基于BP神经网络的2D70铝合金本构关系模型  

Model of constitutive relationship for 2D70 aluminum alloy based on BP neural network

作　　者：鲁世强[1] 周细林[1] 王克鲁[1] 李鑫[1] 赵为纲[1] 

机构地区：[1]南昌航空大学材料科学与工程学院,江西南昌330063

出　　处：《锻压技术》2008年第1期148-151,共4页Forging & Stamping Technology

基　　金：江西省材料科学与工程中心基金资助项目(ZX200601002)

摘　　要：利用Thermecmastor-Z型热加工模拟试验机对2D70铝合金进行等温恒应变速率压缩试验,获得了不同变形温度、不同应变速率和不同真应变下的流动应力数据。结合实验数据和神经网络知识,建立了具有BP算法的人工神经网络,训练结束后的神经网络即成为2D70铝合金的一个知识基的本构关系模型。误差分析表明,该神经网络本构关系模型具有较高的精度,可用于指导2D70铝合金热加工工艺的制定,并可用于2D70铝合金热变形过程的有限元模拟。Isothermal and constant strain rate compression tests on 2D70 aluminum alloy were conducted by using Thermecmastor-Z simulator, and the flow stress datas were obtained at different temperatures and strain rates for various true strains. Based on the experimental data and network knowledge, an artificial neural network with back propagation algorithm was established and knowledge based constitutive relations model was developed after training. Error analysis shows that the artificial neural network model for constitutive relationship has higher predicted precision, and it can be used for guiding the hot working process and applied in finite element simulation of 2D70 aluminum alloy.

关 键 词：2D70铝合金 BP算法 神经网络 本构关系 热加工工艺 

分 类 号：TG115.53[金属学及工艺—物理冶金]