In the present invention, a random forest algorithm is applied to modeling strain and temperature-dependent flow stress in hot forming of a Ti-6Al-4V alloy, and Ti-6Al-4V can improve the accuracy of flow stress predicted by this modeling. It relates to a method for predicting the flow stress of an alloy. The present invention is a step of performing a compression experiment on the specimen of the Ti-6Al-4V alloy; Storing experimental data on the flow stress of the Ti-6Al-4V alloy; Learning a specified flow stress model among a plurality of flow stress models using the experimental data; Predicting the flow stress of the Ti-6Al-4V alloy using the learned flow stress model, and generating a predicted flow stress prediction value; And verifying the generated flow stress prediction value based on a result predicted by other flow stress models other than the specified flow stress model.
展开▼
