Integrating Machine Learning into Additive Manufacturing of Metallic Biomaterials: A Comprehensive Review.

Abstract

The global increase in osteomuscular diseases, particularly bone defects and fractures, has driven the growing demand for metallic implants. Additive manufacturing (AM) has emerged as a transformative technology for producing high-precision metallic biomaterials with customized properties, offering significant advantages over traditional manufacturing methods. The integration of machine learning (ML) with AM has shown great promise in optimizing the fabrication process, enhancing material performance, and predicting long-term behavior, particularly in the development of orthopedic implants and vascular stents. This review explores the application of ML in AM of metallic biomaterials, focusing on four key areas: (1) component design, where ML guides the optimization of multi-component alloys for improved mechanical and biological properties; (2) structural design, enabling the creation of intricate porous architectures tailored to specific functional requirements; (3) process control, facilitating real-time monitoring and adjustment of manufacturing parameters; and (4) parameter optimization, which reduces costs and enhances production efficiency. This review offers a comprehensive overview of four key aspects, presenting relevant research and providing an in-depth analysis of the current state of ML-guided AM techniques for metallic biomaterials. It enables readers to gain a thorough understanding of the latest advancements in this field. Additionally, the this review addresses the challenges in predicting in vivo performance, particularly degradation behavior, and how ML models can assist in bridging the gap between in vitro tests and clinical outcomes. The integration of ML in AM holds great potential to accelerate the design and production of advanced metallic biomaterials.