论文部分内容阅读
以球磨转速、球磨时间、热等静压保温温度、热等静压保压时间、退火温度和退火时间共6个主要工艺参数作为输入层参数,以抗弯强度和冲击韧性作为输出参数,构建了高钒冷作模具钢粉末冶金工艺优化神经网络模型,并对优化工艺下的模具钢进行了测试。结果表明,该模型具有较好的预测能力和较高的预测精度,经神经网络工艺优化后高钒冷作模具钢的室温抗弯强度和冲击韧性分别达3486MPa、12J。
Six main process parameters including ball milling speed, ball milling time, hot isostatic pressing temperature, hot isostatic pressing time, annealing temperature and annealing time were taken as input layer parameters and flexural strength and impact toughness were taken as output parameters to construct High vanadium cold work die steel powder metallurgy process optimization neural network model, and the optimization of the mold steel was tested. The results show that the model has better predictive ability and higher prediction accuracy. The flexural strength and impact toughness of high vanadium cold work die steel optimized by neural network technology are 3486MPa and 12J at room temperature respectively.