建立了铝合金压铸模热疲劳性能的优化神经网络模型,并对该模型进行了试验验证。结果表明,该神经网络模型的相对训练误差和相对预测误差均小于5%。经神经网络模型优化后,3Cr2W8V铝合金压铸模的热疲劳裂纹级别从15级降为8级,H13钢铝合金压铸模从12级降为4级,表明两种材料的热疲劳性能均得到提高。 An optimized neural network model of thermal fatigue properties of aluminum alloy die-casting mold was established, and the model was verified by experiments. The results show that the relative training error and the relative prediction error of the neural network model are less than 5%. After the optimization of the neural network model, the thermal fatigue crackle of 3Cr2W8V aluminum alloy die-casting mold was reduced from 15 to 8, and the aluminum alloy die-casting mold of H13 steel was reduced from 12 to 4, which indicated that the thermal fatigue properties of both materials were improved .