This Website is not fully compatible with Internet Explorer.
For a more complete and secure browsing experience please consider using Microsoft Edge, Firefox, or Chrome

3D Deep-Learning Based Surrogate Modeling and Optimisation

This presentation was made at the NAFEMS European Conference on Simulation-Based Optimisation held on the 15th of October in London.

Optimisation has become a key ingredient in many engineering disciplines and has experienced rapid growth in recent years due to innovations in optimisation algorithms and techniques, coupled with developments in computer hardware and software capabilities. The growing popularity of optimisation in engineering applications is driven by ever-increasing competition pressure, where optimised products and processes can offer improved performance and cost-effectiveness which would not be possible using traditional design approaches. However, there are still many hurdles to be overcome before optimisation is used routinely for engineering applications.

The NAFEMS European Conference on Simulation-Based Optimisation brings together practitioners and academics from all relevant disciplines to share their knowledge and experience, and discuss problems and challenges, in order to facilitate further improvements in optimisation techniques.

Resource Abstract

Numerical simulations have become of primary importance for the industry over the last decades.Nevertheless, since a simulation must be re-ran each time an engineer wishes to change the shape being designed, this makes the engineering process slow and costly. A typical approach is therefore to test only a few designs without a fine-grained search in the space of potential variations. This is a severe limitation and there have been many attempts at overcoming it and automating the shape optimization process, but none has been entirely successful yet. A classical approach to reduce the computational complexity is to use surrogate modelling via Gaussian Process (GP) regressors, or others, trained to interpolate the performance landscape given a low dimensional parametrization of the shape space. This interpolator is then used as a proxy for the true objective to speed-up the computation, which is referred to as Kriging in the literature. However, those regressors are only effective for shape deformations that can be parameterized using relatively few parameters and their performance therefore hinges on a well-designed parameterization. Furthermore, the regressors are specific to a particular parameterization and pre-existing computed simulation data using different ones cannot be easily leveraged.

Document Details

ReferenceC_Oct_19_Opt_5
AuthorBaqué. P
LanguageEnglish
TypePresentation
Date 15th October 2019
OrganisationNeural Concept
RegionUK

Download


Back to Previous Page