STM Journals Peer-reviewed research from Consortium e-Learning Network

Journal of Polymer & Composites Original Research

Machine Learning–Assisted Design of High-Performance Biomedical Polymer Composites

  1. Snehal Masurkar Department of Science, Krishna Institute of Science and Technology, Krishna Vishwa Vidyapeeth “Deemed to be University”, Karad, Satara
  2. Chetan Kumar Sharma Department of Science, School of Sciences, Noida international University, Greater Noida
  3. Prashant Anerao Department of Mechanical Engineering, Vishwakarma Institute of Technology, Pune
  4. Roshini B, Meenakshi Department of Science, College of Allied Health Sciences, Meenakshi Medical College Hospital & Research Institute, Meenakshi Academy of Higher Education and Research, Kanchipuram
  5. MANZOOR MOHAMMAD Department of Computer Science and Engineering (AI&ML), Vardhaman College of Engineering, Shamshabad, Hyderabad
  6. Avinash Gudimetla Department of Mechanical Engineering, Pragati Engineering College, Kakinada District

Abstract

The high-performance biomedical polymer composite design needs to represent a trade-off between the strength, biocompatibility, and degradation that cannot be accomplished using conventional design methods. The study aims to develop a predictive and optimization framework of composite properties with the help of machine learning. The methods include ANN, SVM, Random Forest, and Gradient Boosting with experiment and simulation data. The results of Gradient Boosting show that the accuracy is 95.9 which is 27.4% and 32.6% less than that of SVM, RMSE and MAE respectively. It is examined to make sure that there is an enhanced predictability and material performance. The framework helps to design the multi-objectives efficiently and optimally and come to the conclusion that ML can significantly enhance the effectiveness of composite development in high-tech biomedical materials. The specified method proved to be effective in the determination of complex dependence between the composition of the material and performance property that led to the appropriate prediction and optimization. The comparative analysis indicated that the hybrid model was very accurate and reliable to the conventional methods. Moreover, multi-objective based optimizations enabled mechanical strength, biocompatibility and degradation behaviour to be harmonized. The framework significantly reduces the development cost of the experimentation and facilitates the development of the materials. The future of real-time adaptive learning and integration with digital twin systems will be focused on the personalized biomedical applications.

Keywords

References (15)

  1. Hrehova, S., & Knapcikova, L. (2022). The Study of Machine Learning Assisted the Design of Selected Composites Properties. Applied Sciences, 12(21), 10863. https://doi.org/10.3390/app122110863.
  2. Gyabaah, K. Y., Mahoney, B., Martey, A. K., Yan, C., Mensah, P., & Li, G. (2026). Machine Learning-Assisted Polymer and Polymer Composite Design for Additive Manufacturing. AI Materials, 1(1), 2. https://doi.org/10.3390/aimater1010002.
  3. Malashin, I., Masich, I., Tynchenko, V., Gantimurov, A., Nelyub, V., Borodulin, A., Martysyuk, D., & Galinovsky, A. (2024). Machine Learning in 3D and 4D Printing of Polymer Composites: A Review. Polymers, 16(22), 3125. https://doi.org/10.3390/polym16223125.
  4. Fernandes, C. (2025). Scientific Machine Learning for Polymeric Materials. Polymers, 17(16), 2222. https://doi.org/10.3390/polym17162222.
  5. Ashok, N., Garcia-Diaz, P., Mosquera, M. E. G., & Sessini, V. (2025). Machine Learning for the Optimization of the Bioplastics Design. Macromol, 5(3), 38. https://doi.org/10.3390/macromol5030038.
  6. Sadat, T. (2023). Machine Learning-Assisted Tensile Modulus Prediction for Flax Fiber/Shape Memory Epoxy Hygromorph Composites. Applied Mechanics, 4(2), 752-762. https://doi.org/10.3390/applmech4020038.
  7. Zhou, X., Xu, J., Meng, L., Wang, W., Zhang, N., & Jiang, L. (2024). Machine-Learning-Assisted Composition Design for High-Yield-Strength TWIP Steel. Metals, 14(8), 952. https://doi.org/10.3390/met14080952.
  8. R. N. Gaidhane, D. T. G. Shende, and D. A. Rai, “Bacteria-Based Self-Healing Concrete Technologies: A Review of Literature and Future Perspectives ”, IJTARME, vol. 14, no. 1, pp. 67–74, Dec. 2025.
  9. Chen, G., Shen, Z., Iyer, A., Ghumman, U. F., Tang, S., Bi, J., Chen, W., & Li, Y. (2020). Machine-Learning-Assisted De Novo Design of Organic Molecules and Polymers: Opportunities and Challenges. Polymers, 12(1), 163. https://doi.org/10.3390/polym12010163.
  10. Mairpady, A., Mourad, A.-H. I., & Mozumder, M. S. (2021). Statistical and Machine Learning-Driven Optimization of Mechanical Properties in Designing Durable HDPE Nanobiocomposites. Polymers, 13(18), 3100. https://doi.org/10.3390/polym13183100.
  11. Zhang, J., Mapossa, A. B., Liu, Y., & Sundararaj, U. (2026). AI-Driven Design of Sustainable Flame-Retardant Biodegradable Polymer Composites. Applied Sciences, 16(5), 2405. https://doi.org/10.3390/app16052405.
  12. Long, T., Pang, Q., Deng, Y., Pang, X., Zhang, Y., Yang, R., & Zhou, C. (2025). Recent Progress of Artificial Intelligence Application in Polymer Materials. Polymers, 17(12), 1667. https://doi.org/10.3390/polym17121667.
  13. Nguyen, P.C.; Choi, J.B.; Udaykumar, H.; Baek, S. Challenges and opportunities for machine learning in multiscale computational modeling. J. Comput. Inf. Sci. Eng. 2023, 23, 060808.
  14. Van Cranenburgh, S.; Wang, S.; Vij, A.; Pereira, F.; Walker, J. Choice modelling in the age of machine learning-discussion paper. J. Choice Model. 2022, 42, 100340.
  15. Yu, J., Yao, D., Wang, L., & Xu, M. (2025). Machine Learning in Predicting and Optimizing Polymer Printability for 3D Bioprinting. Polymers, 17(13), 1873. https://doi.org/10.3390/polym17131873.
Support