Application of deep learning to inverse design of phase separation structure in polymer alloy
Kazuya Hiraide, Kenta Hirayama, Katsuhiro Endo, Mayu Muramatsu
Abstract
In this study, using some machine learning methods, we develop a framework that deals with forward analysis to predict a property from a polymer alloy’s phase separation structure and inverse design to generate the structure from the property. We only consider Young’s modulus as the property in this study. The forward analysis is performed using a convolutional neural network (CNN) and the inverse design is realized by a random search toward a model combining a generative adversarial network (GAN) and a CNN. This framework is applicable to other properties at a low computational cost, and latent variables belonging to the GAN are useful for feature extraction.
Topics & Concepts
InverseComputer scienceConvolutional neural networkProperty (philosophy)Generative grammarPhase (matter)Feature (linguistics)Deep learningAlloyArtificial neural networkArtificial intelligenceAlgorithmMathematical optimizationMaterials scienceMathematicsPhysicsComposite materialLinguisticsEpistemologyQuantum mechanicsGeometryPhilosophyMachine Learning in Materials ScienceHydrogen embrittlement and corrosion behaviors in metalsMicrostructure and Mechanical Properties of Steels