Aging Properties Prediction of the Lead Frame Cu-Cr-Sn-Zn Alloy via Neural Network

The aging process of lead frame Cu-Cr-Sn-Zn alloy has only been studied empirically by trial-and-error method so far. This paper builds up the prediction model of the aging properties via a supervised artificial neural network(ANN) to model the non-linear relationship between parameters of aging process with respect to hardness and electrical conductivity properties of the alloy. The improved model is developed by the Levenberg- Marquardt training algorithm. The predicted values of the ANN coincide with the tested data. So the ANN system is effective and successful for predicting and analyzing the properties of Cu-Cr-Sn-Zn alloy. The optimized processing parameters are available at 475 C ° -520 C ° aging for 2h-1h.