| Abstract Scope |
Artificial intelligence (AI) and machine learning (ML) are increasingly being used to improve the reliability and performance of additive manufacturing (AM) by establishing direct links between process parameters, thermal behavior, microstructural evolution, and mechanical properties. However, conventional trial-and-error approaches still dominate many AM workflows, resulting in long development cycles and limited process stability. This work presents an AI-enabled modeling and simulation framework aimed at improving process control, minimizing defect formation, and enhancing microstructural consistency across metallic, ceramic, and polymer-based AM systems. Key applications such as real-time process monitoring, melt pool behavior prediction, parameter optimization, and digital twin development are discussed to highlight practical implementation pathways. Deep learning approaches for analyzing in-situ sensor data and microstructural characterization outputs are also emphasized. Remaining challenges related to data availability, model robustness, and interpretability are addressed, along with future directions toward physics-informed ML and closed-loop autonomous manufacturing systems. |