材料响应信息驱动的DeepONet及其在晶体塑性多晶应力-应变预测中的应用
Material-Response-Informed DeepONet and its Application to Polycrystal Stress-strain Prediction in Crystal Plasticity
AI总结:
本文提出一种材料响应信息驱动的DeepONet架构,以单晶应力-应变曲线为分支输入、卷积神经网络编码微观组织,通过迁移学习实现不同材料和加载条件下多晶应力-应变的高精度快速预测。
摘要:
晶体塑性(CP)模拟是理解微观组织形貌和织构如何影响力学性能的工具,也是阐明结构-性能关系的重要组成部分。然而,其计算成本可能很高。因此,数据驱动的机器学习模型已被用于预测多晶代表性体积单元的平均场响应,以减少计算时间。在本工作中,我们提出了一种新颖的深度算子网络(DeepONet)架构,用于预测微观组织的应力-应变响应。该架构在主干网络中使用卷积神经网络对微观组织进行编码。为了考虑不同的材料属性、边界条件和加载方式,我们提出将单晶应力-应变曲线作为分支网络的输入,从而构建了一种材料响应信息驱动的DeepONet。通过四个数值算例,我们证明当前的DeepONet可以在单一材料和加载条件下进行训练,然后通过迁移学习推广到新的条件。结果表明,使用单晶响应作为输入优于使用材料属性作为输入的类似模型,并克服了边界条件和时间分辨率变化带来的局限性。在所有情况下,新模型均取得了0.99以上的$R^2$值,超过95%的预测应力相对误差$\le$ 5%,表明其具有优越的准确性。仅需少至20个新数据点和不到1分钟的训练时间,训练好的DeepONet即可通过微调在不同材料和加载条件下生成准确预测。训练完成后,预测速度比CP模拟快近$1\times10^{4}$倍。我们的DeepONet的高效性和高泛化能力使其成为多尺度分析中CP模拟的强大数据驱动代理模型。
英文摘要:
Crystal plasticity (CP) simulations are a tool for understanding how microstructure morphology and texture affect mechanical properties and are an essential component of elucidating the structure-property relations. However, it can be computationally expensive. Hence, data-driven machine learning models have been applied to predict the mean-field response of a polycrystal representative volume element to reduce computation time. In this work, we proposed a novel Deep Operator Network (DeepONet) architecture for predicting microstructure stress-strain response. It employs a convolutional neural network in the trunk to encode the microstructure. To account for different material properties, boundary conditions, and loading, we proposed using single crystal stress-strain curves as inputs to the branch network, furnishing a material-response-informed DeepONet. Using four numerical examples, we demonstrate that the current DeepONet can be trained on a single material and loading and then generalized to new conditions via transfer learning. Results show that using single crystal responses as input outperforms a similar model using material properties as inputs and overcomes limitations with changing boundary conditions and temporal resolution. In all cases, the new model achieved a $R^2$ value of above 0.99, and over 95\% of predicted stresses have a relative error of $\le$ 5\%, indicating superior accuracy. With as few as 20 new data points and under 1min training time, the trained DeepONet can be fine-tuned to generate accurate predictions on different materials and loading. Once trained, the prediction speed is almost $1\times10^{4}$ times faster the CP simulations. The efficiency and high generalizability of our DeepONet render it a powerful data-driven surrogate model for CP simulations in multi-scale analyses.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。