ANALYSIS OF THE APPLICATIONS OF THE DATA-DRIVEN APPROACH IN EVALUATING THE THERMAL-PHYSICAL PROPERTIES OF COMPOSITES
DOI:
https://doi.org/10.20998/2079-0023.2024.02.02Keywords:
data-driven approach, composites, thermo-physical properties, data analysis, mathematical modeling, machine learning, process optimization, simulationsAbstract
This research analyzes the potential and prospects of a data-driven methodology for examining the thermo-physical properties of composite materials. The research is to provide an analysis of the potential and benefits of employing data-driven procedures, especially in contrast to conventional methods. The analysis examines fundamental principles and advanced machine learning approaches utilized in materials science, highlighting their ability to improve the knowledge, optimization, and overall quality of composite materials. This study thoroughly examines the application of neural networks in forecasting thermal characteristics, highlighting its predictive skills and potential to transform the analysis of thermal properties in composite materials. Additionally, the research underscores the growing reliance on big data analytics in addressing complex challenges in material behavior, particularly under variable environmental conditions. A comparison assessment is performed between the data-driven methodology and traditional analytical methodologies, emphasizing the distinct advantages and drawbacks of each. This comparison elucidates how data-driven methodologies can enhance and refine the precision of thermo-physical analysis. The convergence of machine learning and material science is shown to not only facilitate more accurate predictions but also reduce experimentation time and costs. The report also delineates contemporary techniques for measuring and forecasting the thermo-physical properties of composites, emphasizing the advancements in new technologies in recent years. The function of computational tools and computer technology is elaborated upon, especially with the modeling of thermo-physical properties and the simulation of production processes for composite materials. This paper highlights the growing significance of these technologies in enhancing both theoretical and practical dimensions of material science. The research provides novel insights into composite manufacture, thereby advancing the future of materials science and the practical applications of composite materials. The results have significant implications for enhancing production processes, fostering innovation, and progressing the research of composite materials across diverse industries.
References
Wu L., Zhang P., Xu B., Liu J., Yin H., Zhang L., Jiang X., Zhang C., Zhang R., Wang Y., Qu X. Data-driven design of brake pad composites for high-speed trains. Journal of Materials Research and Technology. 2023, vol. 27, pp. 1058–1071. DOI: https://doi.org/10.1016/j.jmrt.2023.09.280.
He Z. C., Huo S. L., Li E., Cheng H. T., Zhang L. M. Data-driven approach to characterize and optimize properties of carbon fiber non-woven composite materials. Composite Structures. 2022, vol. 297, article 115961. DOI: https://doi.org/10.1016/j.compstruct.2022.115961.
Fathidoost M., Yang Y., Oechsner M., Xu B.-X. Data-driven thermal and percolation analyses of 3D composite structures with interface resistance. Materials & Design. 2023, vol. 227, article 111746. DOI: https://doi.org/10.1016/j.matdes.2023.111746.
Ciampaglia A. Data-driven statistical method for the multiscale characterization and modelling of fiber reinforced composites. Composite Structures. 2023, vol. 320, article 117215. DOI: https://doi.org/10.1016/j.compstruct.2023.117215.
Malley S., Reina C., Nacy S., Gilles J., Koohbor B., Youssef G. Predictability of mechanical behavior of additively manufactured particulate composites using machine learning and data-driven approaches. Computers in Industry. 2022, vol. 142, article 103739. DOI: https://doi.org/10.1016/j.compind.2022.103739.
Lvov G. I. Numerical Homogenization of the Thermophysical Properties of Fibrous Composites. Mechanics of Composite Materials. 2022, vol. 58, no. 5, pp. 613–628. DOI: https://doi.org/10.1007/s11029-022-10054-x.
Barkanov E., Akishin P., Namsone E., Auzins J., Morozovs A. Optimization of Pultrusion Processes for an Industrial Application. Mechanics of Composite Materials. 2021, vol. 6, pp. 697–712.
Eleftheroglou N., Zarouchas D., Benedictus R. An adaptive probabilistic data-driven methodology for prognosis of the fatigue life of composite structures. Composite Structures. 2020, vol. 245, article 112386. DOI: https://doi.org/10.1016/j.compstruct.2020.112386.
Huang T., Gao J., Sun Q., Zeng D., Su X., Liu W. K., Chen W. Stochastic nonlinear analysis of unidirectional fiber composites using image-based microstructural uncertainty quantification. Composite Structures. 2021, vol. 260, article 113470. DOI: https://doi.org/10.1016/j.compstruct.2020.113470.
Saenz-Dominguez I., Tena I., Esnaola A., Sarrionandia M., Torre J., Aurrekoetxea J. Design and characterisation of cellular composite structures for automotive crash-boxes manufactured by out of die ultraviolet cured pultrusion. Composites Part B: Engineering. 2019, vol. 160, pp. 217–224. DOI: https://doi.org/10.1016/j.compositesb.2018.10.046.
Tian W., Chao X., Fu M. W., Qi L., Ju L. New numerical algorithm for the periodic boundary condition for predicting the coefficients of thermal expansion of composites. Mechanics of Materials. 2021, vol. 154, article 103737.
Sun Z., Shan Z., Shao T., Li J., Wu X. A multiscale modeling for predicting the thermal expansion behaviors of 3D C/SiC composites considering porosity and fiber volume fraction. Ceramics International. 2021, vol. 47, no. 6, pp. 7925–7936.
Koohbor B., Ravindran S., Kidane A. A multiscale experimental approach for correlating global and local deformation response in woven composites. Composite Structures. 2018, vol. 194, pp. 328–334. DOI: https://doi.org/10.1016/j.compstruct.2018.04.016.
Zhou L., Yuan T. B., Yang X. S., Liu Z. Y., Wang Q. Z., Xiao B. L., Ma Z. Y. Microscale prediction of effective thermal conductivity of CNT/Al composites by finite element method. International Journal of Thermal Sciences. 2022, vol. 171, article 107206.
Wu L., Adam L., Noels L. Micro-mechanics and data-driven based reduced order models for multi-scale analyses of woven composites. Composite Structures. 2021, vol. 270, article 114058. DOI: https://doi.org/10.1016/j.compstruct.2021.114058.
Veenstra S. W. P., Wijskamp S., Rosić B., Akkerman R. Bending behaviour of thermoplastic composites in melt: A data-driven approach. Composites Science and Technology. 2022, vol. 219, article 109220. DOI: https://doi.org/10.1016/j.compscitech.2021.109220.
Cheung H. L., Mirkhalaf M. A multi-fidelity data-driven model for highly accurate and computationally efficient modeling of short fiber composites. Composites Science and Technology. 2024, vol. 246, article 110359. DOI: https://doi.org/10.1016/j.compscitech.2023.110359.
Castricum B. A., Fagerström M., Ekh M., Larsson F., Mirkhalaf S. M. A computationally efficient coupled multi-scale model for short fiber reinforced composites. Composites Part A: Applied Science and Manufacturing. 2022, vol. 163, article 107233. DOI: https://doi.org/10.1016/j.compositesa.2022.107233.
Mirkhalaf S. M., Eggels E. H., van Beurden T. J. H., Larsson F., Fagerström M. A finite element based orientation averaging method for predicting elastic properties of short fiber reinforced composites. Composites Part B: Engineering. 2020, vol. 202, article 108388. DOI: https://doi.org/10.1016/j.compositesb.2020.108388.
Mirkhalaf S. M., van Beurden T. J. H., Ekh M., Larsson F., Fagerström M. An FE-based orientation averaging model for elasto-plastic behavior of short fiber composites. International Journal of Mechanical Sciences. 2022, vol. 219, article 107097. DOI: https://doi.org/10.1016/j.ijmecsci.2022.107097.
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).
