Machine Learning-Based Prediction of Thermal Behaviour and Shape Memory Response of 4D Printed PLA/bTPU/Lignin Biocomposites Fabricated by Fused Deposition Modelling

Mohd Romainor Manshor, Amjad Fakhri Kamarulzaman, Hazleen Anua, Yakubu Adekunle Alli

Abstract


This study develops a data-driven framework for predicting the thermal recovery behaviour and shape memory response of biodegradable polymer biocomposites prepared by fused deposition modelling for four-dimensional printing applications. The work addresses the need to reduce trial-and-error experimentation during the design of sustainable thermo-responsive materials. Experimental data from material formulation and thermal recovery testing were used to train and evaluate four regression models: linear regression, support vector regression, random forest, and artificial neural network. Composition, recovery temperature, and recovery time were used as input variables, while recovery angle and shape memory responses were used as target outputs. The artificial neural network achieved the highest coefficient of determination of 0.95 and captured the nonlinear recovery behaviour most consistently. Support vector regression produced the lowest root mean square error of 2.66 and the lowest mean squared error of 7.09, indicating strong numerical accuracy. Random forest showed moderate predictive capability, while linear regression was less effective because of the nonlinear nature of the recovery response. The findings show that artificial neural network modelling provides the most reliable overall prediction for this biocomposite system, while support vector regression is effective for minimizing prediction error. Machine learning can therefore support formulation screening, reduce experimental workload, and guide the development of sustainable shape memory biocomposites for four-dimensional printing applications.

Keywords


Machine learning, 4D printing, shape memory polymer, fused deposition modelling

Full Text:

PDF

References


References

E. H. Tümer and H. Y. Erbil, “Extrusion-based 3d printing applications of pla composites: A review,” 2021. doi: 10.3390/coatings11040390.

S. K. Leist, D. Gao, R. Chiou, and J. Zhou, “Investigating the shape memory properties of 4D printed polylactic acid (PLA) and the concept of 4D printing onto nylon fabrics for the creation of smart textiles,” Virtual Phys. Prototyp., vol. 12, no. 4, pp. 290–300, Oct. 2017, doi: 10.1080/17452759.2017.1341815.

T. Dayyoub, A. V Maksimkin, O. V Filippova, V. V Tcherdyntsev, and D. V Telyshev, “Shape Memory Polymers as Smart Materials: A Review.,” Polymers (Basel)., vol. 14, no. 17, Aug. 2022, doi: 10.3390/polym14173511.

F. Vásquez-Garay, I. Carrillo-Varela, C. Vidal, P. Reyes-Contreras, M. Faccini, and R. Teixeira Mendonça, “A Review on the Lignin Biopolymer and Its Integration in the Elaboration of Sustainable Materials,” Sustainability, vol. 13, no. 5, p. 2697, Mar. 2021, doi: 10.3390/su13052697.

X. Jing, H. Mi, X. Peng, and L. Turng, “The morphology, properties, and shape memory behavior of polylactic acid/thermoplastic polyurethane blends,” Polym. Eng. Sci., vol. 55, no. 1, pp. 70–80, Jan. 2015, doi: 10.1002/pen.23873.

T. S. Tran, R. Balu, S. Mettu, N. Roy Choudhury, and N. K. Dutta, “4D Printing of Hydrogels: Innovation in Material Design and Emerging Smart Systems for Drug Delivery,” Pharmaceuticals, vol. 15, no. 10, p. 1282, Oct. 2022, doi: 10.3390/ph15101282.

X. Colom, F. Carrillo, F. Nogués, and P. Garriga, “Structural analysis of photodegraded wood by means of FTIR spectroscopy,” Polym. Degrad. Stab., vol. 80, no. 3, pp. 543–549, Jan. 2003, doi: 10.1016/S0141-3910(03)00051-X.

M. E. Pekdemir, E. Özen Öner, M. Kök, and A. Cherkezova, “Thermo-responsive shape memory polymer blends based on polylactic acid and polyethylene glycol,” Macromol. Res., vol. 32, no. 10, pp. 929–934, Oct. 2024, doi: 10.1007/s13233-024-00287-1.

O. Gordobil, I. Egüés, R. Llano-Ponte, and J. Labidi, “Physicochemical properties of PLA lignin blends,” Polym. Degrad. Stab., vol. 108, pp. 330–338, Oct. 2014, doi: 10.1016/j.polymdegradstab.2014.01.002.

Q. Mu, C. K. Dunn, L. Wang, M. L. Dunn, H. J. Qi, and T. Wang, “Thermal cure effects on electromechanical properties of conductive wires by direct ink write for 4D printing and soft machines,” Smart Mater. Struct., vol. 26, no. 4, 2017, doi: 10.1088/1361-665X/aa5cca.

D. W. Abueidda, M. Almasri, R. Ammourah, U. Ravaioli, I. M. Jasiuk, and N. A. Sobh, “Prediction and optimization of mechanical properties of composites using convolutional neural networks,” Compos. Struct., vol. 227, Nov. 2019, doi: 10.1016/j.compstruct.2019.111264.

T. Sadat, “Machine Learning-Assisted Tensile Modulus Prediction for Flax Fiber/Shape Memory Epoxy Hygromorph Composites,” Appl. Mech., vol. 4, no. 2, pp. 752–762, Jun. 2023, doi: 10.3390/applmech4020038.

S. K. Leist, “Design of a 4D Printing System using Thermal Sensitive Smart Materials and Photoactivated Shape Changing Polymers,” 2017.

Y. Lee, J. Choi, Y. Choi, S. M. Park, and C. Yoon, “Four-Dimensional Printing of Stimuli-Responsive Hydrogel-Based Soft Robots,” J. Vis. Exp., no. 191, Jan. 2023, doi: 10.3791/64870.

A. Géron, Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow, 3rd Edition. O’Reilly Media, Inc., 2022.

C. Qiu, S. Du, and J. Yang, “A deep learning approach for efficient topology optimization based on the element removal strategy,” Mater. Des., vol. 212, p. 110179, Dec. 2021, doi: 10.1016/j.matdes.2021.110179.

D. Segura Ibarra, J. Mathews, F. Li, H. Lu, G. Li, and J. Chen, “Deep learning for predicting the thermomechanical behavior of shape memory polymers,” Polymer (Guildf)., vol. 261, p. 125395, Nov. 2022, doi: 10.1016/j.polymer.2022.125395.

X. Peng, F. Jiang, and Z. Li, “Enhancing compatibility of polylactic acid and lignin through acetylation for improving controlled release of pesticide,” Pest Manag. Sci., vol. 81, no. 6, pp. 3088–3102, Jun. 2025, doi: 10.1002/ps.8677.

C. K. Fisher et al., “Machine learning for comprehensive forecasting of Alzheimer’s Disease progression,” Sci. Rep., vol. 9, no. 1, Dec. 2019, doi: 10.1038/s41598-019-49656-2.

W. M. Huang et al., “Thermo/chemo-responsive shape memory effect in polymers: a sketch of working mechanisms, fundamentals and optimization,” J. Polym. Res., vol. 19, no. 9, p. 9952, Sep. 2012, doi: 10.1007/s10965-012-9952-z.

O. Gordobil, R. Herrera, R. Llano-Ponte, and J. Labidi, “Esterified organosolv lignin as hydrophobic agent for use on wood products,” Prog. Org. Coatings, vol. 103, pp. 143–151, Feb. 2017, doi: 10.1016/j.porgcoat.2016.10.030.

A. Darnal, Z. Shahid, H. Deshpande, J. Kim, and A. Muliana, “Tuning mechanical properties of 3D printed composites with PLA:TPU programmable filaments,” Compos. Struct., vol. 318, p. 117075, Aug. 2023, doi: 10.1016/j.compstruct.2023.117075.

E. S. Esakkimuthu, V. Ponnuchamy, M. H. Sipponen, and D. DeVallance, “Elucidating intermolecular forces to improve compatibility of kraft lignin in poly(lactic acid).,” Front. Chem., vol. 12, p. 1347147, 2024, doi: 10.3389/fchem.2024.1347147.

C. Yan, X. Feng, and G. Li, “From Drug Molecules to Thermoset Shape Memory Polymers: A Machine Learning Approach,” ACS Appl. Mater. Interfaces, vol. 13, no. 50, pp. 60508–60521, Dec. 2021, doi: 10.1021/acsami.1c20947.

S. Frasca et al., “Compatibility of Kraft Lignin and Phenol-Organosolv Lignin with PLA in 3D Printing and Assessment of Mechanical Recycling,” ACS Appl. Polym. Mater., vol. 6, no. 22, pp. 13574–13584, Nov. 2024, doi: 10.1021/acsapm.4c02208.




DOI: http://dx.doi.org/10.52155/ijpsat.v58.2.8534

Refbacks

  • There are currently no refbacks.


Copyright (c) 2026 Mohd Romainor Manshor

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.