Acquiring the constitutive relationship for a thermal viscoplastic material using an artificial neural network

Prediction of nickel-base superalloys’ rheological behaviour under hot forging conditions using artificial neural networks

“…[8,9]. However, even if some applications of neural networks to predict metals flow stress have been proposed in the last years [6,7,10,11], very few studies are recordable in scientific literature that utilise neural networks to describe material behaviour under varying hot deformation conditions. Material response in terms of flow strength or microstructure is predicted in case of well-defined deformation conditions, mainly single-step deformation conditions; but, even if these operative conditions are near to those of conventional rheological testing, they can be very different from those of industrial hot forging operations [1,2].…”

“…dependence on previous histories is needed. They can represent an alternative tool to describe material behaviour as the knowledge a priori of the phenomena and their interactions during forging is not needed when used to represent rheological data [5][6][7]. Recently, this technique has been applied to many areas where modelling is too complex and highly non-linear, as in several areas of manufacturing-process planning, process monitoring and control, tool design, etc.…”

Coupling of scales in a multiscale simulation using neural networks

“…Essentially, there are two major fields of application; ANN's can be used to identify model parameters or to simulate the material itself. The first approach is expedient if the parameter identification of complex material models is not easily obtained from experimental data [1][2][3][4][5]. Especially, if some material parameters do not have a physical meaning as e.g.…”

An artificial neural network approach to multiphase continua constitutive modeling

“…Ghaboussi demonstrated the effectiveness of ANNs by accurately predicting the strain increments of plain concrete in a biaxial state of stress from inputs comprising current stress and strain states as well as the stress increments. ANNs have been utilized in other non-linear constitutive modeling research such as finding the flow stress in different materials given only the parameters of temperature, effective strain, and effective strain rate [9][10][11][12][13].…”