Prediction of amorphous forming ability based on artificial neural network and convolutional neural network

Using a trial and error method to measure amorphous forming ability in the experiment is a complex and timeconsuming process. Therefore, it is necessary to devise a method that can rapidly and accurately predict the amorphous forming ability. In this study, two models, artificial neural network and convolutional neural network, are proposed for the prediction of amorphous forming ability of various amorphous alloys. The prediction accuracy of the two models reached 0.77623 and 0.71693, respectively, both of which were more than 19% higher than the reported prediction accuracy of the 13 criteria. This result shows that artificial neural network and convolutional neural network models can accurately predict the amorphous forming ability of a variety of amorphous alloys and provide theoretical guidance for the development and preparation of amorphous alloys.