haghighat's blog

PINNs for solving multiphase poroelasticity relations

Submitted by haghighat on Fri, 10/08/2021 - 20:40

If you are interested in physics informed neural networks (PINNs) and coupled single and multiphase flow in porous media, please check out our work below:

- We find it challenging to solve coupled poroelasticity relations using PINNs (data-free).

A nonlocal physics-informed deep learning framework using the peridynamic differential operator

Submitted by haghighat on Thu, 06/04/2020 - 18:55

research

Physics-informed deep learning

nonlocal theory

Plasticity

https://www.researchgate.net/publication/341816480_A_nonlocal_physics-i…

Dear iMechanica Community:

SciANN: Scientific computations and physics-informed deep learning using artificial neural networks

Submitted by haghighat on Mon, 05/25/2020 - 16:10

Interested in deep learning, scientific computations, solution, and inversion methods for PDE?

Check out the preprint at:

https://www.researchgate.net/publication/341478559_SciANN_A_Keras_wrapp…

Some problems are shared in our GitHub repository on how to use sciann for inversion and forward solution of:

Postdoctoral Researcher at MIT - Geomechanics and Multiphase Flow in Porous Media

Submitted by haghighat on Tue, 04/16/2019 - 23:56

How to update solution-dependat variable (SVARS) during iterations

Submitted by haghighat on Thu, 02/09/2012 - 01:07

User subroutines in ABAQUS

Hello everyone,

I am implementing a uel user subroutine in ABAQUS. This uel is for modeling contact in X-FEM framework. Thus, it's a nonlinear problem and I need to store some solution dependent variables during each iteration. I know I can store SDVs in SVARS. But this vector will update at the end of each step, and not during iterations. Anybody knows about this problem?

I really appreciate if anybody can help me with this.

Thanks

Ehsan

Subscribe to haghighat's blog