Detecting Microstructural Criticality/Degeneracy through Hybrid Learning Strategies Trained by Molecular Dynamics Simulations

Abstract

Efficient microstructure design can strongly accelerate the development of materials. However, the complexity of the microstructure–behavior relation renders the criticalities and degeneracies within the microstructure space highly possible. Criticality means that a slight microstructural change can lead to a dramatic transition in material behavior, while degeneracy means that very different microstructures may lead to similar behaviors. To investigate these microstructural characteristics of the fiber/matrix interface within composite materials, we have proposed a hybrid deep-learning-based framework by integrating the supervised feed-forward neural network and the unsupervised autoencoder, which are trained by the molecular dynamics (MD) simulation results. The well-trained model continuously maps the elemental density images within the interfacial area into a low-dimensional latent space. Assisted by the extracted latent features, we can easily detect the criticalities and degeneracies within the original microstructure space of the composite’s interface. The predicted microstructural criticalities and degeneracies are validated by investigating their atomistic origins through MD simulations. The proposed framework can be employed for the interfacial microstructure design of composite materials by identifying certain interfacial microstructures that might lead to undesirable behaviors.

Artificial Intelligence in Predicting Mechanical Properties of Composite Materials

“…The current research demonstrates that implementing active learning reduces the amount of data required to effectively cover microstructure-property spaces. To investigate the microstructure-behavior characteristics of the fiber-matrix interface in composite materials, Chen and Xu [138] developed a hybrid deep-learning-based method by combining an unsupervised auto-encoder with a feedforward ANN. By employing molecular dynamics simulations, a hybrid learning strategy was able to successfully identify the degeneracies present within the original microstructural space of the composite's interface.…”

Investigation of the Dislocation Density of NiCr Coatings Prepared Using PVD–LMM Technology

“…Molecular dynamics simulations may be used to analyze the evolution of the dislocations resulting from LMM treatment. Indeed, many studies addressing the evolution of the crystals and defects of materials in complex environments have been carried out based on molecular dynamics simulations, and the simulation results have been verified via experiments [19][20][21][22][23][24][25][26][27][28].…”