Artificial intelligence design algorithm for nanocomposites optimized for shear crack resistance

CH Yu and Z Qin and MJ Buehler, NANO FUTURES, 3, UNSP 035001 (2019).

DOI: 10.1088/2399-1984/ab36f0

Here we report a design approach for optimizing the toughness of nanocomposite materials using artificial intelligence (AI), implemented in a novel 'AutoComp Designer' algorithm. The algorithm consists of a machine learning predictor combined with an AI improved genetic algorithm, which is capable of discovering de novo materials designs in a vast space of possible solutions. Facilitated by a deep convolutional neural network that is trained with a dataset of hundreds of thousands of combinations of soft and brittle materials originating from a finite element analysis, we predict the material properties of novel graphene nanocomposites without running conventional simulations. Through the algorithm, we extend the capability of physical simulations beyond property predictions to optimize the fracture toughness by altering the material distribution. The solutions are generated by our AI model at a dramatically lower computational cost compared to brute-force searching methods. We further investigate the physical mechanism for improving material performance behind the AI approach, and demonstrate the ability of AI to search for optimal designs with very limited sampling. Brute- force molecular dynamics simulations of the nanocomposite designs confirm that our AI design improves the performance by effectively decreasing the stress concentration at the crack tip. This AI approach can be easily applied to other nanocomposites, biomaterials, and other material classes, and provides a transferable and reliable rapid design approach expanding current capabilities.

Return to Publications page