Abstract
To automatically reconstruct the prior austenite grains from as-quenched martensitic structure, we applied a deep learning algorithm to recognize the prior austenite grains boundaries hidden in the martensitic matrix. The FC-DenseNet architecture based on FCN (fully convolutional networks) was used to train the martensite and ground truth label of the..... More

Abstract
Al-Mg-Si alloy was rolled asymmetrically at several temperatures to apply shear deformation, and the effects of the initial precipitate on shear deformation, texture evolution, formability, and plastic anisotropy were studied. Texture was analyzed using a EBSD, and the formability and plastic anisotropy of the specimen were evaluated using the value..... More

Abstract
The methane reduction (MR) of SnO₂ has been proposed as a highly efficient method for recovering Sn from SnO₂ containing industrial wastes. The MR of SnO₂ also produces a mixture of H₂ and CO, which can be further utilized as a syngas for the production of various fuels through the..... More