航空学报 > 2023, Vol. 44 Issue (19): 228367-228367   doi: 10.7527/S1000-6893.2023.28367

固体力学与飞行器总体设计

基于深度学习的权函数法应力强度因子求解

赵鋆赫(), 王生楠   

  1. 西北工业大学 航空学院,西安 710129
  • 收稿日期:2022-12-06 修回日期:2023-01-30 接受日期:2023-03-02 出版日期:2023-10-15 发布日期:2023-03-10
  • 通讯作者: 赵鋆赫 E-mail:3250386721@qq.com

Solution to stress intensity factor by weight function method based on deep learning

Yunhe ZHAO(), Shengnan WANG   

  1. School of Aeronautics,Northwestern Polytechnical University,Xi’an 710129,China
  • Received:2022-12-06 Revised:2023-01-30 Accepted:2023-03-02 Online:2023-10-15 Published:2023-03-10
  • Contact: Yunhe ZHAO E-mail:3250386721@qq.com

摘要:

针对传统多参考载荷条件权函数法在复杂几何构型下存在的问题,提出了一种基于深度学习的多参考载荷条件权函数法,应用该方法得到的有限矩形板单边穿透裂纹权函数解与Wu-Carlsson的解析权函数解在相应各点处的格林函数偏差在0.4%以内,验证了该方法获得的权函数的精度,证明了该方法的可行性。针对航空航天领域常见的偏心孔边裂纹情况,使用该方法得到了部分几何尺寸下的偏心孔边裂纹权函数解,与有限元法得到的格林函数值对比,绝大部分偏差小于1.5%,最大偏差为4.8%,进一步验证了该方法获得权函数解的准确性。该方法具有应用于复杂几何裂纹体的潜力。

关键词: 权函数法, 应力强度因子, 深度学习, 偏心孔边穿透裂纹, 格林函数

Abstract:

A deep-learning based multiple reference states weight function method is proposed to address the problems in traditional multiple reference states weight function method for complex geometric configurations. Comparison with the Green's functions at corresponding points of the crack surface shows that the deviation between the Green’s functions of unilateral penetrating crack at the edge of the finite width plate obtained by this method and the Wu-Carlsson analytical weight function method is within 0.4%, verifying the accuracy of the weight function obtained by this method and proving the feasibility of this method. Using this method, we derive the weight function with some geometric dimensions for the edge crack at the off-center hole on the finite plate common in the aerospace field, and compare it with the Green’s function value obtained by the finite element method. The results show that most of the deviations are smaller than 1.5%, with the maximum deviation of 4.8%, further verifying the accuracy of the weight function solution obtained by this method. The proposed method has the potential to be applied to complex geometric crack bodies.

Key words: weight function method, stress intensity factor, deep learning, crack at edge of off-center hole, Green’s function

中图分类号: