摘要
在变形温度为850~1150℃、应变速率为0.1~10s -1 的条件下,对Cr-Mo-B系机械工程用钢进行高温热压缩实验。基于真应力-应变曲线,建立输入参数为温度、变形速率、应变和输出参数为流变应力的人工神经网络(ANN)模型。结果表明:神经网络模型的预测精度高,其预测流变应力的均方根误差为1.3858。根据动态材料模型理论(DMM),构建并分析材料在真应变为0.5和0.7时的热加工图,确定了最佳热变形工艺参数:当真应变ε=0.5时,变形温度为1050~1150℃、应变速率为0.1~0.4s -1 区域的功率耗散因子η≥37.20%;当真应变ε=0.7时,变形温度为1000~1150℃、应变速率为0.1~0.6s -1 区域的功率耗散因子η≥35.80%。
The hot deformation behavior of Cr-Mo-B mechanical engineering steel was conducted at deformation temperature of 850-1150℃ and strain rates of 0.1-10s -1 . The artificial neural network(ANN) model was developed based on the true stress-strain curves, where the input parameters were deformation temperature, strain rate, strain, and flow stress was the output parameter. The results show that the ANN model is accurate in predicting the flow stress, and the root mean square error is 1.3858. Based on the dynamic material model (DMM), the processing maps of the studied alloy at true strains of 0.5 and 0.7 are constructed to recognize optimum hot deformation regions: the optimum region for the strain of 0.5 is at deformation temperature of 1050-1150℃ and strain rate of 0.1-0.4s -1 with a peak power dissipation factor of about 37.20%, and the optimum region for the strain of 0.7 is at deformation temperature of 1000-1150℃ and strain rate of 0.1-0.6s -1 with a peak power dissipation factor of about 35.80%.
作者
孙挺
闫永明
何肖飞
尉文超
杜玉婧
SUN Ting;YAN Yong-ming;HE Xiao-fei;YU Wen-chao;DU Yu-jing(Institute for Special Steels,Central Iron and Steel ResearchInstitute,Beijing 100081,China)
出处
《材料工程》
EI
CAS
CSCD
北大核心
2019年第9期55-60,共6页
Journal of Materials Engineering
关键词
机械工程用钢
本构模型
神经网络
热加工图
mechanical engineering steel
constitutive model
neural network
processing map
