神经网络在奥氏体钢设计中的应用  

Application of Artificial Neural Network to Austenitic Steel Design

作　　者：戴起勋[1] 戴希敏[1] 

机构地区：[1]江苏理工大学

出　　处：《钢铁研究学报》1997年第6期37-40,共4页Journal of Iron and Steel Research

基　　金：机械工业技术发展基金

摘　　要：采用人工神经网络分别对奥氏体钢的相变临界点ＭＳ、ＭεＳ，力学性能和化学成分间的关系建立了非线性网络模型，并通过试验数据验证了这些模型的正确性。此方法不同于以线性回归为基础来推导得到经验公式。它具有容错性好，通用性强等优点。神经网络的应用为材料的设计与应用提供了一种较为可靠的新途径。A non linear neural network model for the phase transformation points M S and M εS , compositions and mechanical properties of austenitic steels is established. And the correctness of the model is proved by experimental data. This method is different from the traditional experiential formulas that is on the basis of linear regression. It has the advantages of good fault tolerance and generality, etc. and provides a new and reliable way for the material design and application.

关 键 词：人工神经网络 奥氏体钢 材料设计 网络模型 

分 类 号：TG142.25[一般工业技术—材料科学与工程]