This is an unedited manuscript accepted for publication and provided as an Article in Press for early access at the author’s request. The article will undergo copyediting, typesetting, and galley proof review before final publication. Please be aware that errors may be identified during production that could affect the content. All legal disclaimers of the journal apply.
Tanveer Ahmad Wani,
Rahul Sonavale,
Nishant Kulkarni,
Ramachandro Majji,
Karpagavalli,
N Raghuveer,
- Associate Professor, Department of Physics, Noida international University, Greater Noida, Uttar Pradesh, India
- Associate Professor, Department of Computer Science and Engineering, Krishna Institute of Science and Technology, Krishna Vishwa Vidyapeeth “Deemed to be University”, Karad, Satara, Maharashtra, India
- Associate Professor, Department of Mechanical Engineering Vishwakarma Institute of Technology, Pune, Maharashtra, India
- Associate Professor, Department of Computer Science and Engineering (AI&ML), Vardhaman College of Engineering, Shamshabad, Hyderabad, Telangana, India
- Associate Professor, Department of Pharmaceutics, Meenakshi College of Pharmacy, Meenakshi Academy of Higher Education and Research, Mevalurkuppam, Tamil Nadu, India
- Associate Professor, Department of Mechanical Engineering, Pragati Engineering College, Kakinada District, Andhra Pradesh, India
Abstract
This paper introduces a knowledge-based design platform of biofunctional polymer composite substances through the combination of machine learning, materials informatics, and digital twins applications. The framework allows the effortless forecasting and maximization of mechanical, biological and degradation characteristics based on supervised, unsupervised and deep learning models. A materials database is accompanied by the AI algorithms to find the best material compositions and microstructure-property relationships. Experimental validation proves to be more accurate, less time development effort and greater material performance. The presented strategy provides a scalable and smart solution in the field of the next-generation biomedical composite design and individual material engineering applications. The data-driven design of bio functional polymer composite materials through machine learning, materials databases, and digital twins is proposed in the high-fidelity system, as suggested in this paper. The proposed approach enables to predict the material properties with the target accuracy, optimize the compositions, and even perfect the design on the fly. The framework is a complex microstructure-performance interaction through supervised and unsupervised and deep learning models. The experiment outcomes indicate that the level of accuracy of the experimental results is higher, development and material efficiency are lower than with the conventional methods. In total, the framework provides a chance to create the innovative technologies in the design of biomedical products at the scale and create the next-generation applications of composite materials in accordance with the developed biomedical materials design.
Keywords: Data-driven design, Polymer composites, Biofunctional materials, Machine learning, Digital twin, Materials informatics.
References
- Velazquez L, Palardy G, Barbalata C. A robotic 3D printer for UV-curable thermosets: dimensionality prediction using a data-driven approach. Int J Comput Integr Manuf. 2024;37:772-789.
- Cui B, Wang H. Compatibility analysis of waste polymer recycling in asphalt binder using molecular descriptor and graph neural network. Resour Conserv Recycl. 2025;212:107950.
- Shi J, Liu T, Zhou L, Yan P, Wang Z, Zhang X. A physics-informed deep learning liquid crystal camera with data-driven diffractive guidance. Commun Eng. 2024;3:46.
- Li Z, Chen Z, Sun W, Liu Y, Wang X, Lin J, et al. Properties of EPDM nanocomposites reinforced with modified montmorillonite. Polymers (Basel). 2024;16:2381.
- Jasinski W, Auriga R, Lee SH, Adamik L, Borysiuk P. Coniferous bark as filler for polylactic acid-based biocomposites. Polymers (Basel). 2024;16:2669.
- Song Z, Feng Y, Lu C. Prediction of the compressive strength and carpet plot for cross-material CFRP laminate based on deep transfer learning. Mater Sci Eng A. 2025;924:147792.
- Sukhadeve K, Meshram D, Akhare A, Gonnade A, Wayzode RR. A review design & analysis for better directional stability of centrally suspended cage-less slip differential and performance of steering geometry. IJTARME. 2025;14(1):48-50.
- Xu C, Wang Y, Barati Farimani A. TransPolymer: a transformer-based language model for polymer property predictions. npj Comput Mater. 2023;9:64.
- Pawar NM, Sairise RM, Karemore P, Jadhav A, Turaev D, Ajani SN. ML-based verification systems using discrete mathematical models. J Discrete Math Sci Cryptogr. 2026;29(2B):971-978. doi:10.47974/JDMSC-2548.
- Kolya H, Kang CW. Eco-friendly polymer nanocomposite coatings for next-generation fire retardants for building materials. Polymers (Basel). 2024;16:2045.
- Liu DF, Feng QK, Zhang YX, Zhong SL, Dang ZM. Prediction of high-temperature polymer dielectrics using a Bayesian molecular design model. J Appl Phys. 2022;132:014901.
- Miccio LA, Borredon C, Schwartz GA. A glimpse inside materials: polymer structure-glass transition temperature relationship as observed by a trained artificial intelligence. Comput Mater Sci. 2024;236:112863.
- Zhang L, Chen B, Lyu D, Wang L, Wang K. Estimation of lithium-ion battery health state by EVAE and BiGRU based on EIS. SSRN [Preprint]. 2025. SSRN:5100808.
Journal of Polymer & Composites
| Volume | 14 | |
| 04 | ||
| Received | 01/05/2026 | |
| Accepted | 30/06/2026 | |
| Published | 21/08/2026 | |
| Publication Time | 112 Days |