当前位置: X-MOL 学术Comput. Methods Appl. Mech. Eng. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
A recurrent neural network-accelerated multi-scale model for elasto-plastic heterogeneous materials subjected to random cyclic and non-proportional loading paths
Computer Methods in Applied Mechanics and Engineering ( IF 6.9 ) Pub Date : 2020-09-01 , DOI: 10.1016/j.cma.2020.113234
Ling Wu , Van Dung Nguyen , Nanda Gopala Kilingar , Ludovic Noels

Abstract An artificial Neural Network (NNW) is designed to serve as a surrogate model of micro-scale simulations in the context of multi-scale analyses in solid mechanics. The design and training methodologies of the NNW are developed in order to allow accounting for history-dependent material behaviors. On the one hand, a Recurrent Neural Network (RNN) using a Gated Recurrent Unit (GRU) is constructed, which allows mimicking the internal variables required to account for history-dependent behaviors since the RNN is self-equipped with hidden variables that have the ability of tracking loading history. On the other hand, in order to achieve accuracy under multi-dimensional non-proportional loading conditions, training of the RNN is achieved using sequential data. In particular the sequential training data are collected from finite element simulations on an elasto-plastic composite RVE subjected to random loading paths. The random loading paths are generated in a way similar to a random walking in stochastic process and allow generating data for a wide range of strain-stress states and state evolution. The accuracy and efficiency of the RNN-based surrogate model is tested on the structural analysis of an open-hole sample subjected to several loading/unloading cycles. It is shown that a similar accuracy as with a FE 2 multi-scale simulation can be reached with the RNN-based surrogate model as long as the local strain state remains in the training range, while the computational time is reduced by four orders of magnitude.

中文翻译:

受随机循环和非比例加载路径影响的弹塑性异质材料的递归神经网络加速多尺度模型

摘要 人工神经网络 (NNW) 被设计为在固体力学多尺度分析的背景下作为微尺度模拟的替代模型。开发了 NNW 的设计和培训方法,以便考虑与历史相关的材料行为。一方面,构建了一个使用门控循环单元 (GRU) 的循环神经网络 (RNN),它允许模拟解释历史相关行为所需的内部变量,因为 RNN 自我配备了隐藏变量,这些变量具有跟踪加载历史的能力。另一方面,为了在多维非比例加载条件下达到准确率,RNN 的训练是使用序列数据来实现的。特别是,连续训练数据是从受到随机加载路径的弹塑性复合材料 RVE 上的有限元模拟中收集的。随机加载路径的生成方式类似于随机过程中的随机游走,并允许为各种应变-应力状态和状态演变生成数据。基于 RNN 的替代模型的准确性和效率在经受多次加载/卸载循环的裸眼样品的结构分析中得到测试。结果表明,只要局部应变状态保持在训练范围内,基于 RNN 的代理模型就可以达到与 FE 2 多尺度模拟相似的精度,同时计算时间减少四个数量级. 随机加载路径的生成方式类似于随机过程中的随机游走,并允许为各种应变-应力状态和状态演变生成数据。基于 RNN 的替代模型的准确性和效率在经受多次加载/卸载循环的裸眼样品的结构分析中得到测试。结果表明,只要局部应变状态保持在训练范围内,基于 RNN 的代理模型就可以达到与 FE 2 多尺度模拟相似的精度,同时计算时间减少四个数量级. 随机加载路径的生成方式类似于随机过程中的随机游走,并允许为各种应变-应力状态和状态演变生成数据。基于 RNN 的替代模型的准确性和效率在经受多次加载/卸载循环的裸眼样品的结构分析中得到测试。结果表明,只要局部应变状态保持在训练范围内,基于 RNN 的代理模型就可以达到与 FE 2 多尺度模拟相似的精度,同时计算时间减少四个数量级. 基于 RNN 的替代模型的准确性和效率在经受多次加载/卸载循环的裸眼样品的结构分析中得到测试。结果表明,只要局部应变状态保持在训练范围内,基于 RNN 的代理模型就可以达到与 FE 2 多尺度模拟相似的精度,同时计算时间减少四个数量级. 基于 RNN 的替代模型的准确性和效率在经受多次加载/卸载循环的裸眼样品的结构分析中得到测试。结果表明,只要局部应变状态保持在训练范围内,基于 RNN 的代理模型就可以达到与 FE 2 多尺度模拟相似的精度,同时计算时间减少四个数量级.
更新日期:2020-09-01
down
wechat
bug