基于人工神经网络与遗传算法的Al-Mg-Si系合金抗拉强度预测模型

为了研究Al-Mg-Si系合金热处理制度和合金成分对力学性能的影响规律，采用人工神经网络（artificial neural network, ANN）和遗传算法（genetic algorithm, GA）相结合的方法，构建了Al-Mg-Si系合金强度预测模型（ANN-GA模型）。通过单因素和双因素分析，研究了合金元素含量和热处理工艺参数对铝合金抗拉强度的影响规律。结果表明，随着Si含量的增加，铝合金的抗拉强度呈现先降低后升高的趋势；随着Mg含量的增加、Cu含量的增加或者Fe含量的减少，铝合金的抗拉强度整体上呈现升高的趋势。双因素分析更能反映输入参数对铝合金抗拉强度的影响。Mg/Si比、Mg+Si总量和时效时间对Al-Mg-Si系合金力学性能的影响显著。铝合金的硬度随时间的变化趋势与ANN-GA模型的计算结果一致，峰值时效时间为29 h，相对误差为11.86%。

Prediction model of tensile strength of Al-Mg-Si alloy based on artificial neural network and genetic algorithm

In order to study the effect of heat treatment system and alloy composition on the mechanical properties of Al-Mg-Si alloys, the strength prediction model (ANN-GA model) of Al-Mg-Si alloys was constructed by using the combination of artificial neural network (ANN) and genetic algorithm (GA). The effects of alloying element content and heat treatment process parameters on the strength of aluminum alloy were studied by single factor and double factor analysis. The results show that the tensile strength of aluminum alloy decreases first and then increases with the increase of Si content; With the increase of Mg content, the increase of Cu content or the decrease of Fe content, the tensile strength of aluminum alloy increases as a whole. Two factor analysis can better reflect the influence of input parameters on the tensile strength of aluminum alloy. Mg/Si ratio, total amount of Mg+Si and aging time have significant effects on the mechanical properties of Al-Mg-Si alloys. The variation trend of hardness of aluminum alloy with time was consistent with the calculation results of ANN-GA model. The peak aging time was 29h and the relative error was 11.86%.