AI and Computational Intelligence Methods for Modeling and Optimization of Fiber-Reinforced Metal and Polymer Matrix Composites

The advancement of fiber-reinforced composites has revolutionized the design and development of high- performance materials for aerospace, automotive, and structural applications. However, the complexity of composite systems—arising from heterogeneous microstructures, multiple reinforcement mechanisms, and nonlinear mechanical behavior—poses challenges in predictive modeling and performance optimization. Recent developments in artificial intelligence (AI) and computational intelligence (CI) have enabled efficient modeling, simulation, and optimization of these materials by integrating machine learning, deep learning, and evolutionary algorithms. This study reviews and analyzes AI-driven methods applied to fiber-reinforced metal matrix composites (MMCs) and polymer matrix composites (PMCs), emphasizing data-driven prediction of mechanical, thermal, and tribological properties. The paper further explores hybrid computational models combining finite element analysis (FEA) with neural networks, genetic algorithms (GA), and fuzzy logic to achieve enhanced predictive accuracy and process parameter optimization. The proposed framework demonstrates the potential of AI–CI methods in accelerating material design cycles and optimizing composite fabrication processes with improved precision, reduced experimental cost, and higher reliability.