Effect of Data Augmentation and Membership Functions on ANFIS-Based Tensile Strength Prediction of FDM-Printed PETG Parts

Abstract

Fused deposition modeling (FDM) enables the fabrication of complex polymeric components; however, the tensile performance of printed parts is strongly influenced by processing conditions and can be difficult to predict when only a limited number of experimental observations are available. This study investigates the use of linear interpolation-based data augmentation combined with an adaptive neuro-fuzzy inference system (ANFIS) for predicting the tensile strength of FDM-printed polyethylene terephthalate glycol-modified (PETG) specimens. Layer thickness, infill density, and nozzle temperature were investigated using a Taguchi L9 experimental design, with three specimens fabricated for each condition and their mean tensile strength values used as the reference dataset. The experimental data were augmented in MATLAB using linear interpolation to generate datasets containing 200, 400, and 600 samples. Gaussian ANFIS models with three membership function configurations (M222, M333, and M444) were subsequently developed using 60/40, 70/30, and 80/20 training/testing ratios. Model performance was assessed using R2, MSE, and MEP, and a multi-criteria performance index was employed to determine the optimum configuration. The results showed that increasing the number of membership functions generally improved prediction accuracy, whereas increasing the augmented dataset size did not necessarily result in continuous performance gains. The optimum configuration was obtained with 400 augmented samples, an 80/20 training/testing ratio, and the M444 structure, yielding testing R2, MSE, and MEP values of 0.998935, 0.053107, and 0.00548758, respectively. The findings demonstrate that combining interpolation-based data augmentation with ANFIS provides an effective approach for predicting the tensile strength of FDM-printed PETG components when experimental datasets are limited.

Keywords

• Fused deposition modeling
• Tensile strength
• Data augmentation
• Linear interpolation
• ANFIS
• PETG

Ethical Statement

Ethics committee approval was not required for this study because no studies involving animals or humans were conducted.

Thanks

The author would like to thank the Department of Mechanical Engineering, Sakarya University of Applied Sciences, for providing laboratory facilities and technical support during the experimental study.

References

1. Agrawal, A. P., Kumar, V., Kumar, J., Paramasivam, P., Dhanasekaran, S., & Prasad, L. (2023). An investigation of combined effect of infill pattern, density, and layer thickness on mechanical properties of 3D printed ABS by fused filament fabrication. Heliyon, 9(6), Article e16531. https://doi.org/10.1016/j.heliyon.2023.e16531
2. Albaşkara, M. (2026). Impact of printing parameters and post-curing on surface quality in mSLA 3D printing. Black Sea Journal of Engineering and Science, 9(2), 845–853. https://doi.org/10.34248/bsengineering.1842733
3. Alkan, A., Koç, M. A., & Inan, M. S. (2026). Deep learning-based efficiency forecasting of automotive air conditioning system with variable-capacity compressors under different conditions. Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering, Article 09544070261433677. Advance online publication. https://doi.org/10.1177/09544070261433677
4. Andrés, M. S., Chércoles, R., Navarro, E., De La Roja, J. M., Gorostiza, J., Higueras, M., & Blanch, E. (2023). Use of 3D printing PLA and ABS materials for fine art. Analysis of composition and long-term behaviour of raw filament and printed parts. Journal of Cultural Heritage, 59, 181–189. https://doi.org/10.1016/j.culher.2022.12.005
5. Arslan, Y. (2025). Effects of ultra-cold temperature on thermoplastic (ASA, PLA) parts produced by 3D FDM printing technology. Sādhanā, 50(4), Article 250. https://doi.org/10.1007/s12046-025-02922-8
6. Ashok, G., Kumar, P., & Prabhu, T. (2025). Global developments in additive manufacturing of polymer composite materials: A scientometric review. Archives of Computational Methods in Engineering. Advance online publication. https://doi.org/10.1007/s11831-025-10282-z
7. Ayeb, M., Turki, M., Frija, M., & Fathallah, R. (2024). Artificial neural network and ANFIS approaches for mechanical properties prediction and optimization of a turbine blade treated by laser shock peening. Expert Systems with Applications, 250, Article 123911. https://doi.org/10.1016/j.eswa.2024.123911
8. Bahiraei, M., Nazari, S., & Safarzadeh, H. (2021). Modeling of energy efficiency for a solar still fitted with thermoelectric modules by ANFIS and PSO-enhanced neural network: A nanofluid application. Powder Technology, 385, 185–198. https://doi.org/10.1016/j.powtec.2021.03.001

9. Borah, J., Chandrasekaran, M., & Selvarajan, L. (2025). Taguchi-based experimental investigation and modeling of 3D-printed PEEK parts as biomedical implants using fused deposition modeling for improving mechanical strength and surface quality. Journal of Materials Engineering and Performance, 34(1), 195–207. https://doi.org/10.1007/s11665-023-09036-4
10. Çerlek, Ö., Han, K., Akin, Y., & Seçgin, Ö. (2024). Experimental investigation of parameters affecting the tensile strength of silicone-filled 3D printed ABS products. Journal of Materials Engineering and Performance. Advance online publication. https://doi.org/10.1007/s11665-024-10498-3
11. Durgashyam, K., Indra Reddy, M., Balakrishna, A., & Satyanarayana, K. (2019). Experimental investigation on mechanical properties of PETG material processed by fused deposition modeling method. Materials Today: Proceedings, 18, 2052–2059. https://doi.org/10.1016/j.matpr.2019.06.082
12. Eryildiz, M. (2021). Effect of build orientation on mechanical behaviour and build time of FDM 3D-printed PLA parts: An experimental investigation. European Mechanical Science, 5(3), 116–120. https://doi.org/10.26701/ems.881254
13. Golubović, Z., Danilov, I., Bojović, B., Petrov, L., Sedmak, A., Mišković, Ž., & Mitrović, N. (2023). A comprehensive mechanical examination of ABS and ABS-like polymers additively manufactured by material extrusion and vat photopolymerization processes. Polymers, 15(21), Article 4197. https://doi.org/10.3390/polym15214197
14. Guvenc, M. A., Bilgic, H. H., Cakir, M., & Mistikoglu, S. (2022). The prediction of surface roughness and tool vibration by using metaheuristic-based ANFIS during dry turning of Al alloy (AA6013). Journal of the Brazilian Society of Mechanical Sciences and Engineering, 44(10), Article 474. https://doi.org/10.1007/s40430-022-03798-z
15. Jang, J.-S. R. (1993). ANFIS: Adaptive-network-based fuzzy inference system. IEEE Transactions on Systems, Man, and Cybernetics, 23(3), 665–685. https://doi.org/10.1109/21.256541
16. Kahraman, H., Cesur, I., Eren, B., & Coban, A. (2023). An artificial neural network and Taguchi approach to the optimization of wear and friction for biodiesel fuel. Journal of Polytechnic, 26(4), 1431–1439. https://doi.org/10.2339/politeknik.1101970
17. Kartal, F., & Kaptan, A. (2023). Investigating the effect of nozzle diameter on tensile strength in 3D-printed polylactic acid parts. Black Sea Journal of Engineering and Science, 6(3), 276–287. https://doi.org/10.34248/bsengineering.1287141
18. Koç, M. A. (2022). Development of an intelligent software based on adaptive neural-fuzzy inference systems for predicting muzzle vibration of a gun barrel. Arabian Journal for Science and Engineering, 47(7), 8829–8846. https://doi.org/10.1007/s13369-021-06425-6
19. Özen, A., Abali, B. E., Völlmecke, C., Gerstel, J., & Auhl, D. (2021). Exploring the role of manufacturing parameters on microstructure and mechanical properties in fused deposition modeling (FDM) using PETG. Applied Composite Materials, 28(6), 1799–1828. https://doi.org/10.1007/s10443-021-09940-9
20. Ramos, A., Angel, V. G., Siqueiros, M., Sahagun, T., Gonzalez, L., & Ballesteros, R. (2025). Reviewing additive manufacturing techniques: Material trends and weight optimization possibilities through innovative printing patterns. Materials, 18(6), Article 1377. https://doi.org/10.3390/ma18061377
21. Sagias, V. D., Zacharia, P., Tempeloudis, A., & Stergiou, C. (2024). Mechanical properties predictive model of additive manufacturing specimens using ANFIS [Preprint]. Preprints. https://doi.org/10.20944/preprints202407.0094.v1
22. Şener, R., Koç, M. A., & Ermiş, K. (2024). Hybrid ANFIS-PSO algorithm for estimation of the characteristics of porous vacuum preloaded air bearings and comparison performance of the intelligent algorithm with the ANN. Engineering Applications of Artificial Intelligence, 128, Article 107460. https://doi.org/10.1016/j.engappai.2023.107460
23. Shergill, K. (2023). An investigation into the layer thickness effect on the mechanical properties of additively manufactured polymers: PLA and ABS. The International Journal of Advanced Manufacturing Technology, 126(11–12), 5283–5295. https://doi.org/10.1007/s00170-023-11438-w
24. Srinivasan, R., Prathap, P., Raj, A., Aswinth Kannan, S., & Deepak, V. (2020). Influence of fused deposition modeling process parameters on the mechanical properties of PETG parts. Materials Today: Proceedings, 27, 1877–1883. https://doi.org/10.1016/j.matpr.2020.03.809
25. Taguchi, G., Elsayed, E. A., & Hsiang, T. C. (1989). Quality engineering in production systems. McGraw-Hill.
26. Yadav, D., Chhabra, D., Gupta, R. K., Phogat, A., & Ahlawat, A. (2020). Modeling and analysis of significant process parameters of FDM 3D printer using ANFIS. Materials Today: Proceedings, 21, 1592–1604. https://doi.org/10.1016/j.matpr.2019.11.227
27. Yaman, P., Ekşi, O., Karabeyoğlu, S. S., & Feratoğlu, K. (2024). Effect of build orientation on tribological and flexural properties of FDM-printed composite PLA parts. Journal of Reinforced Plastics and Composites, 43(1–2), 97–110. https://doi.org/10.1177/07316844231157790
28. Yermurat, B., Seçgin, Ö., & Taşdemir, V. (2023). Multi-material additive manufacturing: Investigation of the combined use of ABS and PLA in the same structure. Materials Testing, 65(7), 1119–1126. https://doi.org/10.1515/mt-2022-0368