基于BP神经网络的方法,建立了长期时效下GH4169合金动态拉伸行为研究的神经网络模型。实验表明,在应变速率为101、102s-1时,GH4169合金的力学性能受时效时间影响显著,在应变速率为103s-1时,时效时间对其力学性能无明显影响。采用BP神经网络模型的预测结果与真实实验测试结果吻合度很高,绝对误差比大多为1%～2%,采用BP神经网络的方法是切实可行的。 Based on the BP neural network method, a neural network model of dynamic tensile behavior of GH4169 alloy under long-term aging was established. The experimental results show that the mechanical properties of GH4169 alloy are significantly affected by the aging time at the strain rates of 101 and 102s-1. The aging time has no significant effect on the mechanical properties at the strain rate of 103s-1. The results of BP neural network model are in good agreement with the real experimental results and the absolute error ratio is mostly 1% -2%. It is practicable to adopt BP neural network method.