Prediction of Mechanical Properties of 3D Printed Particle-Reinforced Resin Composites

This review explores fundamental analytical modelling approaches using conventional composite theory and artificial intelligence (AI) to predict mechanical properties of 3D printed particle-reinforced resin composites via digital light processing (DLP). Their mechanisms, advancement, limitations, va...

Full description

Bibliographic Details
Main Authors: Rooney, Kimberley, Dong, Yu, Basak, Animesh, Pramanik, Alokesh
Format: Journal Article
Language:English
Published: MDPI 2024
Subjects:
Online Access:http://hdl.handle.net/20.500.11937/96080
_version_ 1848766092015566848
author Rooney, Kimberley
Dong, Yu
Basak, Animesh
Pramanik, Alokesh
author_facet Rooney, Kimberley
Dong, Yu
Basak, Animesh
Pramanik, Alokesh
author_sort Rooney, Kimberley
building Curtin Institutional Repository
collection Online Access
description This review explores fundamental analytical modelling approaches using conventional composite theory and artificial intelligence (AI) to predict mechanical properties of 3D printed particle-reinforced resin composites via digital light processing (DLP). Their mechanisms, advancement, limitations, validity, drawbacks and feasibility are critically investigated. It has been found that conventional Halpin-Tsai model with a percolation threshold enables the capture of nonlinear effect of particle reinforcement to effectively predict mechanical properties of DLP-based resin composites reinforced with various particles. The paper further explores how AI techniques, such as machine learning and Bayesian neural networks (BNNs), enhance prediction accuracy by extracting patterns from extensive datasets and providing probabilistic predictions with confidence intervals. This review aims to advance a better understanding of material behaviour in additive manufacturing (AM). It demonstrates exciting potential for performance enhancement of 3D printed particle-reinforced resin composites, employing the optimisation of both material selection and processing parameters. It also demonstrates the benefit of combining empirical models with AI-driven analytics to optimise material selection and processing parameters, thereby advancing material behaviour understanding and performance enhancement in AM applications.
first_indexed 2025-11-14T11:45:38Z
format Journal Article
id curtin-20.500.11937-96080
institution Curtin University Malaysia
institution_category Local University
language English
last_indexed 2025-11-14T11:45:38Z
publishDate 2024
publisher MDPI
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-960802024-12-05T04:47:52Z Prediction of Mechanical Properties of 3D Printed Particle-Reinforced Resin Composites Rooney, Kimberley Dong, Yu Basak, Animesh Pramanik, Alokesh digital light processing (DLP) additive manufacturing (AM) particle-reinforced resin composites mechanical properties material optimisation empirical modelling artificial intelligence (AI) This review explores fundamental analytical modelling approaches using conventional composite theory and artificial intelligence (AI) to predict mechanical properties of 3D printed particle-reinforced resin composites via digital light processing (DLP). Their mechanisms, advancement, limitations, validity, drawbacks and feasibility are critically investigated. It has been found that conventional Halpin-Tsai model with a percolation threshold enables the capture of nonlinear effect of particle reinforcement to effectively predict mechanical properties of DLP-based resin composites reinforced with various particles. The paper further explores how AI techniques, such as machine learning and Bayesian neural networks (BNNs), enhance prediction accuracy by extracting patterns from extensive datasets and providing probabilistic predictions with confidence intervals. This review aims to advance a better understanding of material behaviour in additive manufacturing (AM). It demonstrates exciting potential for performance enhancement of 3D printed particle-reinforced resin composites, employing the optimisation of both material selection and processing parameters. It also demonstrates the benefit of combining empirical models with AI-driven analytics to optimise material selection and processing parameters, thereby advancing material behaviour understanding and performance enhancement in AM applications. 2024 Journal Article http://hdl.handle.net/20.500.11937/96080 10.3390/jcs8100416 English http://creativecommons.org/licenses/by/4.0/ MDPI fulltext
spellingShingle digital light processing (DLP)
additive manufacturing (AM)
particle-reinforced resin composites
mechanical properties
material optimisation
empirical modelling
artificial intelligence (AI)
Rooney, Kimberley
Dong, Yu
Basak, Animesh
Pramanik, Alokesh
Prediction of Mechanical Properties of 3D Printed Particle-Reinforced Resin Composites
title Prediction of Mechanical Properties of 3D Printed Particle-Reinforced Resin Composites
title_full Prediction of Mechanical Properties of 3D Printed Particle-Reinforced Resin Composites
title_fullStr Prediction of Mechanical Properties of 3D Printed Particle-Reinforced Resin Composites
title_full_unstemmed Prediction of Mechanical Properties of 3D Printed Particle-Reinforced Resin Composites
title_short Prediction of Mechanical Properties of 3D Printed Particle-Reinforced Resin Composites
title_sort prediction of mechanical properties of 3d printed particle-reinforced resin composites
topic digital light processing (DLP)
additive manufacturing (AM)
particle-reinforced resin composites
mechanical properties
material optimisation
empirical modelling
artificial intelligence (AI)
url http://hdl.handle.net/20.500.11937/96080