Artificial Intelligence in the Design and Optimization of Laminated FRP Composites: A Review of Methodologies and Applications

The growing adoption of laminated fiber-reinforced polymer (FRP) composites in aerospace, automotive, and civil engineering demands advanced design methodologies capable of navigating their complex anisotropic behavior. While traditional design approaches rely heavily on iterative simulations and classical optimization, recent advances in artificial intelligence (AI) offer a transformative alternative. This review systematically examines the expanding role of AI in composite design and optimization—highlighting a critical transition from physics-based modeling to data-driven, intelligent frameworks. This paper emphasizes emerging AI paradigms not yet widely covered in the composite literature, including Explainable AI (XAI) for interpretable decision-making and Large Language Models (LLMs) for automating design synthesis and knowledge retrieval. Key findings demonstrate AI’s capacity to efficiently optimize stacking sequences, ply orientations, and manufacturing parameters while satisfying multi-objective constraints such as weight, stiffness, and damage tolerance. Furthermore, we explore AI’s integration across the composite lifecycle—from surrogate-assisted finite element analysis and uncertainty-aware design allowables to in-service structural health monitoring. By bridging the gap between computational intelligence and industrial practicability, this review underscores AI’s potential not as a supplementary tool, but as a foundational technology poised to redefine next-generation composite engineering.