AI-Enabled Adaptive Process Control and Decision-Making Framework for Advanced Metal 3D Printing Systems
Metal 3D Printing, Laser Powder Bed Fusion and Directed Energy Deposition is a deal for making complex metal parts. We can make these parts with a lot of design freedom and material efficiency. Even with a lot of progress it is not widely used in industries. This is because of some problems like process instability, defects and stress buildup. Most research looks at process modeling, control and optimization. This means we do not have a system that can support autonomous manufacturing. This study proposes a framework that uses intelligence to control and make decisions for advanced metal 3D printing systems. This framework combines physics-based modeling, real-time monitoring, adaptive control and digital twin technology to make a manufacturing system. We use math to understand how heat, material and process interact during metal 3D Printing. We also use intelligence and optimization algorithms to improve accuracy, energy efficiency, surface quality and reliability of metal 3D Printing. The digital twin environment helps us predict quality detect defects and correct the process in time for metal 3D Printing. We tested our framework using metal 3D Printing machines and common engineering alloys like Ti-6Al-4V, Inconel 718 and SS316L. Our framework showed high accuracy improved surface quality, reduced energy consumption and robust process stability for metal 3D Printing. The digital twin was very accurate which means we can make decisions and optimize the process in time, for metal 3D Printing. Our results show that using intelligence, adaptive control, digital twins and data-driven optimization can greatly improve the performance and reliability of metal 3D Printing. Our framework provides a foundation for generation intelligent metal 3D printing systems that can control themselves predict quality and improve process management. This can help accelerate the use of manufacturing technologies, in aerospace, biomedical and high-performance engineering applications.
Authors
- Fasil Kebede Tesfaye (ORCID: https://orcid.org/0000-0001-8776-6786)
- Abraham Debebe Woldeyohannes (ORCID: https://orcid.org/0000-0001-7598-9915)
Institutions
- Addis Ababa Science and Technology University (ET)
Publication Details
- Journal
- International Journal of Intelligent Information Systems
- Published
- 2026-10-09
- DOI
- https://doi.org/10.11648/j.ijiis.20261503.12
- Primary Topic
- Additive Manufacturing Materials and Processes
- Type
- article
- Field-Weighted Citation Impact
- 0.00