Used to be part of the suite of open-source python packages for Additive Manufacturing (AM) research, JAX-AM. FEM is a powerful tool, where we support the following features. Updates (Dec 11, 2023): We now support multi-physics problems in the sense that multiple variables can be solved monolithically.

2024年2月5日 · 为了进一步推动可 自动微分 的 有限元方法 库JAX-FEM项目的发展，JAX-FEM将加入DeepModeling社区，与诸位社区开发者和用户共同在AI4Science时代下拓展有限元方法的边界。

2023年10月1日 · This paper introduces JAX-FEM, an open-source differentiable finite element method (FEM) library. Constructed on top of Google JAX, a rising machine learning library focusing on high-performance numerical computing, JAX-FEM is implemented with pure Python while scalable to efficiently solve problems with moderate to large sizes.

本notebook旨在介绍JAX, FEM和Inverse Problem的基本内容, 以此将读者引导向JAX-FEM的七个算例及其具体介绍. JAX-FEM 框架是一款用JAX编写的有限元框架, 我们先简要介绍JAX, 尤其是它的即时编译 (Just-in-Time Compilation), 自动并行优化与自动微分这三大特性. JAX (Just-in-Time Accelerated X) 是由谷歌开发的一个用于高性能数值计算和机器学习的开源库. 它是构建在Python的科学计算库NumPy和自动微分库Autograd的基础上, 并结合了XLA (Accelerated …

2022年12月2日 · Abstract: This paper introduces JAX-FEM, an open-source differentiable finite element method (FEM) library. Constructed on top of Google JAX, a rising machine learning library focusing on high-performance numerical computing, JAX-FEM is implemented with pure Python while scalable to efficiently solve problems with moderate to large sizes.

2024年10月29日 · Used to be part of the suite of open-source python packages for Additive Manufacturing (AM) research, JAX-AM. FEM is a powerful tool, where we support the following features. Updates (Dec 11, 2023): We now support multi-physics problems in the sense that multiple variables can be solved monolithically.

A GPU-accelerated differentiable finite element analysis package based on JAX. Used to be part of the suite of open-source python packages for Additive Manufacturing (AM) research, JAX-AM. Finite Element Method (FEM) FEM is a powerful tool, where we support the following features 2D quadrilateral/triangle elements 3D hexahedron/tetrahedron elements

2023年8月14日 · 有限元法（FEM，Finite Element Method）是一种为求解偏微分方程边值问题近似解的数值技术。求解时对整个问题区域进行分解，每个子区域上定义基函数，把有限元组合起来近似得到原方程的解。

今天，我们向您隆重推荐一个基于谷歌的高性能自动微分库 JAX 的开源项目—— JAX-FEM。 这个项目旨在提供一个高效、可微分的 GPU 加速 FEM 解决方案，为研究和应用带来新的可能。 JAX-FEM 是一个强大的 Python 包，它为线性和非线性问题的求解提供了全面的支持。 作为 JAX-AM 套件的一部分，这个项目专注于利用深度学习技术和有限元素法来解决增材制造（Additive Manufacturing, AM）中的挑战。 通过自动导数支持，JAX-FEM 能够轻松地进行逆问题求解和 …

JAX-AM is a collection of several numerical tools, currently including Discrete Element Method (DEM), Lattice Boltzmann Methods (LBM), Computational Fluid Dynamics (CFD), Phase Field Method (PFM) and Finite Element Method (FEM), that cover the analysis of the Process-Structure-Property relationship in AM.