Selective Laser Sintering of Polymers: Process Parameters, Machine Learning Approaches, and Future Directions

Abstract

Selective laser sintering (SLS) is a bed fusion additive manufacturing technology that facilitates rapid, versatile, intricate, and cost-effective prototype production across various applications. It supports a wide array of thermoplastics, such as polyamides, ABS, polycarbonates, and nylons. However, manufacturing plastic components using SLS poses significant challenges due to issues like low strength, dimensional inaccuracies, and rough surface finishes. The operational principle of SLS involves utilizing a high-power-density laser to fuse polymer or metallic powder surfaces. This paper presents a comprehensive analysis of the SLS process, emphasizing the impact of different processing variables on material properties and the quality of fabricated parts. Additionally, the study explores the application of machine learning (ML) techniques—supervised, unsupervised, and reinforcement learning—in optimizing processes, detecting defects, and ensuring quality control within SLS. The review addresses key challenges associated with integrating ML in SLS, including data availability, model interpretability, and leveraging domain knowledge. It underscores the potential benefits of coupling ML with in situ monitoring systems and closed-loop control strategies to enable real-time adjustments and defect mitigation during manufacturing. Finally, the review outlines future research directions, advocating for collaborative efforts among researchers, industry professionals, and domain experts to unlock ML’s full potential in SLS. This review provides valuable insights and guidance for researchers in regard to 3D printing, highlighting advanced techniques and charting the course for future investigations.