Prediction and optimization of mechanical properties of composites using convolutional neural networks
This work addresses the optimization of composite materials for engineering applications, but it is incremental as it applies existing neural network and genetic algorithm methods to a specific domain problem.
The authors tackled the problem of predicting and optimizing mechanical properties of two-dimensional checkerboard composites by developing a convolutional neural network model, which accurately predicted stiffness, strength, and toughness, and integrated it with a genetic algorithm to identify optimal microstructural designs, converging to configurations with highly enhanced properties such as no soft elements for modulus and soft elements near crack tips for strength and toughness.
In this paper, we develop a convolutional neural network model to predict the mechanical properties of a two-dimensional checkerboard composite quantitatively. The checkerboard composite possesses two phases, one phase is soft and ductile while the other is stiff and brittle. The ground-truth data used in the training process are obtained from finite element analyses under the assumption of plane stress. Monte Carlo simulations and central limit theorem are used to find the size of the dataset needed. Once the training process is completed, the developed model is validated using data unseen during training. The developed neural network model captures the stiffness, strength, and toughness of checkerboard composites with high accuracy. Also, we integrate the developed model with a genetic algorithm (GA) optimizer to identify the optimal microstructural designs. The genetic algorithm optimizer adopted here has several operators, selection, crossover, mutation, and elitism. The optimizer converges to configurations with highly enhanced properties. For the case of the modulus and starting from randomly-initialized generation, the GA optimizer converges to the global maximum which involves no soft elements. Also, the GA optimizers, when used to maximize strength and toughness, tend towards having soft elements in the region next to the crack tip.