Prediction of jump-like creep using preliminary plastic strain

Abstract

There was studied a jump-like creep of AMg6 aluminum alloy on its preliminary plastic strain during the tensile test in the soft mode of loading. Experimental studies showed that the creep of AMg6 aluminum alloy is accompanied by jump-like increments of strain, the values of which are similar to the "steps" of the tensile strain. The methods of experimental studies are often complicated and time-consuming. Therefore, it is more efficient to predict the magnitude of the jump during the creep by methods of machine learning, in particular, neural networks, which show the best results. It was determined that in this case the error of neural networks method was equal to 4.8%.