论文部分内容阅读
基于BP神经网络研究了NB-TiAl合金的高温变形。通过热压缩试验,获得了在不同温度和流动速率下的真应力-真应变数据。采用BP神经网络法,对试验数据进行训练。训练结果表明,试验值与预测值的误差小,训练精度高,模型可靠度好,可使用于研究NB-TiAl合金的其他金属性能。
The high temperature deformation of NB-TiAl alloy was studied based on BP neural network. The true stress-true strain data at different temperatures and flow rates were obtained by hot compression test. BP neural network method is used to train the experimental data. The training results show that the error between the experimental value and the predicted value is small, the training precision is high and the reliability of the model is good. It can be used to study other metal properties of NB-TiAl alloy.