wouterpeere
Size borefield configuration function
Hi @wouterpeere ,
As already dicussed It would be nice to reimplement a borefield sizing method.
With best regards @tblanke
If issue #322 is implemented, this issue can be solved. The idea is to create a function with the following inputs (shape, max length x, max length y, min Bx, max Bx, min By, max Bx, min H, max H) which contains an objective function that sizes the borefield for a particular configuration and returns the total borehole length.
This function can than be used as an input to the optuna hyberparameter optimisation function to find the minimum value. The maximum number of iterations can be set here.
@tblanke , thank you for the update!
Everything works, it seems. I'm however missing some validation files to show the accurateness of the ANN. When I created a new test in the test_gfunction file, I get this result, where you can see that the gfunction for the ANN is completely different from the one directly calculated with pygfunction. I don't know if that is due to an error in the implementation of in the ANN itself?
Can you take a closer look at it?