leopoldoagorio/solid-mechanics-ML

This repository contains code for a project that trains a neural network to solve solid mechanics problems faster than the traditional finite element method. It includes a pipeline for generating a database of FEM solutions and experiments comparing the neural network model to the FEM.

32
/ 100
Emerging

This project helps mechanical engineers and researchers quickly estimate the behavior of materials under compression or extension. By using a pre-trained neural network, you can get rapid predictions of how a material deforms, instead of running time-consuming Finite Element Method (FEM) simulations. It takes material properties and applied forces as input and outputs the resulting mechanical response.

No commits in the last 6 months.

Use this if you need fast, approximate solutions for material deformation problems, especially in uniaxial compression or extension scenarios, and want to reduce reliance on lengthy FEM simulations.

Not ideal if you require extremely high precision for complex 3D solid mechanics problems or need to simulate conditions beyond simple compression/extension.

material-science mechanical-engineering finite-element-analysis structural-analysis computational-mechanics
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 11 / 25

How are scores calculated?

Stars

12

Forks

2

Language

TeX

License

MIT

Last pushed

Sep 28, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/leopoldoagorio/solid-mechanics-ML"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.