Artificial neural network modelling to predict hot deformation behaviour of zinc–aluminium alloy

Abstract

Isothermal hot compression of ZA27 alloy was conducted on a Gleeble-1500 thermomechanical simulator in the temperature range of 473-523 K with strain rates of 0?01-5 s 21 and height reduction of 60%. Based on the experimental results, an artificial neural network (ANN) model with a backpropagation learning algorithm was developed for the description and prediction of the hot deformation behaviour. The inputs of the model are temperature, strain rate and strain. The output of the model is the flow stress. Then, a comparative evaluation of the trained ANN model and the constitutive equations was carried out. It was found that the trained ANN model was more efficient and accurate in predicting the hot deformation behaviour of ZA27 alloy.

New constitutive model for high-temperature deformation behavior of inconel 718 superalloy

“…Lin and Chen [1] presented a critical review on the development of constitutive descriptions for metals and alloys under hot working in recent years, and the constitutive models are divided into three categories, including the phenomenological , physically-based [47][48][49][50][51][52][53][54][55] and artificial neural network models [56][57][58][59][60]. Considering the effects of strain on material constants, Lin et al [18] proposed a modified Arrhenius model to describe the hot deformation behavior of 42CrMo steel at elevated temperatures by the compensation of strain and strain rate.…”

“…Based on the classical stress-dislocation relation and the kinetics of dynamic recrystallization, the constitutive equations were established to describe the work hardening, dynamic recovery and dynamical recrystallization behavior of 42CrMo steel [48], TiAl alloy [49,50], commercial purity (CP) titanium [51], 4340 steel [52], and a typical nickel-based superalloy (GH4169) [53]. Additionally, neural network models were developed to predict the flow stresses of alloy steels [54,55], titanium alloys [56,57], and aluminum alloys [58,59]. Besides, some internal variable thermo-mechanical constitutive models have been proposed or modified in recent years.…”

Constitutive behaviour in as quenched Al–5Cu–0·4Mn alloy during hot deformation

“…Recently, artificial neural network (ANN) model has been widely used in describing the constitutive behaviour and the mechanical properties of materials. [9][10][11][12] The ANN method is capable of treating the non-linear problems, which is superior to the empirical or semiempirical constitutive model. As far as the constitutive behaviour of materials is concerned, the ANN has the capability to predict the flow stress through self-organisation without taking the deformation mechanisms into account.…”