论文部分内容阅读
以0.33C,0.40Si,1.50Mn,0.099V(wt%)的中碳含钒微合金钢在应变速率为0.005～30 s-1、温度为750～1050℃条件下的单向热压缩变形实验数据为样本数据,用商用软件matlab6.5构建BP人工神经网络模型。经实验数据验证,该模型预测的流变应力结果可靠。研究结果表明:利用人工神经网络方法建立热变形流变应力预测模型,适用于预测一定温度与应变速率范围内(0.1～0.9)应变处的热变形流变应力,为控制轧制工艺参数提供参考。与常用的表征稳态或峰值应变处的流变应力与温度和应变速率关系的Arrhenius方程相比,应用范围更广。
Uniaxial hot compression deformation experiments of medium carbon vanadium microalloyed steels of 0.33C, 0.40Si, 1.50Mn and 0.099V (wt%) under strain rate of 0.005-30 s-1 and temperature of 750-1050 ℃ Data for the sample data, using a commercial software matlab6.5 BP artificial neural network model. The experimental data show that the model predicts the flow stress is reliable. The results show that the prediction model of flow stress in hot deformation is established by artificial neural network, which is suitable for predicting the hot deformation flow stress in the range of strain (0.1-0.9) within a certain temperature and strain rate, which can provide references for controlling the rolling process parameters . Compared with the Arrhenius equation commonly used to characterize the relationship between the flow stress at steady-state or peak strain and the temperature and strain rate, the application range is wider.