MECHANICAL BEHAVIOR PREDICTION OF CARBON FIBER-REINFORCED ONYX IN FDM USING INTEGRATED STATISTICAL AND MACHINE LEARNING APPROACHES
DOI:
https://doi.org/10.20998/2078-7405.2025.102.05Keywords:
Additive Manufacturing, Carbon Fiber Reinforced Onyx, Fused deposition modeling, Machine Learning, Mechanical Optimization, Response Surface Methodology, XGBoostAbstract
The mechanical performance of additively manufactured components is highly sensitive to process parameters, especially in advanced composite materials like carbon fiber-reinforced Onyx. This study presents a comparative optimization framework combining Response Surface Methodology (RSM) and machine learning (ML) to model and enhance the tensile and flexural strengths of Fused Deposition Modeling (FDM) printed Onyx composites. Key parameters including infill pattern, infill density, and nozzle temperature—were systematically varied using a Taguchi L9 design, and mechanical testing was performed according to ASTM standards. Statistical analysis revealed infill pattern as the most significant factor affecting strength properties. RSM provided reliable predictions with R² values of 97.61% (tensile) and 95.93% (flexural), while ML models, particularly XGBoost coupled with Bayesian optimization, achieved superior prediction accuracy with zero average error. Both methods converged on the same optimal parameters hexagonal infill, 60% infill density, and 265 °C nozzle temperature highlighting the consistency and robustness of the integrated approach. The results demonstrate that combining traditional statistical methods with advanced machine learning offers a powerful pathway for precise process control and mechanical optimization in polymer composite additive manufacturing.
References
Nikooharf, M. H., Shirinbayan, M., Arabkoohi, M., et al. (2023). Machine learning in polymer additive manufacturing: A review. Journal of Intelligent Manufacturing. https://doi.org/10.1007/s10845-023-02078-w
Jiang, J., Xiong, Y., Zhang, Z., et al. (2020). Machine learning integrated design for additive manufacturing. Journal of Intelligent Manufacturing, 33(4), 1073–1086. https://doi.org/10.1007/s10845-020-01715-6
Xames, M. D., Torsha, F. K., Sarwar, F., et al. (2022). A systematic literature review on recent trends of machine learning applications in additive manufacturing. Journal of Intelligent Manufacturing, 34(6), 2529–2555. https://doi.org/10.1007/s10845-022-01957-6
Raza, A., Deen, K. M., Jaafreh, R., et al. (2022). Incorporation of machine learning in additive manufacturing: A review. International Journal of Advanced Manufacturing Technology, 122(3–4), 693–716. https://doi.org/10.1007/s00170-022-09916-4
Qi, X., Chen, G., Li, Y., et al. (2019). Applying neural-network based machine learning to additive manufacturing: Current applications, challenges, and future perspectives. Engineering, 5(4), 721–729. https://doi.org/10.1016/j.eng.2019.04.012
Oh, S., Jung, Y., Kim, S., et al. (2019). Deep generative design: Integration of topology optimization and generative models. Journal of Mechanical Design, 141(11), 111405. https://doi.org/10.1115/1.4044197
Qin, J., Hu, F., Liu, Y., et al. (2022). Research and application of machine learning for additive manufacturing. Additive Manufacturing, 52, 102691. https://doi.org/10.1016/j.addma.2022.102691
Ciccone, F., Bacciaglia, A., Ceruti, A., et al. (2022). Optimization with artificial intelligence in additive manufacturing: A systematic review. The International Journal of Advanced Manufacturing Technology, 121, 5535–5558. https://doi.org/10.1007/s00170-022-09941-3
Kumar, S., Gopi, T., Harikeerthana, N., et al. (2023). Machine learning techniques in additive manufacturing: A state of the art review on design, processes and production control. The International Journal of Advanceg, Z., Demir, K., et al. (2022). Machine learning for advanced additive manufacturing. Additive Manufacturing, 53, 102726. https://dd Manufacturing Technology, 126, 4313–4334. https://doi.org/10.1007/s00170-023-11279-6
Jin, Z., Zhanoi.org/1.1016/j.addma.20220.102726
Ukwaththa, J., Herath, S., Meddage, D. P. P., et al. (2023). A review of machine learning (ML) and explainable artificial intelligence (XAI) methods in additive manufacturing. Additive Manufacturing, 61, 103377. https://doi.org/10.1016/j.addma.2022.103377
Patel, K. S., Shah, D. B., Kchaou, M., et al. (2022). Effect of process parameters on the mechanical performance of FDM printed carbon fiber reinforced PETG. Materials Today: Proceedings, 62(3), 2102–2108. https://doi.org/10.1016/j.matpr.2022.02.063
Dou, H., Cheng, Y., Ye, W., et al. (2021). Effect of process parameters on tensile mechanical properties of 3D printing continuous carbon fiber-reinforced PLA composites. Polymers, 13(5), 820. https://doi.org/10.3390/polym13050820
Dawood, A., Marti, B. M., Sauret-Jackson, V., et al. (2015). 3D printing in dentistry. British Dental Journal, 219(11), 521–529. https://doi.org/10.1038/sj.bdj.2015.914
Atakok, G., Kam, M., Koc, H. B., et al. (2022). Tensile, three-point bending and impact strength of 3D printed parts using PLA and recycled PLA filaments: A statistical investigation. Journal of Materials Research and Technology, 18, 1542–1554. https://doi.org/10.1016/j.jmrt.2022.02.018
Bilgin, M. (2022). Optimization of 3D processing parameters used FDM method in the production of ABS based samples. Materials Today: Proceedings, 62(1), 342–347. https://doi.org/10.1016/j.matpr.2022.02.062
Nalbant, M., Gökkaya, H., Sur, G. (2007). Application of Taguchi method in the optimization of cutting parameters for surface roughness in turning. Materials & Design, 28(4), 1379–1385. https://doi.org/10.1016/j.matdes.2006.01.008
Zhang, H., Li, A., Wu, J., et al. (2023). Multi-material 3D printing of continuous carbon fibre reinforced thermoset composites. Composites Part B: Engineering, 241, 110032. https://doi.org/10.1016/j.compositesb.2022.110032
Subramaniyan, M., Karuppan, S., Appusamy, A., et al. (2022). Sandwich printing of PLA and carbon fiber reinforced-PLA for enhancing tensile and impact strength. Materials Today: Proceedings, 62(3), 2186–2192. https://doi.org/10.1016/j.matpr.2022.02.077
Ramachandrarao, M., Khan, S. H., Abdullah, K., et al. (2021). Carbon nanotubes and nanofibers—reinforcement to carbon fiber composites: A review. Materials Today: Proceedings, 45(6), 5163–5170. https://doi.org/10.1016/j.matpr.2020.10.548
Wang, F., Ming, Y., Zhao, Y., et al. (2023). Fabrication of a novel continuous fiber 3D printed thermoset all-composite honeycomb sandwich structure with PMI foam reinforcement. Composite Structures, 308, 116585. https://doi.org/10.1016/j.compstruct.2023.11658
Burnett, C., Graninger, G., Eren, Z., et al. (2022). Tensile performance of carbon fibre-reinforced 3D-printed polymers: Effect of printing parameters. Composites Part B: Engineering, 247, 110312. https://doi.org/10.1016/j.compositesb.2022.110312
Kállai, Z., Nettig, D., Kipping, J., et al. (2023). A novel method for carbon fiber reinforced thermoplastics production combining incremental forming and 3D printing. Journal of Materials Processing Technology, 314, 118989. https://doi.org/10.1016/j.jmatprotec.2023.118989
Kumar, V., Veeman, D., Vellaisamy, M., et al. (2022). Evaluation of flexural strength of 3D-printed nylon with carbon reinforcement: An experimental validation using ANN. Materials Today: Proceedings, 62(3), 2210–2217. https://doi.org/10.1016/j.matpr.2022.02.080
ASTM International. (2021). Standard Test Method for Tensile Properties of Plastics (ASTM D638-21). West Conshohocken, PA:ASTM International.
ASTM International. (2021). Standard Test Methods for Flexural Properties of Plastics (ASTM D790-21). West Conshohocken, PA: ASTM International.
Downloads
Published
Issue
Section
License
Copyright Notice
Authors who publish with this Collection agree to the following terms:
1. Authors retain copyright and grant the Collection right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this Collection.
2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the Collection's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this Collection.
3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
