Optimising 3D-printed carbon fibre composites using machine learning: Balancing strength and efficiency
Additive manufacturing (AM) of fibre-reinforced composites offers design freedom but necessitates a trade-off between mechanical performance and production speed. This study introduces a data-driven framework that integrates machine learning (ML) and genetic algorithms (GA) to optimise interlaminar...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-08-01
|
| Series: | Materials & Design |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S0264127525007452 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849428541047832576 |
|---|---|
| author | José Humberto S. Almeida, Jr. Guilherme Ferreira Gomes |
| author_facet | José Humberto S. Almeida, Jr. Guilherme Ferreira Gomes |
| author_sort | José Humberto S. Almeida, Jr. |
| collection | DOAJ |
| description | Additive manufacturing (AM) of fibre-reinforced composites offers design freedom but necessitates a trade-off between mechanical performance and production speed. This study introduces a data-driven framework that integrates machine learning (ML) and genetic algorithms (GA) to optimise interlaminar strength and minimise printing time simultaneously. Among the seven ML models evaluated, artificial neural networks (ANNs) achieved the highest predictive accuracy (9.2% for strength, 14.7% for time). Pareto-optimal solutions were identified, with the best configuration reaching 27.6 MPa SBS in 75.9 minutes. Experimental validation confirmed the predicted failure modes, including interlaminar shear and delamination. Additionally, computed tomography (CT) scans revealed distinct internal microstructures: the strength-optimised configuration exhibited a well-consolidated morphology, while the speed-optimised sample showed increased void content. These results demonstrate that the proposed optimisation framework not only enhances AM efficiency and mechanical performance, but also enables more predictable failure behaviour, enabled by informed microstructural control. |
| format | Article |
| id | doaj-art-ea8161a437254edaa79a6283c0d0de2d |
| institution | Kabale University |
| issn | 0264-1275 |
| language | English |
| publishDate | 2025-08-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Materials & Design |
| spelling | doaj-art-ea8161a437254edaa79a6283c0d0de2d2025-08-20T03:28:40ZengElsevierMaterials & Design0264-12752025-08-0125611432510.1016/j.matdes.2025.114325Optimising 3D-printed carbon fibre composites using machine learning: Balancing strength and efficiencyJosé Humberto S. Almeida, Jr.0Guilherme Ferreira Gomes1Department of Mechanical Engineering, LUT University, Lappeenranta, Finland; Corresponding author.Mechanical Engineering Institute, Federal University of Itajubá, Itajubá, BrazilAdditive manufacturing (AM) of fibre-reinforced composites offers design freedom but necessitates a trade-off between mechanical performance and production speed. This study introduces a data-driven framework that integrates machine learning (ML) and genetic algorithms (GA) to optimise interlaminar strength and minimise printing time simultaneously. Among the seven ML models evaluated, artificial neural networks (ANNs) achieved the highest predictive accuracy (9.2% for strength, 14.7% for time). Pareto-optimal solutions were identified, with the best configuration reaching 27.6 MPa SBS in 75.9 minutes. Experimental validation confirmed the predicted failure modes, including interlaminar shear and delamination. Additionally, computed tomography (CT) scans revealed distinct internal microstructures: the strength-optimised configuration exhibited a well-consolidated morphology, while the speed-optimised sample showed increased void content. These results demonstrate that the proposed optimisation framework not only enhances AM efficiency and mechanical performance, but also enables more predictable failure behaviour, enabled by informed microstructural control.http://www.sciencedirect.com/science/article/pii/S0264127525007452Artificial intelligenceMachine learning3D printed compositesMulti-objective optimisationInterlaminar properties |
| spellingShingle | José Humberto S. Almeida, Jr. Guilherme Ferreira Gomes Optimising 3D-printed carbon fibre composites using machine learning: Balancing strength and efficiency Materials & Design Artificial intelligence Machine learning 3D printed composites Multi-objective optimisation Interlaminar properties |
| title | Optimising 3D-printed carbon fibre composites using machine learning: Balancing strength and efficiency |
| title_full | Optimising 3D-printed carbon fibre composites using machine learning: Balancing strength and efficiency |
| title_fullStr | Optimising 3D-printed carbon fibre composites using machine learning: Balancing strength and efficiency |
| title_full_unstemmed | Optimising 3D-printed carbon fibre composites using machine learning: Balancing strength and efficiency |
| title_short | Optimising 3D-printed carbon fibre composites using machine learning: Balancing strength and efficiency |
| title_sort | optimising 3d printed carbon fibre composites using machine learning balancing strength and efficiency |
| topic | Artificial intelligence Machine learning 3D printed composites Multi-objective optimisation Interlaminar properties |
| url | http://www.sciencedirect.com/science/article/pii/S0264127525007452 |
| work_keys_str_mv | AT josehumbertosalmeidajr optimising3dprintedcarbonfibrecompositesusingmachinelearningbalancingstrengthandefficiency AT guilhermeferreiragomes optimising3dprintedcarbonfibrecompositesusingmachinelearningbalancingstrengthandefficiency |