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.
参考文献
| [1] | 徐强,张幸红,韩杰才,赫晓东,潘伟.人工神经网络在材料科学中的应用与展望[J].材料科学与工艺,2005(04):352-356. |
| [2] | 陈新,黄洪钟,孙道恒,于兰峰,姚新胜.应用神经网络的疲劳裂纹演化规律的描述[J].铁道学报,2000(03):33-37. |
| [3] | 刘长虹,陈虬,丁宇,翁金堂.疲劳短裂纹扩展中的混沌现象[J].大型铸锻件,2001(03):10-11,14. |
| [4] | 王璐,王正,于淼.高温低周疲劳表面短裂纹合体与干涉行为的实验研究及数值模拟[J].机械强度,2008(04):642-646. |
- 下载量()
- 访问量()
- 您的评分：
-
10%
-
20%
-
30%
-
40%
-
50%