论文部分内容阅读
在Gleeble-1500热模拟机上进行热变形压缩试验,获得了NiTi形状记忆合金在不同应变速率和温度下的真应力-真应变实验数据及微观组织,根据实验数据基于BP神经网络建立模型对NiTi合金的高温变形进行预测。结果表明:随着应变速率的增加,TiNi合金的软化特性变得明显,模型的预测值与试验值误差较小,且预测精度和可靠度高。
The thermal deformation compressive tests on Gleeble-1500 thermal simulator were carried out to obtain the true stress-true strain experimental data and microstructure of NiTi shape memory alloy under different strain rates and temperatures. Based on the experimental data, the model was established based on BP neural network to simulate the NiTi alloy Of the high temperature deformation prediction. The results show that with the increase of strain rate, the softening properties of TiNi alloy become obvious. The prediction error of the model is less than the experimental value, and the prediction accuracy and reliability are high.