神经网络在确定裂纹尖端塑性区中的应用  

The Application of Neural Network to Determing the Plastic Zone Around the Carck Tip

作　　者：师俊平[1] 朱文艺[1] 

机构地区：[1]西安理工大学理学院,陕西西安710048

出　　处：《西安理工大学学报》2003年第4期313-316,共4页Journal of Xi'an University of Technology

基　　金：陕西省自然科学基金资助(2002A05)

摘　　要：通过构造反向传播神经网络,对裂纹尖端的应力场进行模拟,进而实现对裂纹尖端应力场函数的逼近。得到的网络具有较高的联想、记忆能力和较好的稳定性,并且可以快速、准确地计算实际中带裂纹构件的裂纹尖端应力场,从而确定裂纹尖端的塑性区和分析带裂纹构件裂纹的扩展。The stress field around the crack tip is simulated via the constructed Back-Propagation Neural Network (BPNN) whereby achieving the approximation of the stress field around the crack tip. The trained neural network is of the ability of association and memory. At the same time, it can calculate the stress field of the component with a crack in reality quickly and accurately, whereby determing the plastic zone in the crack tip and analyzing the crack expansion of the component with cracks.

关 键 词：神经网络 裂纹 应力 

分 类 号：O346.1[理学—固体力学]