Computational Intelligence and Neuro-Fuzzy Modelling of Polymer Composites: A Critical Review of Performance Prediction and Optimization

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

K. Kiruthiga,

R. Venkata Krishnaiah,

K. Vijay Bhaskar Raju,

  1. Research Scholar, Department of Civil Engineering, Bharath Institute of Science and Technology, Bharath Institute of Higher Education and Research, Tamil Nadu, India
  2. Professor, Department of Civil Engineering, Bharath Institute of Science and Technology, Bharath Institute of Higher Education and Research, Tamil Nadu, India
  3. Professor, Department of Civil Engineering, Bharath Institute of Science and Technology, Bharath Institute of Higher Education and Research, Tamil Nadu, India

Abstract

The increased variety in polymer matrices, reinforcements, fillers, and processing parameters has led to the need to better understand the structure-property, process-property relationships in order to accurately predict and optimize the performance of polymer composites. This paper reviews the applications of computational intelligence methods in polymer composites, with special focus on artificial neural networks, adaptive neuro-fuzzy inference systems, machine learning techniques, and hybrid optimization. The literature is analyzed based on the polymer matrix used, reinforcement or filler type, processing parameters, input/output of the models, predicted property, dataset, validation, and optimization techniques. Special attention is paid to neuro-fuzzy models due to their application in nonlinear relationships including multiple material and processing parameters.

This review further explores the progression from forward property prediction to formulation and process optimization, which incorporates the use of hybrid predictive-optimization methodologies. As opposed to evaluating the models purely based on their statistical precision, the review takes into account the factors of data quality, validation, generalizability, interpretability, uncertainties, and experimental validation of the computationally optimized conditions. Limitations that remain constant due to issues like heterogeneity of datasets, non-consistency in validation measures, and lack of experimental validation of the computationally optimized conditions are pointed out. The future scope of research on the same lines is suggested by focusing on standard polymer-composite datasets, uncertainty-aware modeling, physics-informed computational methods, and data-driven experimental validation.

Keywords: The increased variety in polymer matrices, reinforcements, fillers, and processing parameters has led to the need to better understand the structure-property, process-property relationships in order to accurately predict and optimize the performance of polymer composites.

How to cite this article: K. Kiruthiga, R. Venkata Krishnaiah, K. Vijay Bhaskar Raju. Computational Intelligence and Neuro-Fuzzy Modelling of Polymer Composites: A Critical Review of Performance Prediction and Optimization. Journal of Polymer & Composites. 2026; 14(04):-.
How to cite this URL: K. Kiruthiga, R. Venkata Krishnaiah, K. Vijay Bhaskar Raju. Computational Intelligence and Neuro-Fuzzy Modelling of Polymer Composites: A Critical Review of Performance Prediction and Optimization. Journal of Polymer & Composites. 2026; 14(04):-. Available from: https://journals.stmjournals.com/jopc/article=2026/view=255073

References

  1. Zhang Z, Friedrich K. Artificial neural networks applied to polymer composites: a review. Compos Sci Technol. 2003;63(14):2029-2044. doi:10.1016/S0266-3538(03)00106-4.
  2. Boumaaza M, Belaadi A, Alshahrani H, Alshaikh I, Ghernaout D. Modeling and optimization of tensile properties of epoxy biocomposites reinforced with Washingtonia robusta waste and biochar using response surface methodology, artificial neural networks, and multi-criteria decision-making. J Nat Fibers. 2025;22:2540475. doi:10.1080/15440478.2025.2540475.
  3. Mathur S, Gope PC, Sharma JK. Prediction of fatigue lives of composite materials by artificial neural network. In: Proceedings of the SEM 2007 Annual Conference and Exposition on Experimental and Applied Mechanics; 2007. p. 1017-1024.
  4. C H, Swamy RP. Fatigue life prediction of glass fiber reinforced epoxy composites using artificial neural networks. Compos Commun. 2021;26:100812. doi:10.1016/j.coco.2021.100812.
  5. Al-Assadi M, El Kadi H, Deiab I. Predicting the fatigue life of different composite materials using artificial neural networks. Appl Compos Mater. 2010;17:1-14. doi:10.1007/s10443-009-9090-x.
  6. El Kadi H, Al-Assaf Y. The use of neural networks in the prediction of the fatigue life of different composite materials. In: Proceedings of the 16th International Conference on Composite Materials; 2007 Jul 8-13; Kyoto, Japan. p. 1-9.
  7. Vassilopoulos A, Georgopoulos E, Dionysopoulos V. Artificial neural networks in spectrum fatigue life prediction of composite materials. Int J Fatigue. 2007;29(1):20-29. doi:10.1016/j.ijfatigue.2006.03.004.
  8. Sharma A, Mukhopadhyay T, Rangappa SM, Siengchin S, Kushvaha V. Advances in computational intelligence of polymer composite materials: machine learning-assisted modeling, analysis and design. Arch Comput Methods Eng. 2022;29:3341-3385. doi:10.1007/s11831-021-09700-9.
  9. Şahin I, Bektaş A, Gül F, Cınıcı H. Modeling of wear behavior of Al/B4C composites produced by powder metallurgy. Mater Test. 2017;59:491-496. doi:10.3139/120.111028.
  10. Fazilat H, Ghatarband M, Mazinani S, Asadi Z, Shiri ME, Kalaee MR. Predicting the mechanical properties of glass fiber reinforced polymers via artificial neural network and adaptive neuro-fuzzy inference system. Comput Mater Sci. 2012;58:31-37. doi:10.1016/j.commatsci.2012.01.012.
  11. Shatti K. Prediction of the wear rates of epoxy-based nanocomposites using artificial neural network approach. J Al-Azhar Univ Eng Sector. 2022;17:569-576. doi:10.21608/auej.2022.233841.
  12. Hamdia K, Zhuang X, Rabczuk T. An efficient optimization approach for designing machine learning models based on genetic algorithm. Neural Comput Appl. 2021;33. doi:10.1007/s00521-020-05035-x.
  13. Mohamed R. Modeling of dielectric behavior of polymer nanocomposites using adaptive neuro-fuzzy inference system (ANFIS). Eur Phys J Plus. 2022;137:384. doi:10.1140/epjp/s13360-022-02518-9.
  14. Jang JSR. ANFIS: adaptive-network-based fuzzy inference system. IEEE Trans Syst Man Cybern. 1993;23(3):665-685. doi:10.1109/21.256541.
  15. Tobi O, Jamiru T, Daniyan I, Sadiku R, Ogunbiyi O, Adesina O, et al. Mechanical property prediction of SPS processed GNP/poly(lactic acid) (PLA) polymer nanocomposite using artificial neural network. Cogent Eng. 2020;7. doi:10.1080/23311916.2020.1720894.
  16. Daniyan I, Tlhabadira I, Mpofu K, Adeodu A. Development of numerical models for the prediction of temperature and surface roughness during the machining operation of titanium alloy (Ti6Al4V). Acta Polytech. 2020;60:369-390. doi:10.14311/AP.2020.60.0369.
  17. Khan S, Malik S, Gull N, Saleemi S, Islam A, Butt M. Fabrication and modelling of the macro-mechanical properties of cross-ply laminated fibre-reinforced polymer composites using artificial neural network. Adv Compos Mater. 2019;28:1-15. doi:10.1080/09243046.2019.1573448.
  18. Gyabaah K, Mahoney B, Martey A, Yan C, Mensah P, Li G. Machine learning-assisted polymer and polymer composite design for additive manufacturing. AI Mater. 2026;1. doi:10.3390/aimater1010002.
  19. Shettar M, Shenoy AA, Katagi N. Estimation of mass loss under wear test of nanoclay-epoxy nanocomposite using response surface methodology and artificial neural networks. Sci Rep. 2025;15. doi:10.1038/s41598-025-05263-y.
Ahead of Print Subscription Review Article
Volume 14
04
Received 26/08/2026
Accepted 08/09/2026
Published 09/09/2026
Publication Time 14 Days

Login

My IP

PlumX Metrics