Ai-driven optimization of woven composite via integrated deep and reinforcement learning

Abstract

Woven carbon fiber composites are increasingly adopted in advanced structural applications due to their exceptional strength-to-weight ratio and tunable design features. However, high-fidelity simulations of their complex woven architecture are computationally intensive. This study presents a hybrid deep learning framework that combines a dual-input Convolutional Neural Network (CNN) for mechanical property prediction with a Deep Q-Network (DQN) for reinforcement learning-based optimization. The CNN achieves R² values above 0.96 for elastic deformation, plastic deformation, and strain energy density prediction. Using the DQN, the optimized design achieves a 2.37-fold improvement in strain energy density, increasing from 3590.78 J/m³ to 8527.85 J/m³. Furthermore, by replacing the original woven geometry with a reduced model using stress–strain behavior, simulation time is reduced from 534 min to 2 min, a 267-fold speedup. This approach significantly enhances efficiency in composite design and optimization workflows, enabling rapid exploration of high-performance configurations.