Machine Learning-Driven Optimization of Biodegradable Polymer Nanocomposites for Improved FDM Printability and Strength
DOI:
https://doi.org/10.12974/2311-8717.2025.13.12Keywords:
Biodegradable polymer nanocomposites, Machine learning optimization, FDM printability, PLA/PHA composites, Nanofillers, Mechanical strength, Sustainable additive manufacturingAbstract
Biodegradable polymer nanocomposites have emerged as promising sustainable materials for additive manufacturing, especially in Fused Deposition Modeling (FDM). However, their printability and mechanical performance remain highly sensitive to formulation variability and process parameter interactions. Addressing these limitations requires a systematic and predictive approach that integrates materials engineering with advanced data-driven tools. The present work aims to develop a machine learning-driven optimization framework for enhancing the printability and strength of biodegradable polymer nanocomposites used in FDM. A series of PLA-based and PHA-modified nanocomposites reinforced with cellulose nanocrystals (CNC) and nanosilica (SiO₂) were fabricated using a design-of-experiments approach. Key extrusion and printing parameters—including nozzle temperature, bed temperature, infill density, raster angle, and feed rate—were systematically varied to generate a comprehensive experimental dataset. Supervised machine learning models (Random Forest, XGBoost, and Artificial Neural Networks) were trained to predict printability indices and mechanical responses, including tensile strength, layer adhesion, and dimensional accuracy. Among the models evaluated, XGBoost achieved the highest predictive accuracy with an R² of 0.96 for tensile strength and 0.94 for printability. Feature importance analysis revealed that nanofiller loading, nozzle temperature, and infill density were the most influential factors. The optimized formulation identified by the ML framework—PLA/PHA with 1.5 wt% CNC—combined with optimal FDM settings resulted in a 22.8% improvement in tensile strength and a 17.4% increase in printability index compared to baseline samples. These results demonstrate that machine learning offers a powerful pathway for designing next-generation biodegradable nanocomposites and advancing sustainable, high-performance FDM manufacturing.
References
Dallaev, R., Papež, N., Allaham, M. M., & Holcman, V. (2025). Biodegradable polymers: properties, applications, and environmental impact. Polymers, 17(14), 1981. https://doi.org/10.3390/polym17141981
Olonisakin, K., Mohanty, A. K., Thimmanagari, M., & Misra, M. (2025). Recent advances in biodegradable polymer blends and their biocomposites: a comprehensive review. Green Chemistry, 27(38), 11656-11704. https://doi.org/10.1039/D5GC01294E
Guo, X., Liu, H., Nail, A., Meng, D., Zhu, L., Li, C., & Li, H. (2025). Design and Application of Stimuli‐Responsive Nanocomposite Hydrogels: A Review. Macromolecular Rapid Communications, 2401095. https://doi.org/10.1002/marc.202401095
Paul, D. B., & Susila, P. A. (2025). Direct ink writing of bioceramic prosthetics and scaffolds: advances, challenges, and biomedical applications. Progress in Additive Manufacturing, 1-22. https://doi.org/10.1007/s40964-025-01002-x
Antony Jose, S., Cowan, N., Davidson, M., Godina, G., Smith, I., Xin, J., & Menezes, P. L. (2025). A comprehensive review on cellulose Nanofibers, nanomaterials, and composites: Manufacturing, properties, and applications. Nanomaterials, 15(5), 356. https://doi.org/10.3390/nano15050356
Ali, S., Mehra, V., Eltaggaz, A., Deiab, I., & Pervaiz, S. (2024). Optimization and prediction of additively manufactured PLA-PHA biodegradable polymer blend using TOPSIS and GA-ANN. Manufacturing Letters, 41, 795-802. https://doi.org/10.1016/j.mfglet.2024.09.099
Jm, C. H., Narayanan, P., Pramanik, R., & Arockiarajan, A. (2025). Harnessing machine learning algorithms for the prediction and optimization of various properties of polylactic acid in biomedical use: a comprehensive review. Biomedical Materials.
Verma, D., Dong, Y., Sharma, M., & Chaudhary, A. K. (2022). Advanced processing of 3D printed biocomposite materials using artificial intelligence. Materials and Manufacturing Processes, 37(5), 518-538. https://doi.org/10.1080/10426914.2021.1945090
Baskaran, R., & T, T. (2025). Advances in Sustainable Polymeric Materials Derived from Renewable Biopolymers Integrated with Nanotechnology for Active Food Preservation: A Review. Polymer-Plastics Technology and Materials, 1-40. https://doi.org/10.1080/25740881.2025.2592713
Terzopoulou, P., Achilias, D. S., & Vouvoudi, E. C. (2025). Advanced Wood Composites with Recyclable or Biodegradable Polymers Embedded—A Review of Current Trends. Journal of Composites Science, 9(8), 415. https://doi.org/10.3390/jcs9080415
Radu, I. C., Vadureanu, A. M., Cozorici, D. E., Blanzeanu, E., & Zaharia, C. (2025). Advancing Sustainability in Modern Polymer Processing: Strategies for Waste Resource Recovery and Circular Economy Integration. Polymers, 17(4), 522. https://doi.org/10.3390/polym17040522
Peng, B., Qi, X., Qiao, L., Lu, J., Qian, Z., Wu, C., ... & Kou, X. (2025). Nanocomposite-Enabled Next-Generation Food Packaging: A Comprehensive Review on Advanced Preparation Methods, Functional Properties, Preservation Applications, and Safety Considerations. Foods, 14(21), 3688. https://doi.org/10.3390/foods14213688
Hussain, I., Ching, K. B., Uttraphan, C., Tay, K. G., & Noor, A. (2025). Evaluating machine learning algorithms for energy consumption prediction in electric vehicles: A comparative study. Scientific Reports, 15(1), 16124. https://doi.org/10.1038/s41598-025-94946-7
Yoshi, A. M., Rohan, A., Mitu, S. A., Rabbi, M. M. K., Akther, S., & Ahmed, K. R. (2025). Real-Time Dynamic Pricing Using Machine Learning: Integrating Customer Sentiment and Predictive Models for E-Commerce. International Journal of Advanced Computer Science & Applications, 16(9). https://doi.org/10.14569/IJACSA.2025.0160904
Alnemari, A. M., Elmessery, W. M., Qazaq, A. S., Moustapha, M. E., Rakhimgaliyeva, S., Abuhussein, M. F., ... & Elwakeel, A. E. (2025). Developing highly accurate machine learning models for optimizing water quality management decisions in tilapia aquaculture. Scientific Reports, 15(1), 35600. https://doi.org/10.1038/s41598-025-16939-w
Karuppusamy, M., Thirumalaisamy, R., Palanisamy, S., Nagamalai, S., Massoud, E. E. S., & Ayrilmis, N. (2025). A review of machine learning applications in polymer composites: advancements, challenges, and future prospects. Journal of Materials Chemistry A. https://doi.org/10.1039/D5TA00982K
Mehta, A., Vasudev, H., Prakash, C., Pramanik, A., Basak, A., & Shankar, S. (2025). State of the art in machine learning for the purpose of optimizing and predicting the properties of polymeric nanocomposites. Nanocomposite Manufacturing Technologies, 549-573. https://doi.org/10.1016/B978-0-12-824329-9.00016-4
Malashin, I., Martysyuk, D., Tynchenko, V., Gantimurov, A., Nelyub, V., Borodulin, A., & Galinovsky, A. (2025). Machine Learning in Polymeric Technical Textiles: A Review. Polymers, 17(9), 1172.
https://doi.org/10.3390/polym17091172
Jalaee, A. (2025). Advanced polymeric and wood-derived composites: structure, processing, and application (Doctoral dissertation, University of British Columbia).
Ho, M., Ramirez, A. B., Akbarnia, N., Croiset, E., Prince, E., Fuller, G. G., & Kamkar, M. (2025). Direct Ink Writing of Conductive Hydrogels. Advanced Functional Materials, 35(22), 2415507. https://doi.org/10.1002/adfm.202415507
Gholap, A. D., Said, R. P., Khuspe, P. R., Pardeshi, S. R., Pingale, P. L., Bhandari, K. M., ... & Giram, P. S. (2025). Recent Advances in Polyurethane Polymer for Biomedical Applications. Molecular Pharmaceutics. https://doi.org/10.1021/acs.molpharmaceut.5c00538
Pang, R., Lai, M. K., Teo, H. H., & Yap, T. C. (2025). Influence of Temperature on Interlayer Adhesion and Structural Integrity in Material Extrusion: A Comprehensive Review. Journal of Manufacturing and Materials Processing, 9(6), 196. https://doi.org/10.3390/jmmp9060196
Arunprasand, T. R., & Nallasamy, P. (2025). Advancements in optimizing mechanical performance of 3d printed polymer matrix composites via microstructural refinement and processing enhancements: A comprehensive review. Mechanics of Advanced Materials and Structures, 32(22), 5616-5634. https://doi.org/10.1080/15376494.2024.2426776
Petousis, M., Nasikas, N. K., Papadakis, V., Valsamos, I., Gkagkanatsiou, K., Mountakis, N., ... & Vidakis, N. (2025). Printability and Performance Metrics of New-Generation Multifunctional PMMA/Antibacterial Blend Nanocomposites in MEX Additive Manufacturing. Polymers, 17(3), 410. https://doi.org/10.3390/polym17030410
