Application of constitutive and neural network models for prediction of high temperature flow behavior of Al/Mg based nanocomposite

作者：Senthilkumar V^*; Balaji A; Arulkirubakaran D

来源：Transactions of Nonferrous Metals Society of China, 2013, 23(6): 1737-1750.

DOI：10.1016/S1003-6326(13)62656-4

• hot compression
• Johnson-Cook (JC) model
• Modified Zerilli-Armstrong (ZA) model
• Arrhenius (AR) hyperbolic model
• flow stress
• nanocomposite

To predicate the high temperature flow behavior of Al/Mg based nanocomposite, constitutive models such as general flow, Arrhenius hyperbolic, Johnson-Cook(JC) and modified Zerilli-Armstrong (ZA) models, and artificial neural network(ANN) models were developed using stress-strain data collected from hot compression tests carried at different strain rates (0.01-1.0 s(-1)) and temperatures (523, 623 and 723 K). The validity of the models developed was tested using statistical parameters such as root mean square error (RMSE), regression coefficient (R-2), mean relative error (MRE) and scattered index (I-s). A comparison between ANN and different constitutive models shows that the ANN model has a higher accuracy in estimating the flow stress during hot deformation of AA5083/2%TiC nanocomposite.

• 出版日期2013-6