A multivariable empirical model, based on an artificial neural network (ANN), was developed to predict flow curves of ZAM100 magnesium alloy sheets as a function of process parameters in hot forming conditions. Tensile tests were performed in a wide range of temperature and strain rate to collect the dataset used in the training and testing stages of the network. The generalization ability of the model was tested using both the leave-one-out cross-validation method and flow curves not belonging to the training set. The excellent fitting between experimental and predicted curves was proven the very good predictive capability of the model.
Flow curve prediction of ZAM100 magnesium alloy sheets using artificial neural network-based models
El Mehtedi, MohamadPrimo
;
2019-01-01
Abstract
A multivariable empirical model, based on an artificial neural network (ANN), was developed to predict flow curves of ZAM100 magnesium alloy sheets as a function of process parameters in hot forming conditions. Tensile tests were performed in a wide range of temperature and strain rate to collect the dataset used in the training and testing stages of the network. The generalization ability of the model was tested using both the leave-one-out cross-validation method and flow curves not belonging to the training set. The excellent fitting between experimental and predicted curves was proven the very good predictive capability of the model.File | Dimensione | Formato | |
---|---|---|---|
1-s2.0-S2212827119301659-main.pdf
accesso aperto
Descrizione: paper online
Tipologia:
versione editoriale (VoR)
Dimensione
967.19 kB
Formato
Adobe PDF
|
967.19 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.