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

Modelling of the rheological behaviour of aluminium alloys in multistep hot deformation using the multiple regression analysis and artificial neural network techniques

“…In the ANNbased approach, a multi-layer feed forward ANN, using the back-propagation algorithm, was built [2,3]. Nine inputs were chosen, closely related to the process parameters of multistep deformation [3,9]: T, ε,ε, t p , ε p , ln ε, lnε, 1/T and D 0 , where D 0 is the initial grain size [3]. The outputs of the ANN were the flow stress, in terms of envelope curve through the flow curve maxima of each pass, and the flow stress as logarithmic function.…”

“…Since the restoration mechanisms taking place during each deformation step and between two succeeding steps are related to the thermo-mechanical history of the deforming material, the hot working behaviour must be investigated under multistep deformation conditions. To this purpose, laboratory tests, such as compression and torsion tests [1][2][3], allow the analysis, for each deformation step, of the influence of the process parameters, such as temperature, strain and strain rate, time between two succeeding steps, etc. on both the rheological behaviour and microstructure [1].…”

“…An artificial neural network (ANN) solves a problem by learning rather than by a specific programming based on well-defined rules [2,[9][10][11][12]. Many researchers applied the ANN-based models to predict flow curves in a single step deformation on several materials [2,3,9,13], whilst a limited number of applications concerning the prediction of the stress-strain curves in multistep deformation can be found, mainly in two-steps compression tests [3].…”

FRICTION MODELING OF Al-Mg ALLOY SHEETS BASED ON MULTIPLE REGRESSION ANALYSIS AND NEURAL NETWORKS

“…For instance, application of ANN allowed them to find the relationships between the value of the surface roughness parameters and real contact area under the different friction conditions [19]. Many researchers applied the ANN models to predict flow curves in a single step deformation on several materials [3]. An ANN may solve problems by learning rather than by a specific programming based on well-defined rules [9].…”

Corrosion resistance of the polymer matrix hard magnetic composite materials Nd–Fe–B

“…The growing popularity of neural networks is due their ability to model relations between investigated variables with no need to know the physical model of the phenomena. The results provided by neural networks very often exhibit better correlation with experimental data than those obtained from empirical explorations or mathematical models of the processes under investigation [17][18][19][20][21][22][23].…”