Skip to main content

A finite element analysis (FEA) library built on PyTorch for efficient simulations and automatic differentiation.

Project description

FEA —— 基于 PyTorch 的有限元分析框架

一个支持非线性材料、接触分析与动力学(隐式/显式)的研究型 FEA 框架。采用模块化设计,装配(Assembly)统一管理几何、材料、载荷与约束,求解器层提供静力隐式、动力隐式(Newmark-β)与动力显式(中心差分)。

特色

  • 装配-求解器分层,接口清晰,易扩展
  • 稀疏矩阵装配与 Pardiso/CG 线性求解
  • 动力学两种积分:Newmark-β(隐式)与中心差分(显式,集总质量)
  • 接触(自接触/体-体接触)、压力、体力等载荷组件
  • 基于 PyTorch,可使用 GPU 与自动微分做灵敏度/优化

快速开始

  1. 安装依赖(略)。推荐 Python 3.10+、PyTorch(float64)。
  2. 运行最小示例脚本(静力 + 表面压力):

在仓库根目录下执行(Windows PowerShell):

python .\Docs\examples\run_static_pressure.py

脚本会读取 tests/pressure_test/C3D4Less.inp,在 final_model 上施加表面压力并固定底部节点,调用静力隐式求解,并将位移向量保存至 out/static_pressure_GC.npy

  1. 更多用法示例:
  • 使用说明(从 INP 到求解、导出与可视化)见:Docs/usage.md
  • 框架架构与数据流见:Docs/structure.md

目录导航

  • FEA/:核心代码(装配、元素、载荷、约束、求解器等)
  • tests/:各类算例与验证(元素、压力、接触、动力学、梯度/优化)
  • Docs/:架构与使用文档,Docs/examples/ 提供可直接运行的示例脚本

许可

研究用途优先。若用于生产或商业,请先评估并完善必要的数值与工程健壮性保障。

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

torchfea-1.0.1.tar.gz (73.5 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

torchfea-1.0.1-py3-none-any.whl (93.2 kB view details)

Uploaded Python 3

File details

Details for the file torchfea-1.0.1.tar.gz.

File metadata

  • Download URL: torchfea-1.0.1.tar.gz
  • Upload date:
  • Size: 73.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.9.21 {"installer":{"name":"uv","version":"0.9.21","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":null,"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for torchfea-1.0.1.tar.gz
Algorithm Hash digest
SHA256 f9febdaf66a12866501520630f6765b7287b047d5c2372d3a6f2f573e3f9218e
MD5 ab9f30058de080f38225da3960bd7e79
BLAKE2b-256 6ff46ddb6583f5f25b7e93577ae3fc661421a233d9c24c7ee74a77530db9f324

See more details on using hashes here.

File details

Details for the file torchfea-1.0.1-py3-none-any.whl.

File metadata

  • Download URL: torchfea-1.0.1-py3-none-any.whl
  • Upload date:
  • Size: 93.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.9.21 {"installer":{"name":"uv","version":"0.9.21","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":null,"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for torchfea-1.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 693f12eeddbd1a99073efff65d1afdca8b3da3e29ee521b6d827267906ac29fc
MD5 fea10ba8133142f8da5cf5efbc1490b0
BLAKE2b-256 6b7e6339b93133d145b2f46bed0efc3084fc39dee957ebcd23e2ddb12885cc21

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page