A Neural Network-assisted Theoretical Constitutive Model to Predict the High Temperature Flow Behavior of High-entropy Alloys
Metals and alloys are widely used in industry due to their excellent mechanical properties.Researchers have been continuously searching new materials with better properties or mechanisms to en-hance existing ones.In the metal and alloy forming process,hot deformation can effectively refine the grain and improve mechanical properties such as yield strength and tensile strength.Therefore,it is neces-sary to study the deformation behavior of metal and alloy materials at high temperatures.The hyperbolic-sinusoidal Arrhenius-type model has been widely used by researchers because of its good simulation effect at high temperatures.In this paper,the building process of the model is studied,and the modeling process is optimized with the help of a neural network model.A neural network model is constructed to efficiently determine the hyperbolic-sinusoidal Arrhenius-type equations,based on which the flow stress of high-en-tropy alloys(HEAs)for different high temperatures and strain rates can be well predicted.The reported hot deformation behaviors of Al0.3CoCrFeNi HEAs are examined by current model.The results show that the coefficients obtained by the neural network method can better describe the experimental hot flow stress,especially at high strain rate or low temperature conditions.The root-mean-square error(RMSE)and the correlation coefficient R are used to assess the degree of difference between the results.The RMSE and R of the neural network method at total data are 27.7 and 0.985,respectively,which are better than 33.1 and 0.979 of the traditional method.To show the general applicability of the model,the hot deforma-tion behaviors of(CoCrNi)94Ti3 Al3,FeCrCuNi2Mn2,and AlCrCuFeNi are analyzed by the model.The re-search work presented in this paper can improve the efficiency and accuracy of the hyperbolic-sinusoidal Arrhenius-type model and reduce the difficulty of establishing the model,and is of positive significance for the wide use of the model.
NETL
NSTL
万方数据
