Predicting Austenite Yield Strength in Steels by using Artificial Intelligence

The accurate control of austenite hot deformation requires reliable prediction of yield strength in order to design thermomechanical treatments to optimize the final properties of steels. This has motivated extensive efforts to develop predictive models in the past. Such models have demonstrated good accuracy, but their applicability has been limited to narrow compositional ranges or inaccurate evolution with temperature, largely constrained by the scope of the databases used for calibration. Therefore, when tested against broader datasets encompassing wider temperature and compositional variations, these models exhibit significant deviations. Moreover, strain rate—an influential factor in mechanical behavior—has often been overlooked in earlier approaches. In this study, we present a more comprehensive and robust model that incorporates strain rate effects and extends the compositional and temperature ranges. By integrating physical based methods and artificial intelligence architectures, the model presented significantly enhances the accuracy of yield strength prediction.