Paper Titles
Fabrication and Characterization of NaOH-Treated Nito (Lygodium circinnatum) Fiber-Reinforced Composite
p.45
Self‑Propelled Nanomotor Probe Enabled Lateral Flow Immunoassay for Sensitive Detection of Inflammatory Factors
p.53
Development of Cross-Linked Chitosan Films Reinforced with Chitin Nanofibers
p.59
Prediction of Wear Rate for Aluminium-Based Nano and Hybrid Nano-Composites Using Machine Learning
p.65
Tensile Strength Prediction for Crystalline Nanocellulose-Polyvinyl Alcohol Composites Using Machine Learning Algorithms
p.71
Low-Cost Furnace-Grown Silicon Nanoparticles on Nanographite: A New Pathway to Produce LIB Anodes
p.79
Tribo-Corrosion and Wear Resistance of Biomedical Materials: A Comprehensive Review
p.87
Advances in Magnetic Spinel Ferrites as photocatalysts for waste water treatment: A Review
p.103
Retention Time Enhancement of Concrete with Gluconic Acid: An Evaluation of Fresh and Hardened Concrete Properties
p.119

Tensile Strength Prediction for Crystalline Nanocellulose-Polyvinyl Alcohol Composites Using Machine Learning Algorithms

Article Preview

Abstract:

Machine learning (ML) algorithms can improve and innovate the design of new, eco-friendly composite materials. Therefore, this study aims to forecast tensile strength for polyvinyl alcohol composite reinforced by crystalline nanocellulose (CNC) through ML regression algorithms. Moreover, 107 datapoints from the literature were used to train and test ML models. However, this dataset had missing values for the input variables considered, so an Iterative Imputation with an Extra Tree (ET) Regressor model as estimator was performed, which reached a determination coefficient of 0.88. This study implemented five ML algorithms to predict tensile strength: Adaptive Boosting, Extreme Gradient Boosting, Random Forest, ET, and Gradient Boosting (GB). Additionally, a hyperparameter optimization was carried out using the Random Search optimization technique, obtaining that the GB optimized model had the highest precision with a determination coefficient of 0.97. Moreover, it was determined that PVA hydrolysis degree, CNC percentage, and CNC diameter were the most important variables for the GB-optimized model through SHAP analysis.

You might also be interested in these eBooks
Nanomaterials, Functional and Special Materials, Materials Processing View Preview

Info:

Periodical:

Materials Science Forum (Volume 1168)

Pages:

71-78

DOI:

https://doi.org/10.4028/p-Yu6Rpe

Citation:

Cite this paper

Online since:

November 2025

Authors:

Carolina Massay*, Mauricio Cornejo, Haci Baykara

Keywords:

Data Imputation, Hyperparameter Optimization, Machine Learning, Tensile Strength Prediction

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

© 2025 Trans Tech Publications Ltd. All Rights Reserved

Share:

Citation:

* - Corresponding Author

References

[1] Z. Fu, W. Liu, C. Huang, and T. Mei, "A Review of Performance Prediction Based on Machine Learning in Materials Science," Nanomaterials, vol. 12, no. 17, p.2957, Aug. 2022.

DOI: 10.3390/nano12172957

Google Scholar

[2] L. Rahman and J. Goswami, "Poly(Vinyl Alcohol) as Sustainable and Eco-Friendly Packaging: A Review," J Packag Technol Res, vol. 7, no. 1, p.1–10, Mar. 2023.

DOI: 10.1007/s41783-022-00146-3

Google Scholar

[3] T. T. Le, "Prediction of tensile strength of polymer carbon nanotube composites using practical machine learning method," J Compos Mater, vol. 55, no. 6, p.787–811, Mar. 2021.

DOI: 10.1177/0021998320953540

Google Scholar

[4] C. Machello et al., "Tree-based machine learning approach to modelling tensile strength retention of Fibre Reinforced Polymer composites exposed to elevated temperatures," Compos B Eng, vol. 270, Feb. 2024.

DOI: 10.1016/j.compositesb.2023.111132

Google Scholar

[5] O. Yasniy, P. Maruschak, A. Mykytyshyn, I. Didych, and D. Tymoshchuk, "Artificial intelligence as applied to classifying epoxy composites for aircraft," Aviation, vol. 29, no. 1, p.22–29, Feb. 2025.

DOI: 10.3846/aviation.2025.23149

Google Scholar

[6] O. Yasniy, M. Mytnyk, P. Maruschak, A. Mykytyshyn, and I. Didych, "Machine learning methods as applied to modelling thermal conductivity of epoxy-based composites with different fillers for aircraft," Aviation, vol. 28, no. 2, p.64–71, May 2024.

DOI: 10.3846/aviation.2024.21472

Google Scholar

[7] Google Research, "Google colaboratory." [Online]. Available: https://colab.research.google.com/

Google Scholar

[8] G. Van Rossum and F. L. Drake Jr, "Python reference manual," 1995, Centrum voor Wiskunde en Informatica Amsterdam.

Google Scholar

[9] F. Pedregosa et al., "Scikit-learn: Machine Learning in Python," Journal of Machine Learning Research, vol. 12, p.2825–2830, 2011.

Google Scholar

[10] M. Ali, "PyCaret: An open source, low-code machine learning library in Python.," 2020. [Online]. Available: https://pycaret.gitbook.io/docs/

Google Scholar

[11] L. Zhou, H. He, C. Jiang, L. I. Ma, and P. Yu, "Cellulose Nanocrystals from Cotton Stalk for Reinforcement of Poly(Vinyl Alcohol) Composites," Cellulose Chemistry and Technology, vol. 51, no. 1–2, p.109–119, 2017.

Google Scholar

[12] J. Lamaming, R. Hashim, C. P. Leh, O. Sulaiman, and S. Z. Lamaming, "Bio-nanocomposite Films Reinforced with Various Types of Cellulose Nanocrystals Isolated from Oil Palm Biomass Waste," Waste Biomass Valorization, vol. 11, no. 12, p.7017–7027, Dec. 2020.

DOI: 10.1007/s12649-019-00892-7

Google Scholar

[13] Z. Kassab, Y. Abdellaoui, M. H. Salim, R. Bouhfid, A. E. K. Qaiss, and M. El Achaby, "Micro- and nano-celluloses derived from hemp stalks and their effect as polymer reinforcing materials," Carbohydr Polym, vol. 245, Oct. 2020.

DOI: 10.1016/j.carbpol.2020.116506

Google Scholar

[14] M. El Achaby, Z. Kassab, A. Aboulkas, C. Gaillard, and A. Barakat, "Reuse of red algae waste for the production of cellulose nanocrystals and its application in polymer nanocomposites," Int J Biol Macromol, vol. 106, p.681–691, Jan. 2018.

DOI: 10.1016/j.ijbiomac.2017.08.067

Google Scholar

[15] Z. Kassab, M. El Achaby, Y. Tamraoui, H. Sehaqui, R. Bouhfid, and A. E. K. Qaiss, "Sunflower oil cake-derived cellulose nanocrystals: Extraction, physico-chemical characteristics and potential application," Int J Biol Macromol, vol. 136, p.241–252, Sep. 2019.

DOI: 10.1016/j.ijbiomac.2019.06.049

Google Scholar

[16] T. M. Ejara, S. Balakrishnan, and J. C. Kim, "Nanocomposites of PVA/cellulose nanocrystals: Comparative and stretch drawn properties," SPE Polymers, vol. 2, no. 4, p.288–296, Oct. 2021.

DOI: 10.1002/pls2.10057

Google Scholar

[17] F. Yudhanto, Jamasri, H. S. B. Rochardjo, and A. Kusumaatmaja, "Experimental study of polyvinyl alcohol nanocomposite film reinforced by cellulose nanofibers from agave cantala," International Journal of Engineering, Transactions A: Basics, vol. 34, no. 4, p.987–998, Apr. 2021.

DOI: 10.5829/ije.2021.34.04a.25

Google Scholar

[18] E. Fortunati, D. Puglia, M. Monti, C. Santulli, M. Maniruzzaman, and J. M. Kenny, "Cellulose nanocrystals extracted from okra fibers in PVA nanocomposites," J Appl Polym Sci, vol. 128, no. 5, p.3220–3230, Jun. 2013.

DOI: 10.1002/app.38524

Google Scholar

[19] B. Kord, B. Malekian, H. Yousefi, and A. Najafi, "Preparation and characterization of nanofibrillated cellulose/Poly (vinyl alcohol) composite films," Maderas: Ciencia y Tecnologia, vol. 18, no. 4, p.743–752, 2016.

DOI: 10.4067/S0718-221X2016005000065

Google Scholar

[20] S. Aprilia, N. Razali, Y. Syamsuddin, A. H. P. S. Khalil, and D. Syafrina, "Composites polyvinyl alcohol filled with nanocellulose from oil palm waste by formic acid hydrolysis," MATEC Web of Conferences, vol. 268, p.04012, 2019.

DOI: 10.1051/matecconf/201926804012

Google Scholar

[21] L. Jasmani and S. Adnan, "Preparation and characterization of nanocrystalline cellulose from Acacia mangium and its reinforcement potential," Carbohydr Polym, vol. 161, p.166–171, Apr. 2017.

DOI: 10.1016/j.carbpol.2016.12.061

Google Scholar

[22] Z. Jahan, M. B. K. Niazi, and Ø. W. Gregersen, "Mechanical, thermal and swelling properties of cellulose nanocrystals/PVA nanocomposites membranes," Journal of Industrial and Engineering Chemistry, vol. 57, p.113–124, Jan. 2018.

DOI: 10.1016/j.jiec.2017.08.014

Google Scholar

[23] M. Roohani, Y. Habibi, N. M. Belgacem, G. Ebrahim, A. N. Karimi, and A. Dufresne, "Cellulose whiskers reinforced polyvinyl alcohol copolymers nanocomposites," Eur Polym J, vol. 44, no. 8, p.2489–2498, Aug. 2008.

DOI: 10.1016/j.eurpolymj.2008.05.024

Google Scholar

[24] B. H. Patel and P. V. Joshi, "Banana Nanocellulose Fiber/PVOH Composite Film as Soluble Packaging Material: Preparation and Characterization," J Packag Technol Res, vol. 4, no. 1, p.95–101, Mar. 2020.

DOI: 10.1007/s41783-020-00083-z

Google Scholar

[25] T. Sultana, S. Sultana, H. P. Nur, and M. W. Khan, "Studies on mechanical, thermal and morphological properties of betel nut husk nano cellulose reinforced biodegradable polymer composites," Journal of Composites Science, vol. 4, no. 3, 2020.

DOI: 10.3390/jcs4030083

Google Scholar

[26] M. Mahardika et al., "Nanocellulose reinforced polyvinyl alcohol-based bio-nanocomposite films: improved mechanical, UV-light barrier, and thermal properties," RSC Adv, vol. 14, no. 32, p.23232–23239, Jul. 2024.

DOI: 10.1039/d4ra04205k

Google Scholar

[27] M. J. Cho and B. D. Park, "Tensile and thermal properties of nanocellulose-reinforced poly(vinyl alcohol) nanocomposites," Journal of Industrial and Engineering Chemistry, vol. 17, no. 1, p.36–40, Jan. 2011.

DOI: 10.1016/j.jiec.2010.10.006

Google Scholar

[28] Z. Zhang, X. Liu, H. X. Wang, H. F. He, and R. Bai, "Preparation and characterization of Enteromorpha prolifera nanocellulose/polyvinyl alcohol composite films," Polym Compos, vol. 42, no. 4, p.1712–1726, Apr. 2021.

DOI: 10.1002/pc.25926

Google Scholar

[29] F. Handoko and Y. Yusuf, "Synthesis and physicochemical properties of poly(Vinyl) alcohol nanocomposites reinforced with nanocrystalline cellulose from tea (camellia sinensis) waste," Materials, vol. 14, no. 23, Dec. 2021.

DOI: 10.3390/ma14237154

Google Scholar

[30] M. Suresh, R. Taib, Y. Zhao, and W. Jin, "Sharpening the BLADE: Missing Data Imputation Using Supervised Machine Learning," in AI 2019: Advances in Artificial Intelligence, vol. 11919, J. Liu and J. Bailey, Eds., Cham: Springer International Publishing, 2019.

DOI: 10.1007/978-3-030-35288-2

Google Scholar

[31] Z. Wang, L. Mu, H. Miao, Y. Shang, H. Yin, and M. Dong, "An innovative application of machine learning in prediction of the syngas properties of biomass chemical looping gasification based on extra trees regression algorithm," Energy, vol. 275, p.127438, Jul. 2023.

DOI: 10.1016/j.energy.2023.127438

Google Scholar

[32] L. Yang and A. Shami, "On hyperparameter optimization of machine learning algorithms: Theory and practice," Neurocomputing, vol. 415, p.295–316, Nov. 2020.

DOI: 10.1016/j.neucom.2020.07.061

Google Scholar

[33] B. S. Chandar, P. Ranganathan, and W. Semke, "Imputing ADS-B/GPS Dropouts using Machine Learning Models," in 2024 IEEE 14th Annual Computing and Communication Workshop and Conference (CCWC), IEEE, Jan. 2024, p.0063–0072.

DOI: 10.1109/CCWC60891.2024.10427858

Google Scholar

[34] Y. Zhang and X. Xu, "Machine learning tensile strength and impact toughness of wheat straw reinforced composites," Machine Learning with Applications, vol. 6, p.100188, Dec. 2021.

DOI: 10.1016/j.mlwa.2021.100188

Google Scholar

[35] S. Dong, X. Wu, X. Qi, C. Affolter, G. P. Terrasi, and G. Xian, "Prediction model of long-term tensile strength of glass fiber reinforced polymer bars exposed to alkaline solution based on Bayesian optimized artificial neural network," Constr Build Mater, vol. 400, p.132885, Oct. 2023.

DOI: 10.1016/j.conbuildmat.2023.132885

Google Scholar

[36] B. Liu, N. Vu-Bac, X. Zhuang, X. Fu, and T. Rabczuk, "Stochastic integrated machine learning based multiscale approach for the prediction of the thermal conductivity in carbon nanotube reinforced polymeric composites," Compos Sci Technol, vol. 224, p.109425, Jun. 2022.

DOI: 10.1016/j.compscitech.2022.109425

Google Scholar