基于均匀设计的神经网络预测焊条熔化特性  

THE MELTING CHARACTERISTICS PREDICTION OF THE ELECTRODE COVER OF ANN BASED ON THE UNIFORM DESIGN

作　　者：胡连海[1] 任德亮[1] 许昌玲[1] 孙继友[2] 

机构地区：[1]石家庄铁道学院材料科学与工程分院,050043 [2]中国南车集团石家庄车辆厂,050000

出　　处：《焊接》2006年第2期66-70,共5页Welding & Joining

基　　金：石家庄市科学技术研究与发展计划项目(04108491A)

摘　　要：利用VB语言开发了均匀设计软件并进行配方均匀设计试验,对神经网络模型的建立进行了详细的研究,用均匀设计的样本对建立的预测纤维素型焊条熔化特性的人工神经网络模型进行训练,试验结果表明:该模型可根据药皮成分对焊条熔化特性进行较为准确的预测。The uniform designed software was developed using the Visual Basic language and the uniform designed experiments were carried out in this paper. The development of the neural network model was comprehensively analyzed. The artificial neural netmodel for predicting the melting characteristics of the cellulose electrode was trained using the uniform design samples. The resuits show that the model can exactly predict the melting characteristics according to the composition of the dectrode coating.

关 键 词：纤维素型焊条 熔化特性 人工神经网络 

分 类 号：TQ460.6[化学工程—制药化工] TQ336.1