Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Feature multilayer perceptron #40

Merged
merged 11 commits into from
Apr 28, 2023
Merged

Conversation

EvertBunschoten
Copy link
Member

Added a tutorial and documentation for the CDataDrivenFluid class in SU2 and how to generate the input files required for the fluid model to function.

Comment on lines 1 to 7
---
title: Data-Driven Fluid Model
permalink: /SU2_CFD/src/fluid/CDataDrivenFluid.cpp
---
# Using Data-Driven Fluid Models in SU2
Modeling non-ideal fluid behavior can be difficult when limited to model equations or can be time consuming when performing large-scale simulations using the CoolProp fluid model. The data-driven fluid model class allows for the equation of state to be defined through a look-up table (LUT) or a set of multi-layer perceptrons (MLP), using an entropy-based equation of state. Given enough reference data and careful tuning of the initial conditions, it is possible to attain similar accuracies as the CoolProp library, while being compatible with the SU2 adjoint solver and a faster iteration time.

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

You need to add this file to the website instead, it's not picked up automatically.

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I added a modified version of the tutorial instructions to the website repo (feature_multilayer_peceptron). It explains how to use the data-driven fluid model and how to train a multi-layer perceptron to use as its input. However, in order to explain the entropy-based fluid model, I need to reference a paper which is yet to be published. This may take a couple of weeks. Do you think it's ok to merge this branch in the meantime or is it better to wait until the website tutorial instructions are complete?

Copy link
Member

@pcarruscag pcarruscag left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Sounds good

@EvertBunschoten EvertBunschoten merged commit 63d716b into develop Apr 28, 2023
@EvertBunschoten EvertBunschoten deleted the feature_multilayer_perceptron branch April 28, 2023 07:51
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants