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

Graphical abstract of using AI models to directly predict the mechanical properties of woven composites and optimally design structures. • AI models enhance finite element simulations, reducing time and cost while improving accuracy in woven composite design. • Convolutional Neural Networks (CNN) accelerate the prediction of mechanical properties, speeding up the design process. • Deep Q-learning Networks (DQN) optimize mechanical properties, enhancing the efficiency of composite material design. • The reduced model reduces simulation time, and with DQN it enables more efficient and effective product design. 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 R 2 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/m 3 to 8527.85 J/m 3 . 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.