Generative Parametric Design (GPD): A framework for real-time geometry generation and on-the-fly multiparametric approximation

TL;DR

This paper introduces Generative Parametric Design (GPD), a framework that enables real-time geometry generation and parametric approximation using autoencoders and regression, facilitating design exploration and optimization in engineering.

Contribution

The paper presents a novel GPD framework that combines autoencoders and regression for efficient, real-time design generation and parametric solution approximation.

Findings

Effective generation of designs with reduced basis representations.

Demonstrated on two-phase microstructures with variable material parameters.

Enhanced capabilities for digital twin development and real-time decision-making.

Abstract

This paper presents a novel paradigm in simulation-based engineering sciences by introducing a new framework called Generative Parametric Design (GPD). The GPD framework enables the generation of new designs along with their corresponding parametric solutions given as a reduced basis. To achieve this, two Rank Reduction Autoencoders (RRAEs) are employed, one for encoding and generating the design or geometry, and the other for encoding the sparse Proper Generalized Decomposition (sPGD) mode solutions. These models are linked in the latent space using regression techniques, allowing efficient transitions between design and their associated sPGD modes. By empowering design exploration and optimization, this framework also advances digital and hybrid twin development, enhancing predictive modeling and real-time decision-making in engineering applications. The developed framework is demonstrated on two-phase microstructures, in which the multiparametric solutions account for variations in two key material parameters.