改进神经网络在疲劳短裂纹演化行为中的应用  

Application of improved back-propagation neural network to short fatigue crack evolution

作　　者：王正[1] 刘建雄[1] 王璐[1] 谢伟云[1] 

机构地区：[1]大连理工大学能源与动力学院,大连116024

出　　处：《材料科学与工艺》2012年第6期45-49,55,共6页Materials Science and Technology

基　　金：国家自然科学基金资助项目(50771024)

摘　　要：为研究短裂纹演化行为中复杂的非线性动力学过程,采用改进BP神经网络算法对疲劳短裂纹的演化行为进行表征.该方法采用遗传算法优化确定神经网络的权重,同时集合BP网络算法的局部精确搜索和遗传算法的宏观搜索、全局优化特性,可以综合多个影响因素,反映其隐含的复杂非线性关系.通过对复杂应力状态下高温低周疲劳短裂纹的试验研究及疲劳短裂纹密度和裂纹扩展速率的模拟比较,表明该方法收敛速度更快、计算更精确,基于该方法建立的疲劳短裂纹演化模型合理有效.To research the complicated nonlinear dynamics process of the short crack evolution behavior,a way that improves back-propagation neural network aiming at evolution of short fatigue crack is shown in this paper.This method optimizes the weight of the BP network,and aggregates the characteristics of the local precise search of the BP network and the global optimization of the improved genetic algorithm,which integrates more factors and reflects complicated relation.Comparing the results of the experiment of short fatigue crack for low cycle under complex stress at high temperature with the simulation results of improved back-propagation neural network,it is proved that the method is feasible,accurate and converged quickly.

关 键 词：高温低周疲劳 短裂纹 改进神经网络 裂纹密度 裂纹扩展速率 

分 类 号：TB303[一般工业技术—材料科学与工程]