Rapid application of neural networks and a genetic algorithms to solidified aging processes for copper alloy

Rapidly solidified aging is an effective way to refine the microstructure of Cu-Cr-Sn-Zn lead frame alloy and enhance its hardness. The artificial neural network methodology (ANN) along with genetic algorithms were used for data analysis and optimization. In this paper the input parameters of the artificial neural network (ANN) are the aging temperature and aging time. The outputs of the ANN model are the hardness and conductivity properties. Some explanations of these predicted results from the microstructure and precipitation-hardening viewpoint are given. After the ANN model is trained successfully, genetic algorithms (GAs) are applied for optimizing the aging processes parameters.