Surrogate Assisted Optimization

[adrian.portillo.juan 0]

Dear community:

 

I am working on the optimization of tip-raked propellers for hydro-acoustics. 

 

To do so I have parameterized the tip rake of a propeller based on the tip rake value and a geometrical parameter named "p" that accounts for the curvature of the rake distribution curve. Now, I have built my first population of geometries based on LHS sampling. With that population (200 models) I have built a surrogate.

 

However, now I want to refine the reduced order model by building a new population closer to the optimum point. To do so I am trying to call the project fsc script with python and modify the tip rake and p parameter bounds. However, when I start scripting in python I do not manage to even open the project with CAESES from a python script. Can someone help? Find atached both the project script and the project file.

 

Thank you! 🙂

 

P.S: I need to do it from python scripts instead of directly in CAESES mainly because I need to do some processes outside CAESES and also because I will work in a batch environment (HPC)

CAESES_CLT_OPT_v2.cdbc script_trial.fsc

[Mr. Heinrich von Zadow 12]

Hi Adrian,

but can't you just open the project in CAESES and adjust the boundaries of your LHS sampling algorithm in the GUI? You can then still run the project in batch mode for the generation of the designs...
Or do you do the sampling (i.e. LHS) through a method within your python setup? I'm asking, because CAESES does also provide LHS sampling...

Also, instead of sampling a large design space and then another one in a second iteration, you could use the adaptive sampling method within CAESES. This will automatically start with a LHS and then switch to an adaptive mode based on uncertainty quantification or other criteria.

You can check the documentation for an example on how to run CAESES in batch mode.

Cheers
Heinrich