Article
MLGen: Generative Design Framework Based on Machine
Learning and Topology Optimization
Nikos Ath. Kallioras
†
and Nikos D. Lagaros *
,†
Citation: Kallioras, N.A.; Lagaros,
N.D. MLGen: Generative Design
Framework Based on Machine
Learning and Topology Optimization.
Appl. Sci. 2021, 11, 12044. https://
doi.org/10.3390/app112412044
Academic Editor: Chiara Bedon
Received: 16 November 2021
Accepted: 14 December 2021
Published: 17 December 2021
Publisher’s Note: MDPI stays neutral
with regard to jurisdictional claims in
published maps and institutional affil-
iations.
Copyright: © 2021 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
Institute of Structural Analysis and Antiseismic Research, School of Civil Engineering, National Technical
University of Athens, 9, Heroon Polytechniou Str., Zografou Campus, GR-15780 Athens, Greece;
nkallio@mail.ntua.gr
* Correspondence: nlagaros@central.ntua.gr; Tel.: +30-210-772-2625
† These authors contributed equally to this work.
Abstract:
Design and manufacturing processes are entering into a new era as novel methods and
techniques are constantly introduced. Currently, 3D printing is already established in the production
processes of several industries while more are continuously being added. At the same time, topology
optimization has become part of the design procedure of various industries, such as automotive
and aeronautical. Parametric design has been gaining ground in the architectural design literature
in the past years. Generative design is introduced as the contemporary design process that relies
on the utilization of algorithms for creating several forms that respect structural and architectural
constraints imposed, among others, by the design codes and/or as defined by the designer. In this
study, a novel generative design framework labeled as MLGen is presented. MLGen integrates
machine learning into the generative design practice. MLGen is able to generate multiple optimized
solutions which vary in shape but are equivalent in terms of performance criteria. The output of
the proposed framework is exported in a format that can be handled by 3D printers. The ability
of MLGen to efficiently handle different problems is validated via testing on several benchmark
topology optimization problems frequently employed in the literature.
Keywords:
generative design; machine learning; topology optimization; long short-term networks;
ant colony optimization
1. Introduction
Generally speaking, structural optimization can be distinguished into three categories:
topology, shape and sizing optimization [
1
,
2
]. Topology optimization refers to a mathemat-
ical procedure that aims to identify the optimal shape, in terms of structural performance,
of a structural system when subjected to specific load and support conditions. This is
achieved by optimizing the topological placement of a specific quantity of material into
the design domain. Apart from structural performance, topology optimization can be
used for optimization with respect to sizing and shape criteria as well. The application of
such approaches helps, among others, to create structural systems that are very close to
their optimal shape, and thus can be considered a supporting procedure in the conceptual
design phase [3,4].
With the term generative design, a design exploration process is defined. The basic
idea of this process is that engineers/designers in general introduce their design goals
and constraints imposed by design codes, etc., into the generative design framework,
along with other parameters, such as performance demands, material properties, etc. The
generative design framework should be able to examine all or most of the possible solutions
of the specific problem, and produce design alternatives of equivalent performance and
criteria values.
During the last decade, research on modern soft computing methods drew significant
attention [
5
], mainly due to the excessive amount of data generated. This led to the
Appl. Sci. 2021, 11, 12044. https://doi.org/10.3390/app112412044 https://www.mdpi.com/journal/applsci
