Скачать или смотреть 8. DAKOTA-OpenFOAM optimization loop | Surrogate-based optimization SBO

The blunt body shape optimization case - Part 6

😵‍💫 Surrogate-based optimization SBO - Metamodels - Response surfaces - Gaussian process
👍 CFD optimization and automation.
👏 Engineering design optimization loop.

🤖 DAKOTA optimization toolbox
https://dakota.sandia.gov/

In this demo case, we use the following tools:
Geometry generation: Salome.
Mesh generation: Salome.
Balck box solver: OpenFOAM 11.
Automatic post-processing: bash scripting and Python.
Plotting: Python.
Optimization and orchestrating tool: DAKOTA 6.19.0


00:00 Introduction - Preliminaries
02:55 Surrogate-based optimization in a brief
09:08 Efficient global optimization EGO and the concept of the acquisition function
10:15 Let's take a look at DAKOTA's EGO input file
16:15 Let's launch the EGO optimization study
17:42 The outcome of the EGO study
21:20 Surrogate-based global optimization SBGO with infilling
29:40 Let's run the SBGO case - Reading input data
32:20 Let's run another version of the SBGO case - Reading a different input dataset
34:08 Let's take a look at the outcome
34:49 Avoid overfitting when constructing your models
37:08 A third version of the SBGO case - Reading input data and more infilling points
40:28 A fourth version of the SBGO case - No input data
45:40 Surrogate-based local optimization SBLO
47:52 DAKOTA's SBLO input file
49:11 Let's run the SBLO case - Reading input data
50:18 Let's take a look at the outcome
51:45 Let's run another SBLO case - No input data
53:44 Let's take a look at the outcome
55:44 Final remarks - Main takeaways


Compressed tutorial:
Blunt body shape optimization case
https://bit.ly/3Rvyonj

Deck of slides:
Blunt body shape optimization
https://bit.ly/486DxrG

Related videos:
Blunt body shape optimization | Case presentation
   • DAKOTA-OpenFOAM code coupling and optimiza...  

Related playlists:
Transitioning to OpenFOAM 11 from OpenFOAM 10/9,
   • Transitioning to OpenFOAM 11 from OpenFOAM...  
DAKOTA optimization toolbox | Explore and predict with confidence | Installation and getting started,
   • DAKOTA optimization toolbox | Installation...  

Software links:
https://dakota.sandia.gov/
https://snl-dakota.github.io/
https://github.com/snl-dakota/dakota/...
https://xgboost.ai/
https://www.salome-platform.org/
https://openfoam.org/
https://learn.microsoft.com/en-us/win...

Additional links:
Excellent reference for optimization methods,
https://www.vrand.com/products/multid...
Mixed-Integer Parallel Efficient Global Optimization
https://github.com/wangronin/MIP-EGO

👍 CFD optimization and automation.
👏 Engineering design optimization loop.

**********************************************************************************

Wolʇ Dynamics, your reliable partner for CAE solutions,
CAD and solid modeling → Meshing → Simulations → Automation and optimization → Post-processing → Data analytics and ML → Reporting

http://www.wolfdynamics.com/

Why Wolʇ Dynamics? Simply look at our banner - notice how the F appears backwards.

Wolʇ Dynamics ↔ Flow Dynamics 😯+💣=🤯

****************************************************************************

👉 Subscribe and hit the bell to see new videos or we will go back to OpenFOAM 3:
   / @wolfdynamicscfd  

🖖 Join our channel to help us create more content. By joining our channel, you can also get access to perks:
   / @wolfdynamicscfd  

Follow us:
Twitter → twitter.com/WolfDynamics
LinkedIn → linkedin.com/company/wolf-dynamics

****************************************************************************

Wolf Dynamics makes no warranty, express or implied, about the completeness, accuracy, reliability, suitability, or usefulness of the information disclosed in this training material. This training material is intended to provide general information only. Any reliance the final user place on this training material is therefore strictly at his/her own risk. Under no circumstances and under no legal theory shall Wolf Dynamics be liable for any loss, damage or injury, arising directly or indirectly from the use or misuse of the information contained in this training material.

****************************************************************************

#optimization #CFD #CAE #aerospace #WSL #linux #dakotaopt #snappyhexmesh #openfoam #computationalfluiddynamics