A machine learning approach to characterise fabrication porosity effects on the mechanical properties of additively manufactured thermoplastic composites

Aug 5, 2026

Upload by Aurora

Investigating how fabrication porosity influences the mechanical properties of additively manufactured composites, the study uses machine learning to reduce reliance on time- and cost-intensive experimental testing. Experimental data are drawn from 3D printed carbon fibre-reinforced polyamide (CF-PA) and carbon fibre-reinforced acrylonitrile butadiene styrene (CF-ABS), covering flexural, tensile, compressive, porosity, and hardness. Comparative modelling across ML methods achieves 80–99% accuracy, with ensemble tree learners and K-NN performing best, and extra-tree regression reaching R-squared of 0.9993 and 0.9996.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages36

Reading Time1 h 31 min

AccessFree to download

Abstract

Keywords

Introduction

A machine learning approach to characterise fabrication porosity effects on the mechanical properties of additively manufactured thermoplastic composites Udu, A. G., Osa-Uwagboe, N., Adeniran, O., Aremu, D., Khaksar, M. G . & Dong, H. Published PDF deposited in Coventry University’s Repository Original citation: Udu, AG, Osa-Uwagboe, N, Adeniran, O, Aremu, D, Khaksar, MG & Dong, H 2024, 'A machine learning approach to characterise fabrication porosity effects on the mechanical properties of additively manufactured thermoplastic composites', Journal of Reinforced Plastics and Composites, vol. (In-Press), pp. (In-Press) . [https://dx.doi.org/10.1177/07316844241236696](https://dx.doi.org/10.1177/07316844241236696) [DOI 10.1177/07316844241236696](DOI 10.1177/07316844241236696)[ ](DOI 10.1177/07316844241236696)[ISSN 0731-6844](ISSN 0731-6844) [ESSN 1530-7964](ESSN 1530-7964) Publisher: SAGE Publications This article is distributed under the terms of the Creative Commons AttributionNonCommercial 4.0 License ( [https://creativecommons.org/licenses/by-nc/4.0/](https://creativecommons.org/licenses/by-nc/4.0/)) which permits non-commercial use, reproduction and distribution of the work without further permission provided the original work is attributed as specified on the SAGE and Open Access pages ( [https://us.sagepub.com/en-us/nam/open-access-at-sage](https://us.sagepub.com/en-us/nam/open-access-at-sage)) Original Article A machine learning approach to characterise fabrication porosity effects on the mechanical properties of additively manufactured thermoplastic composites Amadi Gabriel Udu 1,2 􀀁, Norman Osa-uwagboe2,3 􀀁, Olusanmi Adeniran4 􀀁, Adedeji Aremu5, Maryam Ghalati Khaksar 1 and Hongbiao Dong 1 Journal of Reinforced Plastics and Composites 2024, Vol. 0(0) 1–35 © The Author(s) 2024 Article reuse guidelines: [sagepub.com/journals-permissions](sagepub.com/journals-permissions) [DOI: 10.1177/07316844241236696](DOI: 10.1177/07316844241236696)[ ](DOI: 10.1177/07316844241236696)[journals.sagepub.com/home/jrp](journals.sagepub.com/home/jrp) Abstract The investigation of the mechanical properties of additively manufactured (AM) composite has been the focus of several research over the past decades. However, testing constraints of time and cost have encouraged the exploration of more pragmatic methods such as machine learning (ML) for predicting these characteristics. This study builds on experimental investigations ofthe ﬂexural, tensile, compressive, porosity, and hardness properties of 3D printed carbon ﬁbre-reinforced polyamide (CF-PA) and carbon ﬁbre-reinforced acrylonitrile butadiene styrene (CF-ABS) composites, proposing the application of ML for predicting these mechanical properties. A comprehensive comparative analysis of various machine learning approaches was executed, with a resultant accuracy ranging between 80 and 99%. The results unveiled the superior predictive performance of ensemble tree learners and the K-NN regressor algorithms when temperature and porosity are selected (based on correlation analysis) as predictors for material hardness and strength in tension, compression, and ﬂexion. In particular, the model built on the extra-tree regressor algorithm demonstrated a remarkably robust ﬁt, with R-squared evaluation scores of 0.9993 and 0.9996 for CF-PA and CF-ABS, respectively. This work developsa ML model that relates porosity to the other mechanical properties of AM composites and the prediction models’exceptional accuracy, along with their precise alignment with experimental data, provide invaluable insights for the autonomous control and data-driven optimization of the structures. Keywords Additive manufacturing, damage assessment, machine learning, predictive analysis, mechanical properties Introduction Over the past decades, the production and application of AM ﬁbre-reinforced composites have seen a signiﬁcant surge. This growing interest is predominantly dri

FAQs

What problem does the study address?

The study addresses how fabrication porosity affects the mechanical properties of additively manufactured thermoplastic composites, and how to predict these properties without extensive experimental testing.

Which materials and properties are used for the machine learning analysis?

It uses experimental results for 3D printed CF-PA and CF-ABS composites, and includes flexural, tensile, compressive, porosity, and hardness properties.

Which machine learning methods show the strongest predictive performance?

Ensemble tree learners and the K-NN regressor perform best when temperature and porosity are used as predictors, with extra-tree regression achieving very high R-squared values.

Aug 5, 2026

Upload by Aurora