Machine Learning for Additive Manufacturing of Functionally Graded Materials.

Area of Science:

• Materials Science and Engineering
• Manufacturing Technology
• Artificial Intelligence

Background:

• Additive Manufacturing (AM) enables direct fabrication of complex parts from 3D data.
• Functionally Graded Materials (FGMs) offer tailored properties by transitioning between materials.
• FGMs hold significant potential for enhancing component performance in various industries.

Purpose of the Study:

• To comprehensively review the literature on Machine Learning (ML) implementation in AM.
• To focus on ML-based methods for optimizing FGMs fabrication processes.
• To explore ML's role in addressing challenges in FGMs production.

Main Methods:

• Extensive survey of published literature on ML in AM for FGMs.
• Analysis of ML applications in parameter optimization for FGMs.
• Review of ML techniques for defect detection and real-time monitoring in AM.

Main Results:

• ML techniques are increasingly applied to overcome inherent challenges in FGMs fabrication.
• ML aids in optimizing process parameters, improving defect detection, and enabling real-time monitoring.
• The integration of ML enhances the potential of AM for producing advanced FGMs.

Conclusions:

• ML offers powerful tools for advancing the fabrication of Functionally Graded Materials using Additive Manufacturing.
• Further research is needed to address challenges and unlock the full potential of ML-based AM for FGMs.
• ML-driven optimization is crucial for realizing the benefits of FGMs in industrial applications.