-
Notifications
You must be signed in to change notification settings - Fork 24
FNO battery module cooling example #7
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
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks Ben!
It would be good to put something more visual in the README -- especially since the main live script will not be viewable on GitHub.
## Requirements | ||
|
||
Requires | ||
- [MATLAB](https://www.mathworks.com/products/matlab.html) (R2025a or newer) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Could this run in earlier releases? What 25a features are requied?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
OK the example states we're using 25a functionality to handle the geometry.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Yeah the helper function in this example should work in some older releases than 25a. I'm not sure what the most recent Deep Learning Toolbox code I've used is, maybe the networkLayer from 24a, though it isn't strictly necessary. The PDE Toolbox introduced the femodel
in 23a, but there was ThermalModel
before that which might suffice for this example. So potentially we could write a version of the example that's supported quite a few releases back.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
the old APIs like ThermalModel will eventually be removed, so I would strongly suggest staying with femodel (23a as Ben mentioned)
battery-module-cooling-analysis-with-fourier-neural-operator/spectralConvolution3dLayer.m
Show resolved
Hide resolved
battery-module-cooling-analysis-with-fourier-neural-operator/spectralConvolution3dLayer.m
Show resolved
Hide resolved
battery-module-cooling-analysis-with-fourier-neural-operator/createBatteryModuleGeometry.m
Show resolved
Hide resolved
…d files, add images in the resources sub-directory
I've added a bunch more detail and a few images now. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Example looks fantastic, README is clear, and I love the thoughtful discussion at the end of the example about other methods/approaches.
One tiny suggestion for consideration: Maybe rename the sections "Specify material and physical properties and solve" to "Generate simulation data for training" and "Interpolate inputs and targets onto a grid" to "Prepare data for training", to capture the big ideas of those sections as well as to make it resonate more with a deep learning workflow.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This is great Ben!
No description provided.