| 초록 |
In this study, machine learning was applied to predict graphene growth pattern in chemical vapor deposition (CVD) system. At first, CVD experiments were conducted to synthesize graphene to get experimental data. Then, the morphological specifications of graphene were measured automatically by a region proposal convolutional neural network (R-CNN). Next, anartificial neural network (ANN) and a support vector machine (SVM) were used to develop surrogate models to deduce the correlation between CVD process variables and specifications. Next, graphene was created by a generative adversarialnetwork (GAN), and modified to have the same specifications as the predicted values, and placed. Finally, the generated images were colored by Pix2pix to obtain the same outlook as SEM images. As a result, it was possible to simulate graphene synthesis under various conditions. Using the developed model, the experiment condition to synthesize graphene with desired morphologies can be identified. |
