Predicting Flow Stress Behavior of an AA7075 Alloy Using Machine Learning Methods

The present work focuses on the prediction of hot deformation behavior thermo-mechanically processed precipitation hardenable aluminum alloy AA7075. data considered focus a novel forming process at different tool temperatures ranging from 24?C to 350?C set cooling rates after solution heat-treatment. Isothermal uniaxial tensile tests in temperature range 200?C 400?C and strain 0.001 s?1 0.1 were carried out four material conditions. paper mainly comparative study modeling techniques based Machine Learning (ML) Zerilli–Armstrong model (Z–A) as reference. Related predicting single points curves that was trained on. Due way split with respect training testing data, it is possible predict entire stress–strain curves. allows decrease number required laboratory experiments, eventually saving costs time future experiments. While all investigated ML methods showed higher performance than Z–A model, extreme Gradient Boosting (XGB) superior results, i.e., highest error reduction 91% Mean Squared Error.