ML-enabled prediction and optimization of tensile strength and surface characteristics in additively manufactured PETG components
Source abstract
Abstract
This work gives an in-depth discussion on prediction and optimisation of the mechanical properties of FDM-printed polyethylene terephthalate glycol (PETG) parts by applying statistical and machine learning methods. Experimentally, the influence of the three important process variables on the surface roughness (SR) and ultimate tensile strength (UTS) was studied: the melting temperature, the height of the layer, and the infill density. The predictive capacity of the Artificial Neural Network (ANN), Random Forest Regression (RFR) and Response Surface Methodology (RSM) models were developed and compared. RFR model was found to be more accurate than other models with the following values of R 2 = 0.94 (training) and R 2 = 0.83 (testing) and mean absolute error (MAE) = 2.51 when predicting UTS. The mean error between the experimental and predicted values was lower than 5% accounting for the robustness of the developed model. The process parameters were optimised with multi objective Genetic Algorithm (GA) and produced an optimum UTS of 38.39 MPa and a minimum surface roughness of 5.65 um at 82.42% infill density, 0.26 mm layer height, and 230.26 C melting temperature. The findings are also validated by carrying out microstructural study using SEM image. These findings show how the mechanical performance and surface quality of PETG components that are FDM-printed can be enhanced by combining machine learning and evolutionary optimisation.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Additive Manufacturing and 3D Printing Technologies · Polymer Foaming and Composites · Additive Manufacturing Materials and Processes
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
North Eastern Regional Institute of Science and Technology
(NERIST)
Shree Guru Gobind Singh Tricentenary University
References (48)
Show source-provided references
1. 10.3390/polym1107122010.3390/polym11071220 ↗
2. 10.1007/s00170-022-08860-710.1007/s00170-022-08860-7 ↗
3. Stan F, Stanciu NV, Sandu IL, et al. Effect of low and extreme-low temperature on mechanical properties of 3D printed polyethylene terephthalate glycol copolymer. The Romanian journal of technical sciences. Applied Mechanics 2019; 64(1): 21–41.
4. 10.1016/j.jcomc.2023.10039210.1016/j.jcomc.2023.100392 ↗
5. 10.1016/j.polymertesting.2023.10794910.1016/j.polymertesting.2023.107949 ↗
6. 10.1016/j.matpr.2020.03.77710.1016/j.matpr.2020.03.777 ↗
7. 10.1007/978-981-15-9117-4_2110.1007/978-981-15-9117-4_21 ↗
8. 10.1007/s00170-022-09043-010.1007/s00170-022-09043-0 ↗
9. 10.1177/2634983321101647710.1177/26349833211016477 ↗
10. Petrov P Agzamova D Pustovalov V et al. (n.d.). Research into the effect of the 3D-printing mode on changing the properties of PETG transparent plastic – ESAFORM 2021. https://popups.uliege.be/esaform21/index.php?id=376310.25518/esaform21.3763 ↗
11. 10.1007/s40032-020-00646-810.1007/s40032-020-00646-8 ↗
12. 10.1016/j.mtcomm.2022.10477210.1016/j.mtcomm.2022.104772 ↗
13. Mahesh V, Hadi P, Mahesh V, et al. Experimental investigation and optimization of fused filament fabrication parameters for enhanced mechanical performance of PETG and carbon fiber-reinforced PETG composites. J Thermoplast Compos Mater. 2025; 08927057251403516. https://doi.org/10.1177/08927057251403516
14. 10.1007/s11665-026-13416-x10.1007/s11665-026-13416-x ↗
15. 10.1016/j.prostr.2022.02.00410.1016/j.prostr.2022.02.004 ↗
16. 10.1007/s42452-022-05039-310.1007/s42452-022-05039-3 ↗
17. 10.46519/ij3dptdi.106954410.46519/ij3dptdi.1069544 ↗
18. Alexopoulou VE, Christodoulou IT, Markopoulos AP. Effect of printing speed and layer height on geometrical accuracy of FDM-printed resolution holes of PETG artifacts. Eng Proc. 2022; 24(1): 11. https://doi.org/10.3390/IECMA2022-12887
19. 10.1016/j.jmrt.2023.01.04310.1016/j.jmrt.2023.01.043 ↗
20. 10.1007/s00170-025-16220-410.1007/s00170-025-16220-4 ↗
21. 10.1007/s10751-024-02006-910.1007/s10751-024-02006-9 ↗
22. 10.1016/j.polymertesting.2023.10795310.1016/j.polymertesting.2023.107953 ↗
23. Singaravel B, Niranjan T, Laxmireddy P, et al. Experimental investigation of degradation in the marine environment of FDM-based 3D printed specimens. Int J Lightweight Mater Manuf 2026; 9(1): 103–112.
24. 10.1108/RPJ-12-2024-052910.1108/RPJ-12-2024-0529 ↗
25. Ramachandran P, Pandian P, Ramamoorthi V, et al. Influence of process parameters on the mechanical properties of carbon fibre reinforced PETG. Mechanics of Advanced Composite Structures 2026; 13(1): 171–184.
26. 10.1016/j.matpr.2020.03.79710.1016/j.matpr.2020.03.797 ↗
27. 10.3390/polym1210220210.3390/polym12102202 ↗
28. 10.3390/ma1410255610.3390/ma14102556 ↗
29. 10.3390/ma1215249910.3390/ma12152499 ↗
30. 10.1016/j.polymertesting.2023.10805510.1016/j.polymertesting.2023.108055 ↗
31. 10.1007/s00170-023-11003-110.1007/s00170-023-11003-1 ↗
32. 10.1007/s00170-023-12155-w10.1007/s00170-023-12155-w ↗
33. 10.1038/s41524-019-0221-010.1038/s41524-019-0221-0 ↗
34. 10.1016/j.corsci.2008.10.03810.1016/j.corsci.2008.10.038 ↗
35. Kwak S, Kim J, Ding H, et al. Machine learning prediction of the mechanical properties of γ-TiAl alloys produced using random forest regression model. J Mark Res 2022; 18: 520–530. https://doi.org/10.1016/j.jmrt.2022.02.108
36. 10.1016/j.mtcomm.2019.10071510.1016/j.mtcomm.2019.100715 ↗
37. 10.3390/rs7070848910.3390/rs70708489 ↗
38. 10.1109/34.70960110.1109/34.709601 ↗
39. 10.1111/j.1751-5823.2009.00095_18.x10.1111/j.1751-5823.2009.00095_18.x ↗
40. 10.3389/fnins.2018.0041110.3389/fnins.2018.00411 ↗
41. 10.1016/j.matdes.2018.02.06110.1016/j.matdes.2018.02.061 ↗
42. 10.1007/s00170-009-2104-x10.1007/s00170-009-2104-x ↗
43. Mahmood MA Visan AI Ristoscu C et al. 2021 Artificial neural network algorithms for 3D printing materials 14163. MDPI.10.3390/ma14010163 ↗
44. Yamashita R Nishio M Do RKG et al. Convolutional neural networks: an overview and application in radiology. Insights Imaging 2018; 9: 611–629. Springer 2018. https://doi.org/10.1007/s13244-018-0639-910.1007/s13244-018-0639-9 ↗
45. 10.1088/1402-4896/ad651410.1088/1402-4896/ad6514 ↗
46. Goldberg DE. Genetic algorithms in search, optimization and machine learning. Addison-Wesley Longman Publishing Co, 1989.
47. Borah J, Chandrasekaran M. Prediction and optimization of tensile strength of additively manufactured PEEK biopolymer using machine learning techniques. Multiscale and multidiscip. Model. Exp. and Des 2024; 7: 4487–4502. https://doi.org/10.1007/s41939-024-00505-4
48. 10.1007/s40745-021-00354-910.1007/s40745-021-00354-9 ↗