# Prediction and optimization of mechanical properties of composites using convolutional neural networks

## TL;DR

This paper presents a CNN-based model to accurately predict the mechanical properties of checkerboard composites and integrates it with a genetic algorithm to optimize microstructural designs for enhanced properties.

## Contribution

The study introduces a novel CNN model for predicting composite properties and combines it with a genetic algorithm for microstructure optimization, demonstrating high accuracy and effective design convergence.

## Key findings

- CNN accurately predicts stiffness, strength, and toughness.
- Genetic algorithm finds optimal microstructures with enhanced properties.
- Optimizer converges to configurations with no soft elements for modulus.

## Abstract

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.