RBF神经网络在船舶焊接中的建模及应用  

Modeling and Application of RBF Neural Network to Ship-welding Process

作　　者：曹建云[1] 

机构地区：[1]南通工学院,南通226007

出　　处：《武汉理工大学学报（交通科学与工程版）》2004年第5期675-677,共3页Journal of Wuhan University of Technology（Transportation Science & Engineering）

基　　金：江苏省自然科学基金项目资助 (批准号 :BK2 0 0 3 0 3 4) ;江苏省教育厅自然科学基金项目资助 ( 0 3 KJB12 0 10 1)

摘　　要：以船舶钢结构为对象 ,研究了 RBF神经网络在船舶焊接变形中的建模及应用 .以焊接顺序等因素作为网络输入 ,以钢结构板材凹凸变形为输出 ,训练生成网络焊接变形模型 ,可用于预测船舶钢结构焊接变形量的快速预测 .仿真表明该模型的预测输出与实测数据样本基本拟合 。In this paper, by studying of ship steel structure, the modeling and applications of RBF neural network to ship-welding distortion are proposed. Factors including welding sequence being input of the network, and welding distortions being output can make the resulting network which is used for the model of welding distortion and its fast forecasting. Simulations show that the model can almost be the same as the practical situations, and its prediction has enough precision.

关 键 词：径向基函数 神经网络 焊接变形 

分 类 号：TG47[金属学及工艺—焊接]