Page 114 - MSAM-3-2

Materials Science in

Additive Manufacturing

ORIGINAL RESEARCH ARTICLE
Accelerating hybrid lattice structures design

with machine learning

Chenxi Peng , Phuong Tran *, and Erich Rutz 1,2,4,5,6,7 *
1,2
3
1 Department of Paediatrics, The University of Melbourne, Parkville, Victoria, Australia
2 Murdoch Children’s Research Institute, Parkville, Victoria, Australia
3 RMIT Centre for Additive Manufacturing, School of Engineering, RMIT University, Melbourne,
Victoria, Australia
4 Bob Dickens Chair Paediatric Orthopaedic Surgery, The University of Melbourne, Parkville, Victoria,
Australia
5 Department of Orthopaedics, The Royal Children’s Hospital Melbourne, Parkville, Victoria, Australia
6 The Hugh Williamson Gait Analysis Laboratory, The Royal Children’s Hospital Melbourne, Parkville,
Victoria, Australia
7 Medical Faculty, The University of Basel, Basel, Switzerland

Abstract

Lattice structures inspired by triply periodic minimal surfaces (TPMS) have attracted
increasing attention due to their lightweight properties and high mechanical
performance. Recent research showed that hybrid structures based on the topology
of two or more types of TPMS can present interesting multifunctional properties.
However, the complexity of TPMS-based lattice designs presents challenges in both
design and evaluation. To address these challenges, this study was designed to
*Corresponding authors: explore the integration of the machine learning method to predict the mechanical
Phuong Tran properties of hybrid lattice structures inspired by TPMS based on their patterns.
(jonathan.tran@rmit.edu.au)
Erich Rutz A back propagation neural network (BPNN) was designed and trained on a dataset
(erich_rutz@hotmail.com) generated through finite element (FE) simulations and homogenization methods.
Citation: Peng C, Tran P, Rutz E. The BPNN demonstrated robustness in predicting elastic modulus and Poisson’s ratio
Accelerating hybrid lattice structures of TPMS hybrid lattice structures, offering rapid and efficient predictions. Validation
design with machine learning. Mater against FE simulations confirmed the accuracy and reliability of the BPNN predictions,
Sci Add Manuf. 2024;3(2):3430
doi: 10.36922/msam.3430 proving its potential as a valuable tool for accelerating the design and evaluation of
complex hybrid lattice structures.
Received: April 16, 2024
Accepted: June 03, 2024
Keywords: Lattice structures; Triply periodic minimal surfaces; Elastic modulus; Poisson’s
Published Online: June 25, 2024 ratio; Machine learning
Copyright: © 2024 Author(s).
This is an Open-Access article
distributed under the terms of the
Creative Commons Attribution 1. Introduction
License, permitting distribution,
and reproduction in any medium,
provided the original work is Lattice structures are attracting increasing attention from researchers as they present
properly cited. promising multifunctional properties, such as exceptional specific modulus and strength
1,2
Publisher’s Note: AccScience and energy absorption capabilities. Thus, these structures have the potential to meet
Publishing remains neutral with the requirements of various applications, for example, thermal management, bone tissue
3
regard to jurisdictional claims in 4 5-7 8,9 10-12
published maps and institutional engineering, energy absorption, heat dissipation, and structural components.
affiliations. The base material and cell topology are the two dominant factors affecting the properties

Volume 3 Issue 2 (2024) 1 doi: 10.36922/msam.3430