Machine Learning-Based Structure–Property Quantification of Advanced Polymer Composites

Notice

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.

Year : 2026 | Volume : 14 | 04 | Page :
By

Ganesh P. Dawange,

Bhushan S. Chaudhari,

P. William,

Atul A. Barhate,

Sharad Ninu Kolte,

Amit V. Mohod,

Dipesh B. Pardeshi,

  1. Assistant Professor, Department of Structural Engineering, Sanjivani College of Engineering, Kopargaon, Maharashtra, India
  2. Professor, Department of Computer Science and Engineering, School of Engineering and Technology, Pimpri Chinchwad University, Pune, Maharashtra, India
  3. Professor (Research), School of Computer Science and Technology, Karunya Institute of Technology and Sciences, Coimbatore, Tamil Nadu, India
  4. Associate Professor, Department of Electrical Engineering, Godavari College of Engineering, Jalgaon, Dr. Babasaheb Ambedkar Technological University, Lonere, Maharashtra, India
  5. Lecturer, Department of Electrical Engineering, K. J. Somaiya polytechnic, Mumbai, Maharashtra, India
  6. Assistant Professor, Department of Electrical Engineering, Prof. Ram Meghe college of Engineering and Management, Badnera, Maharashtra, India
  7. Professor, Department of Electrical Engineering, Sanjivani College of Engineering, Kopargaon, Maharashtra, India

Abstract

Advanced polymer composites are widely used in high-performance engineering due to their superior mechanical and multifunctional properties. Accurate structure–property quantification is essential for efficient material design and reducing experimental costs. Existing Machine Learning (ML) approaches often exhibit limited predictive generalization due to inadequate feature discrimination and suboptimal hyperparameter tuning. To address these limitations, the proposed method enhances the ability to capture the complex nonlinear interactions among composite structural descriptors. The dataset Advanced Polymer Composite Properties contains 15,000 advanced polymer composite records with structural, processing, and engineering properties for ML-based material performance prediction. Data preprocessing incorporates missing value imputation, Isolation Forest-based outlier removal, and label encoding to improve data quality and ensure reliable model learning. Kernel Principal Component Analysis (KPCA) is employed to extract nonlinear and discriminative structural features while reducing data dimensionality and preserving critical structure–property information. The Runge–Kutta Optimized Stacked Light Gradient Network (RKO-SLGNet) is proposed for accurate structure–property quantification of advanced polymer composites, where the RKO automatically tunes model hyperparameters, Stacked CatBoost captures complex nonlinear relationships among structural descriptors, and the Light Gradient Boosting Machine refines the final prediction to improve accuracy and generalization. Python-based experimental evaluation demonstrated that the proposed RKO-SLGNet achieved superior predictive performance with a Mean Predicted Root Mean Square Error (RMSE) of 16.5, Mean Predicted Mean Absolute Error (MAE) of 11.6, and training time of 3s. It provides an accurate, scalable, and computationally efficient solution for structure–property quantification, facilitating data-driven material design and accelerating the development of next-generation advanced polymer composites.

Keywords: Advanced Polymer Composites, Structure–Property Quantification, Composite Materials, Material Property Prediction, Structure–Property Relationship.

How to cite this article: Ganesh P. Dawange, Bhushan S. Chaudhari, P. William, Atul A. Barhate, Sharad Ninu Kolte, Amit V. Mohod, Dipesh B. Pardeshi. Machine Learning-Based Structure–Property Quantification of Advanced Polymer Composites. Journal of Polymer & Composites. 2026; 14(04):-.
How to cite this URL: Ganesh P. Dawange, Bhushan S. Chaudhari, P. William, Atul A. Barhate, Sharad Ninu Kolte, Amit V. Mohod, Dipesh B. Pardeshi. Machine Learning-Based Structure–Property Quantification of Advanced Polymer Composites. Journal of Polymer & Composites. 2026; 14(04):-. Available from: https://journals.stmjournals.com/jopc/article=2026/view=255089

References

  1. Sheini Dashtgoli, D., Taghizadeh, S., Macconi, L. and Concli, F., 2024. Comparative analysis of machine learning models for predicting the mechanical behavior of bio-based cellular composite sandwich structures. Materials, 17(14), p.3493. https://doi.org/10.3390/ma17143493
  2. Niaki, M.H., Pashaian, M. and Ahangari, M.G., 2023. Experimental assessment of the efficiency of deep learning method in predicting the mechanical properties of polymer concretes and composites. Journal of Building Engineering, 76, p.107107. https://doi.org/10.1016/j.jobe.2023.107107
  3. Ghasemi, H. and Yazdani, H., 2025. Atomistic simulation and machine learning predictions of mechanical response in nanotube-polymer composites considering filler morphology and aggregation. Computational Materials Science, 246, p.113399. https://doi.org/10.1016/j.commatsci.2024.113399
  4. Zhao, Y., Chen, Z. and Jian, X., 2023. A high-generalizability machine learning framework for analyzing the homogenized properties of short fiber-reinforced polymer composites. Polymers, 15(19), p.3962. https://doi.org/10.3390/polym15193962
  5. Das, P.P., Rabby, M.M., Vadlamudi, V. and Raihan, R., 2022. Moisture content prediction in polymer composites using machine learning techniques. Polymers, 14(20), p.4403. https://doi.org/10.3390/polym14204403
  6. Ferdousi, S., Demchuk, Z., Choi, W., Advincula, R.C. and Jiang, Y., 2025. A deep learning and finite element approach for exploration of inverse structure–property designs of lightweight hybrid composites. Composite Structures, 365, p.119179. https://doi.org/10.1016/j.compstruct.2025.119179
  7. Prada Parra, D., Ferreira, G.R.B., Díaz, J.G., Gheorghe de Castro Ribeiro, M. and Braga, A.M.B., 2024. Supervised machine learning models for mechanical properties prediction in additively manufactured composites. Applied Sciences, 14(16), p.7009. https://doi.org/10.3390/app14167009
  8. Karadağ, A. and Ulkir, O., 2026. Taguchi-based multi-parameter optimization and machine learning prediction of mechanical properties in FDM-fabricated polymer composites. Journal of Materials Engineering and Performance, pp.1-19. https://doi.org/10.1007/s11665-026-13650-3
  9. Hamzat, A.K., Salman, U.T., Murad, M.S., Altay, O., Bahceci, E., Asmatulu, E., Bakir, M. and Asmatulu, R., 2025. Development of robust machine learning models for predicting flexural strengths of fiber-reinforced polymeric composites. Hybrid Advances, 8, p.100385. https://doi.org/10.1016/j.hybadv.2025.100385
  10. Liu, B., Lu, W., Olofsson, T., Zhuang, X. and Rabczuk, T., 2024. Stochastic interpretable machine learning based multiscale modeling in thermal conductivity of Polymeric graphene-enhanced composites. Composite Structures, 327, p.117601. https://doi.org/10.1016/j.compstruct.2023.117601
  11. Li, J., Guan, T., Zhang, Z., Fu, Y.T., Guo, F.L., Huang, P., Li, Z., Li, Y.Q. and Fu, S.Y., 2025. Orientation of discontinuous fillers in polymer composites: modelling, characterization, control and applications. Progress in Materials Science, 148, p.101360. https://doi.org/10.1016/j.pmatsci.2024.101360
  12. D. Kumar, P. William, S. Raghunathrao Deshmukh, A. Sharmila, K. Kaushik and J. Shreyas, “Optimizing Litter Detection in Images: An Integration of Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs),” in IEEE Access, vol. 14, pp. 3325-3344, 2026, doi: 10.1109/ACCESS.2025.3646075.
  13. Anber Abraheem Shlash Mohammad, N. Yogeesh, Suleiman Ibrahim Shelash Mohammad, N. Raja, Lingaraju, P. William, Asokan Vasudevan, Nawaf Alshdaifat, and Mohammad Faleh Ahmmad Hunitie. 2025. An Intuitionistic Fuzzy Graph Model: Matrix Representations and Applications. Cybern. Inf. Technol. 25, 4 (Dec 2025), 3–19. https://doi.org/10.2478/cait-2025-0030
  14. Ma, L., Hamidinejad, M., Wei, L., Zhao, B. and Park, C.B., 2023. Absorption-dominant EMI shielding polymer composite foams: Microstructure and geometry optimization. Materials Today Physics, 30, p.100940. https://doi.org/10.1016/j.mtphys.2022.100940
  15. Li, P., Ma, S., Wang, B., Xu, X., Feng, H., Yu, Z., Yu, T., Liu, Y. and Zhu, J., 2022. Degradable benzyl cyclic acetal epoxy monomers with low viscosity: Synthesis, structure-property relationships, application in recyclable carbon fiber composite. Composites Science and Technology, 219, p.109243. https://doi.org/10.1016/j.compscitech.2021.109243
  16. Zhang, Z., Liu, Q. and Wu, D., 2022. Predicting stress–strain curves using transfer learning: Knowledge transfer across polymer composites. Materials & Design, 218, p.110700. https://doi.org/10.1016/j.matdes.2022.110700
  17. Wang, B., Waterhouse, G.I., Yang, B. and Lu, S., 2024. Advances in shell and core engineering of carbonized polymer dots for enhanced applications. Accounts of Chemical Research, 57(19), pp.2928-2939. https://doi.org/10.1021/acs.accounts.4c00516
  18. Jagadeesh, P., Rangappa, S.M. and Siengchin, S., 2024. Basalt fibers: An environmentally acceptable and sustainable green material for polymer composites. Construction and Building Materials, 436, p.136834. https://doi.org/10.1016/j.conbuildmat.2024.136834
  19. Klebert, S., Vardai, R. and Racz, A., 2025. Machine learning-driven property predictions of polypropylene composites using IR spectroscopy. Composites Science and Technology, 264, p.111127. https://doi.org/10.1016/j.compscitech.2025.111127
  20. V. Kulkarni, P. William, Pravin B Khatkale, Sandip R. Thorat, Santosh Kumar Sharma, Apurv Verma. An Innovative AI-Integrated Approach for Identifying the Tensile Robustness of Polymeric Materials. Journal of Polymer & Composites. 2024; 13(01):90-97.
  21. William, P., Mishra, V.P., Khalaf, O.I., Mukundan, A., N, Y. et al. (2025). Dynamic Multi-Objective Gannet Optimization (DMGO): An Adaptive Algorithm for Efficient Data Replication in Cloud Systems. Computers, Materials & Continua, 84(3), 5133–5156. https://doi.org/10.32604/cmc.2025.065840
  22. Jain, A., Upadhyay, S., Pathik, K., Raj, T., Sahai, A. and Sharma, R.S., 2025. Predictive modelling of flexural behaviour of polymer composites: a machine learning approach through material extrusion. Progress in Additive Manufacturing, 10(8), pp.5135-5153. https://doi.org/10.1007/s40964-024-00893-6
  23. Mohammed, A.J., Mohammed, A.S. and Mohammed, A.S., 2023. Prediction of tribological properties of UHMWPE/SiC polymer composites using machine learning techniques. Polymers, 15(20), p.4057. https://doi.org/10.3390/polym15204057
  24. Wan, Z.L., Zhao, W.C., Qiu, H.K., Zhou, S.S., Chen, S.Y., Fu, C.L., Feng, X.Y., Pan, L.J., Wang, K., He, T.C. and Wang, Y.G., 2024. Data-driven exploration of polymer processing effects on the mechanical properties in carbon black-reinforced rubber composites. Chinese Journal of Polymer Science, 42(12), pp.2038-2047. https://doi.org/10.1007/s10118-024-3216-3
  25. Lakshmaiya, N., Kilari, N., Chukka, N.D.K.R., Kaliappan, S., Rajendran, A. and Maranan, R., 2026. Bayesian-optimized deep neural network surrogate for orientation-driven anisotropic thermal conductivity prediction in hybrid polymer nanocomposites. Results in Engineering, p.110049. https://doi.org/10.1016/j.rineng.2026.110049
  26. Liu, Y., Zheng, W., Ai, H., Cheng, L., Guo, R. and Song, X., 2024. Predicting the thermal conductivity of polymer composites with one-dimensional oriented fillers using the combination of deep learning and ensemble learning. Energy and AI, 18, p.100445. https://doi.org/10.1016/j.egyai.2024.100445
  27. M.V. Kulkarni, P. William, Pravin B Khatkale, Harshal P. Varade, Sandip R. Thorat. Developing an AI-Based Novel Forecasting Framework for Surface Irregularity in Metal Matrix Materials. Journal of Polymer & Composites. 2024; 12(05):48-56.
  28. Yogeesh N, Dr. Lingaraju, Chetana. R, Dr. Vasanthakumari T N, Dr. P. William. Optimization of Biohybrid Polymer Synthesis Using Fuzzy Inference Systems. Journal of Polymer & Composites. 2024; 12(05):36-47.
  29. Azad, M.M., Prabhakar, M.N. and Kim, H.S., 2024. Deep learning-based microscopic damage assessment of fiber-reinforced polymer composites. Materials, 17(21), p.5265. https://doi.org/10.3390/ma17215265
  30. Rani, G.E., Murugeswari, R., Siengchin, S., Rajini, N. and Kumar, M.A., 2022. Quantitative assessment of particle dispersion in polymeric composites and its effect on mechanical properties. Journal of Materials Research and Technology, 19(LA-UR-21-27573). https://doi.org/10.1016/j.jmrt.2022.05.147
  31. Krauklis, A.E., Verceux, F. and Grammatikos, S., 2025. Rapid Non-Destructive Polymer Degradation Degree Evaluation Method Using Quantitative Structure-Property Relationship. Mechanics of Composite Materials, 61(4), pp.699-710. https://doi.org/10.1007/s11029-025-10303-9
  32. Ding, X., Hou, X., Xia, M., Ismail, Y. and Ye, J., 2022. Predictions of macroscopic mechanical properties and microscopic cracks of unidirectional fibre-reinforced polymer composites using deep neural network (DNN). Composite Structures, 302, p.116248. https://doi.org/10.1016/j.compstruct.2022.116248
  33. Saeed, K., McIlhagger, A., Harkin-Jones, E., McGarrigle, C., Dixon, D., Shar, M.A., McMillan, A. and Archer, E., 2022. Characterization of continuous carbon fibre reinforced 3D printed polymer composites with varying fibre volume fractions. Composite Structures, 282, p.115033. https://doi.org/10.1016/j.compstruct.2021.115033
  34. Huseynov, O., Hasanov, S. and Fidan, I., 2023. Influence of the matrix material on the thermal properties of the short carbon fiber reinforced polymer composites manufactured by material extrusion. Journal of Manufacturing Processes, 92, pp.521-533. https://doi.org/10.1016/j.jmapro.2023.02.055
  35. Karamov, R., Akhatov, I. and Sergeichev, I.V., 2022. Prediction of fracture toughness of pultruded composites based on supervised machine learning. Polymers, 14(17), p.3619. https://doi.org/10.3390/polym14173619
  36. Fatriansyah, J.F., Linuwih, B.D.P., Andreano, Y., Sari, I.S., Federico, A., Anis, M., Surip, S.N. and Jaafar, M., 2024. Prediction of Glass Transition Temperature of Polymers Using Simple Machine Learning. Polymers, 16(17), p.2464. https://doi.org/10.3390/polym16172464
Ahead of Print Subscription Original Research
Volume 14
04
Received 12/08/2026
Accepted 27/08/2026
Published 09/09/2026
Publication Time 28 Days

Login

My IP

PlumX Metrics