人工神经网络在硼钢淬透性预测中的应用  

Application of Artificial Neural Network in Prediction of Boron Steel Hardenability

作　　者：刘晓燕[1] 赵西成[1] 姚筱春[1] 

机构地区：[1]西安建筑科技大学冶金工程学院,陕西西安710055

出　　处：《热加工工艺》2004年第10期20-21,23,共3页Hot Working Technology

基　　金：陕西省自然科学研究计划资助项目(2002E111);陕西省教育厅专项基金资助项目(03JK134)

摘　　要：根据收集和整理的实验数据,建立了硼钢的化学成分与其淬透性之间的非线性人工神经网络模型,用这种方法预测了一些硼钢的端淬值和淬透性曲线,并与用其它经验公式计算的结果进行了比较。结果表明:所建网络能较准确预测硼钢淬透性,这为研究硼钢淬透性提供了一种有效的方法。A non-linear neural network model used to study the relationship between hardenability and chemical composition of boron steel was established using data collected from domestic literature.Top quench values and the hardenability curves of some boron steel were predicted by using the network and compared with those acquired from other methods.The results show that the hardenability of boron steel can be predicted more accurately using artificaial neural network.The neural network provides an effective method for studying boron steel hardenability.

关 键 词：人工神经网络 硼钢 淬透性 

分 类 号：TG115.61[金属学及工艺—物理冶金]