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.
出处
《锻压技术》
CAS
CSCD
北大核心
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)
关键词
2D70铝合金
BP算法
神经网络
本构关系
热加工工艺
2D70 aluminum alloy
BP arithmetic
neural network
constitutive relationship
hot working process
