摘要
熔模铸造过程中,由于铸件的不均匀收缩而难以确定模具的尺寸。采用三坐标测量仪测量铸件和蜡模尺寸、工业CT测量型壳内腔尺寸。分析了熔模铸造过程中铸件不同部位的尺寸变化,并根据铸件和模具尺寸建立了基于BP神经网络的几何参数与径向收缩率之间的预测模型。结果表明:该模型可以很好地预测筒形铸件的径向收缩率,预测值与实测值的平均偏差为0.000 4%。
It is difficult to determine the size of the mould due to the uneven shrinkage of the casting during investment casting.The dimensions of casting and wax were measured by using coordinate measuring machine(CMM),and the cavity dimensions of shell were measured by using industrial computed tomography(CT).The dimensional change in different parts of casting during investment casting was analyzed, and the prediction model of geometric parameters and radial shrinkage rate based on BP neural network was established according to the size of casting and mould.The results showed that the model could well predict the shrinkage rate of cylindrical casting,and the average deviation between the predicted and actual shrinkage rate was 0.000 4%.
作者
冯岚
刘阳
余建波
王龙
任忠鸣
FENG Lan;LIU Yang;YU Jianbo;WANG Long;REN Zhongming(School of Materials Science and Engineering,Shanghai University,Shanghai 200444,China;State Key Laboratory of Advanced Special Steel,Shanghai 200444,China;School of Electrical Engineering,Shenyang Polytechnic College,Shenyang Liaoning 110045,China)
出处
《上海金属》
CAS
2022年第1期88-92,共5页
Shanghai Metals
基金
上海市人才发展资金资助
国家自然科学基金(No.51701112)
上海市科研计划项目(No.19DZ1100704)
上海市科技人才计划(No.19YF1415900)
上海市启明星计划(No.20QA1403800)。
关键词
熔模铸造
神经网络
收缩率
预测模型
investment casting
neural network
shrinkage rate
prediction model