imprecise control of process parameters, a problem exacerbated by the slow convergence and susceptibility to local optima of conventional reinforcement learning methods operating in discrete action spaces. To overcome these limitations, the study proposes a novel integration of a multi-head attention mechanism into the Soft Actor-Critic (SAC) framework, leveraging continuous action space modeling to enhance the agent’s sensitivity to subtle variations in low-dimensional input features and improve the exploration–exploitation trade-off. Evaluated on a laser powder bed fusion process optimization task, the proposed method achieves a converged reward of 322.79 in only 14 training episodes, significantly outperforming DQN, PPO, TD3, and standard SAC in both convergence speed and stability within a value landscape containing local minima.

Abstract

Additive manufacturing process optimization requires precise parameter control to minimize defects such as porosity. Traditional reinforcement learning (RL) approaches using discrete action spaces suffer from slow convergence and susceptibility to local optima, limiting their effectiveness for high-precision manufacturing tasks. This study addresses these limitations by employing a continuous action space combined with a novel architecture that integrates a multi-head attention mechanism with the Soft Actor-Critic (SAC) algorithm. The attention-based feature extractor enhances the agent's ability to capture subtle variations in low-dimensional input features, enabling more effective exploration-exploitation balance for navigating value spaces with local minima. We validate our approach on porosity prediction and process parameter optimization in laser powder bed fusion, demonstrating faster convergence and higher final reward values compared to standard RL methods including DQN, PPO, TD3, and vanilla SAC. The proposed methodology achieves a convergence value of 322.79 within 14 episodes, outperforming existing approaches while maintaining stability throughout training.

Problem

• porosity prediction
• process parameter optimization
• additive manufacturing
• reinforcement learning
• continuous action space

Innovation

• Multi-Head Attention
• Soft Actor-Critic
• Continuous Action Space
• Additive Manufacturing
• Porosity Prediction