灰色理论与神经网络在形状记忆合金热变形行为中的应用  

Application of Grey Theory and BP Neural Network in Hot Deformation Behavior of Ni-Ti Shape Memory Alloy

作　　者：刘春茂[1] 王俊京[1] 王宏颖[2] 

机构地区：[1]河南工业职业技术学院计算机学院,河南南阳473009 [2]河南工业职业技术学院机械工程学院,河南南阳473009

出　　处：《铸造技术》2015年第2期334-336,共3页Foundry Technology

摘　　要：在传统BP神经网络预测模型基础上,分析了各个因素的灰色关联度权值,建立了基于灰色理论和BP神经网络的Ni-Ti形状记忆合金热变形行为的预测模型。结果表明,仿真数据的相对误差都位于-3%~3%,最小误差仅为0.94%。实验值和预测值的相关性高达0.9971,与传统BP神经网络的预测精度相比大为提高。The grey correlative degree weights of all input factors was analyzed basing on traditional BP neural network model, and then the prediction model of the hot deformation behavior of Ni-Ti shape memory alloy was established basing on grey theory and BP neural network. The results show that the relative error of the simulation data is in the scale of-3% -3%, and the minimum error is only 0.94%. The correlation between experimental and predicted values is as high as 0.9971, and the prediction accuracy is greatly improved compared with traditional BP neural network.

关 键 词：灰色理论 BP神经网络 NI-TI形状记忆合金 热变形 

分 类 号：TG139.6[一般工业技术—材料科学与工程]