Optimization of aging treatment in lead frame copper alloy by intelligent technique

An intelligent technique of artificial neural networks combined with genetic algorithms is developed for the analysis and optimization of the correlation between heat treatment parameters and properties in Cu-Cr-Sn-Zn lead frame alloy. A supervised artificial neural network (ANN) to model the nonlinear relationship between parameters of aging treatment with respect to hardness and conductivity properties was proposed for the alloy. The ANN sub-model improved by the Levenberg-Marquardt training algorithm has good generalization performance. Genetic algorithms (GAs) are used to optimize the input parameters of aging temperature and time. The verifying experiment has shown that the theoretical optimization agrees with the experimental evidence.