Comparative Analysis of Artificial Intelligence Algorithms for Predicting the Elastic Modulus of Recycled Polypropylene-Tea Residue Composites
Article Sidebar
Main Article Content
บทคัดย่อ
This study evaluates the effectiveness of different artificial intelligence (AI) algorithms in forecasting the elastic modulus of recycled polypropylene-tea residue composites. The research seeks to determine the most precise algorithm for this predictive task, thus aiding in the advancement of sustainable materials. Composite samples were formulated utilizing residues from Thai and green tea, with different proportions of polypropylene-graft-maleic anhydride (PP-g-MA) and thermoplastic elastomer (TPE). The elastic modulus of these samples was experimentally determined. Five artificial intelligence algorithms were assessed: Generalized Linear Model, Decision Tree, Random Forest, Support Vector Machine (SVM), and Artificial Neural Network (ANN). Performance metrics, such as Root Mean Square Error (RMSE), Relative Error, R², and P-value, were employed for comparison.
The results demonstrate that the ANN achieved the greatest prediction accuracy, evidenced by a R² value of 0.883 and the minimal relative error of 3.11% ± 0.47%. The Decision Tree and Random Forest algorithms exhibited commendable performance, whereas the SVM yielded the least accurate predictions. The research indicates that the correlation between composite formulation and elastic modulus is significantly non-linear, requiring advanced modeling methodologies. This study identifies the optimal AI algorithm for predicting the elastic modulus of these composites and elucidates the intricate interactions within the material system. The results have considerable implications for expediting the advancement and refinement of sustainable composite materials that incorporate recycled and natural elements.
Article Details
อนุญาตภายใต้เงื่อนไข Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
• บทความทุกเรื่องได้รับการตรวจสอบทางวิชาการโดยผู้ทรงคุณวุฒิ จำนวน 3 ท่าน ต่อ 1 เรื่อง จากภายในและภายนอกวิทยาลัยบัณฑิตเอเซีย
• การตีพิมพ์และเผยแพร่ของวารสารวิทยาลัยบัณฑิตเอเซียนี้ เนื้อหาบทความ ทรรศนะและข้อคิดเห็นใด ๆ ในวารสารถือว่าเป็นของผู้เขียน โดยเฉพาะทางกองบรรณาธิการวารสาร หรือวิทยาลัยบัณฑิตเอเซีย ไม่จำเป็นต้องเห็นด้วย
เอกสารอ้างอิง
Bezerra, E., Ancelotti, A., Pardini, L., Rocco, J., Iha, K., & Ribeiro, C. (2007). Artificial neural networks applied to epoxy composites reinforced with carbon and E-glass fibers: Analysis of the shear mechanical properties. Materials Science and Engineering A, 464(1–2); 177–185.
Brown, D. A., Murthy, P. L. N., & Berke, L. (1991). Computational simulation of composite ply micromechanics using artificial neural networks. Computer-Aided Civil and Infrastructure Engineering, 6(2); 87–97.
Burgada, F., Fages, E., Quiles-Carrillo, L., Lascano, D., Ivorra-Martinez, J., Arrieta, M. P., & Fenollar, O. (2021). Upgrading Recycled Polypropylene from Textile Wastes in Wood Plastic Composites with Short Hemp Fiber. Polymers, 13(8), 1248.
Chiu, M. C., Pun, C. S., & Wong, H. Y. (2017). Big Data challenges of High‐Dimensional Continuous‐Time Mean‐Variance Portfolio Selection and a Remedy. Risk Analysis, 37(8); 1532–1549.
Cipolla, S., & Gondzio, J. (2022). Training very large scale nonlinear SVMs using Alternating Direction Method of Multipliers coupled with the Hierarchically Semi-Separable kernel approximations. EURO Journal on Computational Optimization, 10; 100046.
Cursi, F., & Yang, G. Z. (2019). A novel approach for outlier detection and robust sensory data model learning. In 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (pp. 4250-4257). IEEE.
Esmaeili, H., & Rizvi, R. (2023, April). Machine learning predictions and benchmarking of non-linear mechanical behavior of polymer composites. In Behavior and Mechanics of Multifunctional Materials XVII, 12484; 128-134.
Fini, S. H. A., Farzaneh, M., & Erchiqui, F. (2015). Study of the elastic behaviour of wood–plastic composites at cold temperatures using artificial neural networks. Wood Science and Technology, 49(4); 695–705.
Galimzyanov, B. N., Doronina, M. A., & Mokshin, A. V. (2023). Machine learning-based prediction of elastic properties of amorphous metal alloys. Physica a Statistical Mechanics and Its Applications, 617, 128678.
Garcia-Milian, R., Hersey, D., Vukmirovic, M., & Duprilot, F. (2018). Data challenges of biomedical researchers in the age of omics. PeerJ, 6, e5553.
Hasan, M., Hoque, M. E., & Sapuan, S. M. (2009). Application of artificial neural network in composites materials. In CRC Press eBooks, 17–26.
Heit, D. R., Ortiz‐Calo, W., Poisson, M. K. P., Butler, A. R., & Moll, R. J. (2024). Generalized nonlinearity in animal ecology: Research, review, and recommendations. Ecology and Evolution, 14(7).
Ho, N. X., Le, T., & Le, M. V. (2021). Development of artificial intelligence based model for the prediction of Young’s modulus of polymer/carbon-nanotubes composites. Mechanics of Advanced Materials and Structures, 29(27); 5965–5978.
Insolia, L., Chiaromonte, F., & Riani, M. (2021). A robust estimation approach for Mean-Shift and Variance-Inflation outliers. Springer eBooks; 17–41.
Johnstone, I. M., & Titterington, D. M. (2009). Statistical challenges of high-dimensional data. Philosophical Transactions of the Royal Society a Mathematical Physical and Engineering Sciences, 367(1906); 4237–4253.
Kongrit, A., Limsiri, C., & Meehom, S. (2024a). The influence of polypropylene-grafted-maleic anhydride and thermoplastic elastomer on the tensile properties of recycled polypropylene composites with Thai tea waste. Proceedings of the 2nd National Conference on Science and Technology, Faculty of Science and Technology, Chiang Mai Rajabhat University, 112–140.
Kongrit, A., Limsiri, C., & Meehom, S. (2024b). Application of generative artificial intelligence in studying the effects of additives on the mechanical properties of recycled polypropylene composites with green tea waste. Proceedings of the 15th Conference on Engineering, Technology, and Architecture, 50th Anniversary Thai-German Building, Khon Kaen, Rajamangala University of Technology Isan, Khon Kaen Campus, 913–929.
Lin, T. A., Lin, M., Lin, J., Lin, J., Chuang, Y., & Lou, C. (2020). Modified polypropylene/ thermoplastic polyurethane blends with maleic-anhydride grafted polypropylene: blending morphology and mechanical behaviors. Journal of Polymer Research, 27(2).
May, R. J., Maier, H. R., Dandy, G. C., & Fernando, T. G. (2008). Non-linear variable selection for artificial neural networks using partial mutual information. Environmental Modelling & Software, 23(10–11); 1312–1326.
McCullagh, P., & Nelder, J. A. (2005). Generalized Linear Models. In Springer eBooks, 291–303.
Park, T., Kim, Y., Bekiranov, S., & Lee, J. K. (2007). Error-pooling-based statistical methods for identifying novel temporal replication profiles of human chromosomes observed by DNA tiling arrays. Nucleic Acids Research, 35(9), e69.
Perez, H., & Tah, J. H. M. (2020). Improving the accuracy of convolutional neural networks by identifying and removing outlier images in datasets using T-SNE. Mathematics, 8(5), 662.
Pidaparti, R. M. V., & Palakal, M. J. (1993). Material model for composites using neural networks. AIAA Journal, 31(8); 1533–1535.
Ragunathan, S., Nurul, S. O., Abdillahi, K. M., & Ismail, H. (2016). Effect of maleic anhydride‐grafted polypropylene on polypropylene/recycled acrylonitrile butadiene rubber/empty fruit bunch composite. Journal of Vinyl and Additive Technology, 24(3); 275–280.
Rahnenführer, J., De Bin, R., Benner, A., Ambrogi, F., Lusa, L., Boulesteix, A., Migliavacca, E., Binder, H., Michiels, S., Sauerbrei, W., & McShane, L. (2023). Statistical analysis of high-dimensional biomedical data: a gentle introduction to analytical goals, common approaches and challenges. BMC Medicine, 21(1).
Rudar, J., Golding, G. B., Kremer, S. C., & Hajibabaei, M. (2023). Decision tree ensembles utilizing multivariate splits are effective at investigating beta diversity in medically relevant 16S amplicon sequencing data. Microbiology Spectrum, 11(2). https://doi.org/10.1128/spectrum.02065-22
Spear, M., Eder, A., & Carus, M. (2015). Wood polymer composites. In Elsevier eBooks (pp. 195–249).
Taskin, Z. I., Yildirak, K., & Aladag, C. H. (2023). An enhanced random forest approach using CoClust clustering: MIMIC-III and SMS spam collection application. Journal of Big Data, 10(1).
Tang, C. Y., Fang, E. X., & Dong, Y. (2020). High-dimensional interactions detection with sparse principal hessian matrix. Journal of Machine Learning Research, 21(19); 1-25.
Upadhyay, A., & Singh, R. (2014). Use of Artificial Neural Network and Theoretical Modeling to Predict the Effective Elastic Modulus of Composites with Ellipsoidal Inclusions. OALib, 01(07), 1–14.
Vercher, J., Fombuena, V., Diaz, A., & Soriano, M. (2018). Influence of fibre and matrix characteristics on properties and durability of wood–plastic composites in outdoor applications. Journal of Thermoplastic Composite Materials, 33(4); 477–500.
Yoo, R. M., Lee, H., Chow, K., & Hsien-hsin, S. L. (2006, October). Constructing a non-linear model with neural networks for workload characterization. In 2006 IEEE International Symposium on Workload Characterization, 150-159.
Zhao, X., Copenhaver, K., Wang, L., Korey, M., Gardner, D. J., Li, K., Lamm, M. E., Kishore, V., Bhagia, S., Tajvidi, M., Tekinalp, H., Oyedeji, O., Wasti, S., Webb, E., Ragauskas, A. J., Zhu, H., Peter, W. H., & Ozcan, S. (2021). Recycling of natural fiber composites: Challenges and opportunities. Resources Conservation and Recycling, 177, 105962.
Zulfia, A., Mohar, R. S., & Saptoraharjo, A. W. (2015). Effect of Grafting with Maleic Anhydride on Interfacial Bonding of Rubber Wood Flour Filled Poly(propylene) Composite. Macromolecular Symposia, 353(1), 39–46.
