A comparative study of phenomenological, physically-based and artificial neural network models to predict the Hot flow behavior of API 5CT-L80 steel

Abstract

The hot compressive deformation behavior of as-cast 5CT-L80 medium-carbon steel was investigated under the different elevated temperatures range from 1173 K to 1373 K and diverse strain rate range from 0.001 s−1 to 1 s−1. The multi-peak flow stress curves were observed during deformation, indicating a complex behavior of this steel due to metallurgical phenomena like dynamic recrystallization. Therefore, the modified Johnson-Cook (J-C) as a phenomenological model, modified Zerilli-Armstrong (Z-A) as a physically-based model, and feed-forward back propagation artificial neural network (BP-ANN) model were purposed to describe the high-temperature flow behavior of the studied material. So, the predictability of the developed models is compared by the standard statistical parameters. The extraordinary and accurate performance was observed in the BP-ANN model to predict the complexities of the compressive behavior of 5CT-L80 steel, whereas the modified J–C model has more precise than the modified Z-A model.