Skip to content

This issue was moved to a discussion.

You can continue the conversation there. Go to discussion →

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

Multi-Fidelity Models with Variable Design Spaces #597

Closed
socrates-ferna opened this issue Jun 24, 2024 · 0 comments
Closed

Multi-Fidelity Models with Variable Design Spaces #597

socrates-ferna opened this issue Jun 24, 2024 · 0 comments

Comments

@socrates-ferna
Copy link

socrates-ferna commented Jun 24, 2024

Hi, thanks for such an amazing toolbox!

I have read both the 2.0 and the original release papers looking for a way of building a multifidelity model in which the design space of the low fidelity model has less dimensions than the high fidelity space. This does not seem to be possible with the current Co-Kriging model. The new Hierarchical Design Spaces, which can tackle variable design spaces, seem to be designed only for single-fidelity models. Across the literature, I have only found the technique on design space mappings to deal with this case.

I can think of a very naive way of dealing with this, which is expanding the low-fid input vectors onto the high-fid space forcing the low fid points to be constant along the new dimensions, but I was wondering if I could find a better solution within the toolbox.

An aerospace example of my case would be a low fid surrogate of lift and drag coefficients that only depends on the angle of attack, and a high fid surrogate which accounts in addition for Reynolds and Mach.

Is there any tool in SMT for my issue? If there's not, is it in the roadmap?

Thanks again for your work!

@SMTorg SMTorg locked and limited conversation to collaborators Jun 24, 2024
@relf relf converted this issue into discussion #598 Jun 24, 2024

This issue was moved to a discussion.

You can continue the conversation there. Go to discussion →

Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant