基于循环神经网络的组织演化自监督学习与预测
Self-Supervised Learning and Prediction of Microstructure Evolution with Recurrent Neural Networks
摘要：
微观结构演化是理解和开发材料结构-性能-性能关系的一个关键方面。微观结构演化的模拟通常依赖于粗粒度的模拟，其演化原理由偏微分方程（PDE）描述。在这里，我们证明了卷积循环神经网络可以学习潜在的物理规则，并在预测微观结构现象时取代基于PDE的模拟。神经网络通过自监督学习来训练，其中图像序列来自几个常见过程的模拟，包括平面波传播、晶粒生长、旋节分解和树枝状晶体生长。经过训练的网络可以准确地预测微观结构的短期局部动力学和长期统计特性，并且能够在时空域以及配置和参数空间中外推训练数据集。这种数据驱动的方法在时间步进效率方面比基于PDE的模拟具有显着优势，并且提供了一种有用的替代方案，特别是当材料参数或控制PDE没有很好地确定时。
英文摘要：
Microstructural evolution is a key aspect of understanding and exploiting the structure-property-performance relation of materials. Modeling microstructure evolution usually relies on coarse-grained simulations with evolution principles described by partial differential equations (PDEs). Here we demonstrate that convolutional recurrent neural networks can learn the underlying physical rules and replace PDE-based simulations in the prediction of microstructure phenomena. Neural nets are trained by self-supervised learning with image sequences from simulations of several common processes, including plane wave propagation, grain growth, spinodal decomposition and dendritic crystal growth. The trained networks can accurately predict both short-term local dynamics and long-term statistical properties of microstructures and is capable of extrapolating beyond the training datasets in spatiotemporal domains and configurational and parametric spaces. Such a data-driven approach offers significant advantages over PDE-based simulations in time stepping efficiency and offers a useful alternative especially when the material parameters or governing PDEs are not well determined.
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。
