DATA-DRIVEN APPROACH TO PREDICT THE STRENGTH OF COMPOSITES
DOI:
https://doi.org/10.20998/2079-0023.2025.02.03Keywords:
data-driven approach, composites, limit states, stress, machine learning, Random Forest, Logistic RegressionAbstract
The rapid development of composites requires accurate prediction of their limit state under complex loading conditions, which cannot be provided by classical mechanical criteria due to the anisotropy and nonlinearity of materials. The paper proposes a data-driven approach using machine learning to determine the limit state of composites based on the components of the stress tensor. The object of study is machine learning processes for determining the limit states of unidirectional reinforced composites under a multiaxial stress state. The aim of the study is to create a universal and accurate model capable of detecting the moment of reaching the strength limit without numerical modeling and large-scale experiments. Balanced synthetic samples of stress states were generated for three composite systems. Several machine learning models were implemented in the study: logistic regression, random forest, and multilayer perceptron neural network. To compare the effectiveness, the classical model for determining the limit state according to the von Mises criterion, with a fixed equivalent stress threshold for the fibres or the matrix, was also employed. The results show that the machine learning models achieve an accuracy of up to 99.9 % on test samples, significantly outperforming the classical approach, which demonstrates an accuracy of about 50 % in all cases. Visualization of the stress state in the form of 2D sections showed a complex and nonlinear structure of the boundary surface, which confirms the feasibility of using ML algorithms. The obtained results confirm the high effectiveness and reliability of the data-driven approach for structural health assessment of composite systems. The developed methodology is universal and can be adapted to various types of reinforced materials and loading conditions. The proposed approach can be applied in real-time technical diagnostics of composite structures. The work also creates a basis for further implementation of interpreted models and digital twins in the field of composite mechanics.
References
Hamzat A. K., Murad M. S., Adediran I. A., Asmatulu E., Asmatulu R. Fiber-reinforced composites for aerospace, energy, and marine applications: an insight into failure mechanisms under chemical, thermal, oxidative, and mechanical load conditions. Advanced Composites and Hybrid Materials. 2025, vol. 8, no. 1, article 152. DOI: https://doi.org/10.1007/s42114-024-01192-y.
De B., Bera M., Bhattacharjee D., Ray B. C., Mukherjee S. A comprehensive review on fiber-reinforced polymer composites: Raw materials to applications, recycling, and waste management. Progress in Materials Science. 2024, vol. 146, article 101326. DOI: https://doi.org/10.1016/j.pmatsci.2024.101326.
Petrů M., Novák O., Păcurar R. (ed.) FEM analysis of mechanical and structural properties of long fiber-reinforced composites. Finite Element Method – Simulation, Numerical Analysis and Solution Techniques. Chapter 1. London: IntechOpen, 2017. DOI: https://doi.org/10.5772/intechopen.71881.
Markopoulos I., Kouris L.-A., Konstantinidis A. On the use of microstructure characteristics to predict metal matrix composites’ macroscopic mechanical behavior. Applied Sciences. 2023, vol. 13, no. 8, article 4989. DOI: https://doi.org/10.3390/app13084989.
Kibrete F., Trzepieciński T., Gebremedhen H. S., Woldemichael D. E. Artificial intelligence in predicting mechanical properties of composite materials. Journal of Composites Science. 2023, vol. 7, no. 9, article 364. DOI: https://doi.org/10.3390/jcs7090364.
Kirchdoerfer T., Ortiz M. Data-driven computational mechanics. Computer Methods in Applied Mechanics and Engineering. 2016, vol. 304, pp. 81–101. DOI: https://doi.org/10.1016/j.cma.2016.02.001.
Steingrimsson B., Fan X., Kulkarni A., Gao M. C., Liaw P. K. Machine learning and data analytics for design and manufacturing of high-entropy materials exhibiting mechanical or fatigue properties of interest. High-Entropy Materials: Theory, Experiments, and Applications. 2021, pp. 115–238. DOI: https://doi.org/10.1007/978-3-030-77641-1_4.
Liu X., Tian S., Tao F., Du H., Yu W. How machine learning can help the design and analysis of composite materials and structures? arXiv preprint, 2020. arXiv:2010.09438. Available at: https://arxiv.org/abs/2010.09438 (accessed 10.11.2025).
Lvov G., Kostromytska O. A data-driven approach to the prediction of plasticity in composites. Integrated Computer Technologies in Mechanical Engineering. 2020, pp. 3–10. DOI: https://doi.org/10.1007/978-3-030-37618-5_1.
Feng H., Prabhakar P. Difference-based deep learning framework for stress predictions in heterogeneous media. Composite Structures. 2021, vol. 269, article 113957. DOI: https://doi.org/10.1016/j.compstruct.2021.113957.
Liu Z., Wei H., Huang T., Wu C. T. Intelligent multiscale simulation based on process-guided composite database. arXiv preprint, 2020. arXiv:2003.09491. Available at:: https://arxiv.org/abs/2003.09491 (accessed 10.11.2025).
Shah V., Zadourian S., Yang C., Zhang Z., Gu G. X. Data-driven approach for the prediction of mechanical properties of carbon fiber reinforced composites. Materials Advances. 2022, vol. 3, no. 19, pp. 7319–7327. DOI: https://doi.org/10.1039/D2MA00698G.
Le T.-T. Prediction of tensile strength of polymer carbon nanotube composites using practical machine learning method. Journal of Composite Materials. 2021, vol. 55, no. 6, pp. 787–811. DOI: https://doi.org/10.1177/0021998320953540.
Wu Y., Zhou Y. Hybrid machine learning model and Shapley additive explanations for compressive strength of sustainable concrete. Construction and Building Materials. 2022. Vol. 330. Article 127298. DOI: https://doi.org/10.1016/j.conbuildmat.2022.127298.
Nunez I., Marani A., Flah M., Nehdi M. L. Estimating compressive strength of modern concrete mixtures using computational intelligence: A systematic review. Construction and Building Materials. 2021, vol. 310, article 125279. DOI: https://doi.org/10.1016/j.conbuildmat.2021.125279.
Kumar P., Arora H. Ch., Bahrami A., Kumar A., Kumar K. Development of a reliable machine learning model to predict compressive strength of FRP-confined concrete cylinders. Buildings. 2023, vol. 13, no. 4, article 931. DOI: https://doi.org/10.3390/buildings13040931.
Sacco C., Baz Radwan A., Anderson A., Harik R., Gregory E. Machine learning in composites manufacturing: A case study of Automated Fiber Placement inspection. Composite Structures. 2020, vol. 250, article 112514. DOI: https://doi.org/10.1016/j.compstruct.2020.112514.
Brayek B. E. B., Sayed S., Mînzu V., Tarfaoui M. Machine learning predictions for the comparative mechanical analysis of composite laminates with various fibers. Processes. 2025, vol. 13, no. 3, article 602. DOI: https://doi.org/10.3390/pr13030602.
Jung K.-Ch., Chang S.-H. Advanced deep learning model-based impact characterization method for composite laminates. Composites Science and Technology. 2021, vol. 207, article 108713. DOI: https://doi.org/10.1016/j.compscitech.2021.108713.
Salami B. A., Olayiwola T., Oyehan T. A., Raji I. A. Data-driven model for ternary-blend concrete compressive strength prediction using machine learning approach. Construction and Building Materials. 2021, vol. 301, article 124152. DOI:https://doi.org/10.1016/j.conbuildmat.2021.124152.
Moradi M. J., Khaleghi M., Salimi J., Farhangi V., Ramezanianpour A. M. Predicting the compressive strength of concrete containing metakaolin with different properties using ANN. Measurement. 2021, vol. 183, article 109790. DOI: https://doi.org/10.1016/j.measurement.2021.109790.
Azimi-Pour M., Eskandari-Naddaf H., Pakzad A. Linear and non-linear SVM prediction for fresh properties and compressive strength of high volume fly ash self-compacting concrete. Construction and Building Materials. 2020, vol. 230, article 117021. DOI: https://doi.org/10.1016/j.conbuildmat.2019.117021
Ahmad A., Ahmad W., Aslam F., Joyklad P. Compressive strength prediction of fly ash-based geopolymer concrete via advanced machine learning techniques. Case Studies in Construction Materials. 2022, vol. 16, article e00840. DOI: https://doi.org/10.1016/j.cscm.2021.e00840.
Li H., Lin J., Lei X., Wei T. Compressive strength prediction of basalt fiber reinforced concrete via random forest algorithm. Materials Today Communications. 2022, vol. 30, article 103117. DOI: https://doi.org/10.1016/j.mtcomm.2021.103117.
Kouhestani E., Fakoor M. Extension of von-Mises failure criterion for comprehensive mixed-mode I/II fracture assessment of orthotropic materials. International Journal of Solids and Structures. 2025, vol. 315, article 113363. DOI: https://doi.org/10.1016/j.ijsolstr.2025.113363.
Jiang F., Guan Z., Li Z., Wang X. A method of predicting visual detectability of low-velocity impact damage in composite structures based on logistic regression model. Chinese Journal of Aeronautics. 2021, vol. 34, no. 1, pp. 296–308. DOI: https://doi.org/10.1016/j.cja.2020.10.006.
Lim D. K., Mustapha K. B., Pagwiwoko C. P. Delamination detection in composite plates using random forests. Composite Structures. 2021, vol. 278, article 114676. DOI: https://doi.org/10.1016/j.compstruct.2021.114676.
Li M., Li S., Tian Y., Fu Y., Pei Y., Zhu W., Ke Y. A deep learning convolutional neural network and multi-layer perceptron hybrid fusion model for predicting the mechanical properties of carbon fiber. Materials & Design. 2023, vol. 227, article 111760. DOI: https://doi.org/10.1016/j.matdes.2023.111760.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
