A novel multimodal feature fusion convolutional neural network to predict the mechanical properties of magnesium alloys

Abstract

A novel multimodal feature fusion convolutional neural network (MFFCNN) model, based on the combined effects of texture, grain size, and grain morphology, is established to predict the mechanical properties of AZ31 alloys. Utilizing an image-based approach, texture is reconstructed and further optimized with a reconstruction coefficient, n. When n = 41, the model has strong predictive capabilities for tensile yield strength, ultimate tensile strength, and elongation, achieving goodness of fit (R2) values of approximately 0.95, 0.94, and 0.90, respectively. Therefore, this model offers new insights into quantitatively analyzing the microstructure-property relationship of Mg alloys.