Modeling of rapidly solidified aging process of Cu-Cr-Sn-Zn alloy by an artificial neural network

This paper uses an artificial neural network (ANN) and Levenberg-Marquardt training algorithm to model the non-linear relationship between parameters of rapidly solidified aging processes and mechanical and electrical properties of Cu-Cr-Sn-Zn alloy. The predicted values of the ANN are in accordance with the testing data. A basic repository on the domain knowledge of rapidly solidified age processes is established. Rapidly solidified aging processes can greatly enhance the hardness and electrical conductivity for Cu-Cr-Sn-Zn alloy. At 500 °C for 15 min aging the hardness and conductivity can reach 170 HV and 64% IACS respectively.