论文部分内容阅读
利用Gleeble 3500热模拟试验机,对Ti2248合金的试样进行压缩试验,获得了不同变形温度、应变速率和真应变下的流动应力数据。根据实验数据和神经网络理论,建立BP神经网络。结果表明,该BP神经网络模型具有很高预测精度,误差均在5%以内,可很好预测Ti2448合金在高温变形过程中不同参数对流变应力的影响。
Using Gleeble 3500 thermal simulator, the compressive tests of Ti2248 alloy were carried out, and the flow stress data under different deformation temperature, strain rate and true strain were obtained. According to the experimental data and neural network theory, BP neural network is established. The results show that the BP neural network model has high prediction accuracy and the errors are within 5%, which can predict the effect of different parameters on the flow stress of Ti2448 alloy under high temperature deformation.