摘要
基于Matlab神经网络工具箱 ,设计了一个用于结构钢焊条熔敷金属化学成分预测的神经网络模型。该模型采用前向神经网络 ,利用BP算法 ,建立了熔敷金属化学成分与力学性能之间的关系。用此神经网络 ,既可预测结构钢焊条熔敷金属化学成分 ,也为深入研究结构钢焊条化学成分提供了有利的工具。
A neural network model used in predicting the chemical components of the deposited metal is developed based on Matlab neural network toolbox. By using a back-propagation (BP) algorithm, a feed-forward neural network is employed to establish the function between the chemical component and the mechanics property of the deposited metal. With this neural network, the chemical component of the deposited metal can be predicted, which supply plenty information to study the chemical component of the deposited metal for the structura steel electrodes.
出处
《焊接》
2002年第10期23-25,共3页
Welding & Joining
