Generative Design of Physical Objects using Modular Framework

TL;DR

This paper introduces GEFEST, a flexible modular framework for generative design of physical objects, capable of addressing diverse engineering problems through sampling, estimation, and optimization principles.

Contribution

The paper presents a novel, general framework called GEFEST that enhances flexibility and applicability in generative design across various engineering domains.

Findings

GEFEST outperforms baseline solutions in synthetic and real-world cases.

The framework's flexibility allows adaptation to different problem types.

Experimental results confirm the effectiveness of GEFEST in diverse applications.

Abstract

In recent years generative design techniques have become firmly established in numerous applied fields, especially in engineering. These methods are demonstrating intensive growth owing to promising outlook. However, existing approaches are limited by the specificity of problem under consideration. In addition, they do not provide desired flexibility. In this paper we formulate general approach to an arbitrary generative design problem and propose novel framework called GEFEST (Generative Evolution For Encoded STructure) on its basis. The developed approach is based on three general principles: sampling, estimation and optimization. This ensures the freedom of method adjustment for solution of particular generative design problem and therefore enables to construct the most suitable one. A series of experimental studies was conducted to confirm the effectiveness of the GEFEST framework. It involved synthetic and real-world cases (coastal engineering, microfluidics, thermodynamics and oil field planning). Flexible structure of the GEFEST makes it possible to obtain the results that surpassing baseline solutions.