首页> 外文期刊>Computer Methods in Applied Mechanics and Engineering >Equivalent method of evaluating mechanical properties of perforated Ni-based single crystal plates using artificial neural networks
【24h】

Equivalent method of evaluating mechanical properties of perforated Ni-based single crystal plates using artificial neural networks

机译:人工神经网络评估多孔镍基单晶板力学性能的等效方法

获取原文
获取原文并翻译 | 示例

摘要

Creep experiments were performed to study the mechanical characteristics of Ni-based single crystal superalloy samples with densely arranged air film holes. An equivalent model based on crystallographic theory coupled with continuous damage mechanics was developed. The equivalent method was proposed, combining artificial neural networks and the equivalent solid material concept. A series of experiments and calculation results on plates with diverse arrangement patterns and ligament efficiencies were compared to validate the accuracy of the proposed method. The results indicate that the creep curves of the simplified models agree well with the experimental results. The microstructural evolution observed by scanning electron microscopy can be evaluated using the evolution of the maximum resolved shear stress with the creep time. The damage distribution of the simplified models is consistent with the crack initiation location and propagation region of samples. Additionally, the slip system actuation of the simplified models is the same as that of the experimental results. The equivalent errors of the creep time, maximum resolved shear stress and creep damage are less than 15%, except for individual points, indicating that the equivalent method proposed in this study is feasible and accurate. (C) 2019 Elsevier B.V. All rights reserved.
机译:进行蠕变实验以研究具有密集排列的气膜孔的Ni基单晶高温合金样品的机械特性。建立了基于晶体学理论和连续损伤力学的等效模型。结合人工神经网络和等效固体材料概念,提出了等效方法。比较了在具有不同排列方式和韧带效率的板上进行的一系列实验和计算结果,以验证所提出方法的准确性。结果表明,简化模型的蠕变曲线与实验结果吻合良好。可以使用最大分辨剪切应力随蠕变时间的演变来评估通过扫描电子显微镜观察到的微观结构的演变。简化模型的损伤分布与样品的裂纹萌生位置和传播区域一致。另外,简化模型的滑移系统致动与实验结果相同。除个别点外,蠕变时间,最大解析剪应力和蠕变损伤的等效误差均小于15%,这表明本研究提出的等效方法是可行和准确的。 (C)2019 Elsevier B.V.保留所有权利。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号