Abstract In this paper, an efficient stress recovery technique is presented to estimate the recovered stress field at the nodal points. The feed–forward back–propagation multilayer perceptron (MLP) neural network approach is employed to improve the accuracy of the stress recovery method. An automatic adaptive mesh refinement is performed based on a–posteriori Zienkiewicz–Zhu error estimation method. The proposed technique is employed to recover the stress field accurately in the regions with a high stress gradient where the conventional recovery techniques are not able to improve the stress fields efficiently due to the singular behavior of problem. Finally, several numerical examples are solved to demonstrate the efficiency and accuracy of the proposed computational algorithm. The results are compared with the conventional methods, including the averaging method, superconvergent patch recovery (SPR) technique, and weighted superconvergent patch recovery (WSPR) method that illustrates how the artificial neural network can be used accurately to recover the stress field.

中文翻译：

---

一种基于人工神经网络的自适应有限元方法中的有效应力恢复技术

摘要 本文提出了一种有效的应力恢复技术来估计节点处的恢复应力场。采用前馈反向传播多层感知器 (MLP) 神经网络方法来提高应力恢复方法的准确性。基于后验 Zienkiewicz-Zhu 误差估计方法执行自动自适应网格细化。所提出的技术用于在具有高应力梯度的区域中准确地恢复应力场，由于问题的奇异行为，传统恢复技术无法有效地改善应力场。最后，解决了几个数值例子，以证明所提出的计算算法的效率和准确性。结果与常规方法比较，