Machine learning driven analysis of dimensional accuracy in FFF printed PLA-cenosphere-graphene composites
Source abstract
Abstract
This study investigates the influence of cenosphere and graphene nanoplatelet (GNP) reinforcements on the physical, mechanical, and dimensional accuracy characteristics of PLA-based composites fabricated using Fused Filament Fabrication (FFF). The incorporation of cenospheres effectively reduced the composite density from 1.25 g/cm 3 for neat PLA to 1.19 g/cm 3 and 1.14 g/cm 3 for 5 wt% and 10 wt% cenosphere additions, respectively, demonstrating the lightweighting capability of hollow ceramic fillers. The void content increased progressively with reinforcement loading due to increased melt viscosity, particle agglomeration, and localized air entrapment during processing, with values ranging from 2.14% to 8.09% for the reinforced composites. Despite the increase in porosity, graphene nanoplatelets improved the overall stiffness and stress transfer efficiency of the composites through enhanced interfacial interaction and restriction of polymer chain mobility. Mechanical characterization revealed substantial enhancement in hardness, reaching a maximum value of 91.5 Shore D for the hybrid PCG-5 composite, attributed to the synergistic reinforcement effect of rigid cenospheres and high-stiffness graphene nanoplatelets. Dimensional accuracy analysis identified layer thickness as the most influential processing parameter, contributing nearly 79% of the total variation, with lower layer heights consistently improving geometric fidelity. Statistical analyses using Taguchi design, ANOVA, contour mapping, and regression modeling confirmed this trend, while Random Forest regression further validated the experimental findings with a high prediction accuracy (R 2 = 0.94) and minimal prediction error. Feature importance analysis also established layer thickness as the dominant governing factor, followed by printing speed and raster angle. Overall, the integration of experimental optimization and machine learning provides an effective framework for improving dimensional precision and mechanical performance in additively manufactured PLA hybrid composites intended for lightweight engineering applications.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Additive Manufacturing and 3D Printing Technologies · Polymer Foaming and Composites · Advanced ceramic materials synthesis
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Siddaganga Institute of Technology
References (35)
Show source-provided references
1. 10.1016/j.compscitech.2023.11038510.1016/j.compscitech.2023.110385 ↗
2. 10.1177/0731684423118885310.1177/07316844231188853 ↗
3. 10.3390/jmmp803008610.3390/jmmp8030086 ↗
4. 10.1016/j.polymertesting.2023.10794910.1016/j.polymertesting.2023.107949 ↗
5. 10.1016/j.compositesb.2025.11284210.1016/j.compositesb.2025.112842 ↗
6. 10.3390/polym1514309610.3390/polym15143096 ↗
7. 10.1016/j.giant.2024.10026110.1016/j.giant.2024.100261 ↗
8. 10.1080/00914037.2021.194414010.1080/00914037.2021.1944140 ↗
9. 10.1038/s41598-023-43660-310.1038/s41598-023-43660-3 ↗
10. 10.1016/j.heliyon.2024.e2877110.1016/j.heliyon.2024.e28771 ↗
11. 10.1002/pc.2869310.1002/pc.28693 ↗
12. 10.1007/s40430-024-04744-x10.1007/s40430-024-04744-x ↗
13. 10.1016/j.matpr.2020.11.33210.1016/j.matpr.2020.11.332 ↗
14. 10.1002/smm2.7002710.1002/smm2.70027 ↗
15. 10.1016/j.istruc.2023.06.13610.1016/j.istruc.2023.06.136 ↗
16. 10.12776/qip.v24i1.143510.12776/qip.v24i1.1435 ↗
17. Mahesh V, Nilabh A, Joladarashi S, et al. Analysis of impact behaviour of sisal-epoxy composites under low velocity regime. Rev Des Compos Des Mater Av 2021; 31: 57–63. https://doi.org/10.18280/rcma.310108
18. Mahesh V, Joladarashi S, Kulkarni SM. Experimental study on abrasive wear behaviour of flexible green composite intended to be used as protective cladding for structures. Int J Mod Manuf Technol 2019; XI: 69–76.
19. 10.1002/pls2.1012210.1002/pls2.10122 ↗
20. 10.1016/j.prostr.2021.12.01110.1016/j.prostr.2021.12.011 ↗
21. Mahesh V. Statistical approach of determining the effect of cenosphere on the tribological behaviour of Jute reinforced polymer based composite. Mech Adv Compos Struct 2023; 10: 211–220. https://doi.org/10.22075/macs.2022.28671.1440
22. 10.1177/089270571986461910.1177/0892705719864619 ↗
23. Karamimoghadam M, Dezaki ML, Zolfagharian A, et al. Influence of post-processing CO2 laser cutting and FFF 3D printing parameters on the surface morphology of PLAs: statistical modelling and RSM optimisation. Int J Light Mater Manuf 2023; 6: 285–295. https://doi.org/10.1016/j.ijlmm.2023.01.004
24. 10.1038/s41598-026-42714-610.1038/s41598-026-42714-6 ↗
25. 10.3390/polym1713172810.3390/polym17131728 ↗
26. 10.3390/ma1818431910.3390/ma18184319 ↗
27. 10.1007/s40964-025-01228-910.1007/s40964-025-01228-9 ↗
28. 10.1007/s11665-025-10887-210.1007/s11665-025-10887-2 ↗
29. 10.1080/17480272.2025.252532910.1080/17480272.2025.2525329 ↗
30. 10.1007/s10570-025-06906-z10.1007/s10570-025-06906-z ↗
31. 10.1007/s10904-025-03733-410.1007/s10904-025-03733-4 ↗
32. 10.1007/s00107-025-02253-910.1007/s00107-025-02253-9 ↗
33. 10.1007/s10904-025-04078-810.1007/s10904-025-04078-8 ↗
34. 10.1016/j.apmt.2024.10230610.1016/j.apmt.2024.102306 ↗
35. 10.3390/app1504178110.3390/app15041781 ↗