基于人工神经网络的铜合金时效性能预测
Property Prediction of Aged Copper Alloys Based on Artificial Neural Network
-
摘要: 通过对BP神经网络算法分析和收敛性的运用,对获得的时效实验数据进行训练,建立了Cu-0.30Cr-0.15Zr合金硬度和导电性与时效时间和时效温度的映射模型,从而可预测铜合金在一定时效条件下的硬度和导电性。结果表明,神经网络用于铜合金的时效性能预测是可行的。Abstract: A prediction model for aging properties of copper alloys(Cu-0.30Cr-0.15Zr) based on BP artificial neural net is developed and the non-linear relationship between alloys hardness, alloys conductivity and aging time, aging temperature is established. Hardness and conductivity performances of copper alloys can be predicted by means of the trained neural net from the aging data. The results show that the model is suitable for the property prediction of aged copper alloys.