| Abstract: |
Functionally graded materials (FGMs) manufactured through additive manufacturing (AM) technologies represent a paradigm shift in high-performance engineering applications. This research investigates the integration of artificial intelligence (AI) optimization techniques with metal additive manufacturing processes to produce functionally graded metallic components with enhanced mechanical properties. The study employs machine learning algorithms, specifically neural networks and genetic algorithms, to optimize process parameters including laser power, scanning speed, layer thickness, and powder composition gradients in Ti-6Al-4V and Inconel 718 alloy systems. Experimental validation through selective laser melting (SLM) demonstrates that AI-optimized parameters reduce porosity by 43% and improve tensile strength by 27% compared to conventional manufacturing approaches. Microstructural analysis reveals superior grain refinement and compositional homogeneity in AI-processed specimens. The methodology integrates real-time sensor data with predictive modeling to achieve optimal material gradation profiles. Results indicate significant improvements in fatigue life (38% increase) and thermal resistance for aerospace and biomedical applications. This research establishes a comprehensive framework for AI-driven additive manufacturing of FGMs, demonstrating substantial potential for next-generation high-performance engineering solutions. |
