摘要
CTOD断裂韧性是最受关注的环焊接头性能之一。本文选择了2层神经元的神经网络结构,采用S型激活函数,将板厚、预热温度、线能量、取样位置作为神经网络的输入,将环焊接头的裂纹尖端张开位移CTOD值作为网络的输出,通过BP算法的网络学习,采用VC语言建立了X70管线钢环焊接头CTOD与环焊工艺之间的神经网络。采用实验法对所建立的神经网络的可靠性进行了验证,网络的预测结果与实验值之间有很好的对应关系。
Crack - tip opening displacement is one of the most important performance for girth joint of X70 pipeline steel. In this paper, CTOD artificial neural network for girth joint of X70 pipeline steel is established by composing visual - C program. The process of establishing neural network is as follows: two- layer neuronic network configuration is selected, S - type active function is used, input parameter of network are selected for thickness, preheat temperature, heat input and sampling point, output parameter of network is selected for fracture toughness property CTOD, learning algorithm of network is used for back - propagation algorithm. Reliability standard of established neural network is proved by experiment results. The predicted results of CTOD neural network are in good agreement with experiment results.
出处
《压力容器》
北大核心
2007年第6期6-9,16,共5页
Pressure Vessel Technology
基金
中国石油天然气集团公司技术中心项目(2004-02)
关键词
X70管线钢环焊接头
裂纹尖端张开位移
神经网络
girth joint of X70 pipeline steel
crack - tip opening displacement
neural network