STM Journals Peer-reviewed research from Consortium e-Learning Network

Journal of Polymer & Composites Original Research

ML-Based Predictive Modeling of Mechanical Properties in 3D-Printed Polymer Composites for IoT Applications

  1. Nagaraj G Department of Mechanical Engineering, Sethu Institute of Technology
  2. Dillip Kumar Mohanta Department of Mechanical Engineering, Centurion University of Technology and Management
  3. Rajvardhan Jigyasu Department of Electrical Engineering, Netaji Subhas University of Technology
  4. P. Vidyullatha Department of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation, Vaddeswaram, Guntur
  5. Joshila Grace L K Department of Computer Science and Engineering, Sathyabama Institute of Science and Technology, Chennai
  6. Muthukumar Subramanian Department of Computer Science and Engineering, Hindustan Institute of Technology & Science (Deemed to be University), Chennai

Abstract

This study aims to develop an interpretable and high-accuracy machine learning framework for predicting the mechanical properties of 3D-printed fiber-reinforced polymer composites, with a focus on structure–property correlations relevant to polymer processing and functional performance. Composite specimens based on PLA and ABS matrices were fabricated using FDM with varying weight fractions (5–20 wt%) of carbon and glass fibers. Standardized mechanical testing (ASTM D638, D256, D790) was performed to evaluate tensile strength, elastic modulus, and impact resistance across 324 printed samples. A structured dataset comprising 12 input features including material and processing parameters was used to train XGBoost, SVR, and Random Forest regression models. Recursive feature elimination and SHAP-based explain ability were integrated to ensure dimensional relevance and interpretability. XGBoost outperformed all baseline models, achieving an R² of 0.94 and RMSE below 2.1 MPa. SHAP analysis identified filler wt%, nozzle temperature, and infill density as the most influential parameters. Visualizations such as 3D correlation plots and formulation-specific prediction collages validated prediction accuracy and exposed localized error patterns in high-filler composites. This work uniquely integrates real mechanical data, SHAP explain ability, and multiscale visualization into a predictive framework, offering physically grounded, design-relevant insights for polymer composite development an advancement over existing black-box approaches. The proposed framework establishes a reproducible, transparent methodology for data-driven prediction of polymer composite behavior, enabling intelligent design optimization in reinforced thermoplastics and opening avenues for future adaptive modeling.

Keywords

References (23)

  1. Rooney K, Dong Y, Basak AK, Pramanik A. Prediction of Mechanical Properties of 3D Printed Particle-Reinforced Resin Composites. Journal of Composites Science. 2024;8(10):416. doi:10.3390/jcs8100416
  2. Sharma A, Mukhopadhyay T, Rangappa SM, Siengchin S, Kushvaha V. Advances in Computational Intelligence of Polymer Composite Materials: Machine Learning Assisted Modeling, Analysis and Design. Archives of Computational Methods in Engineering. 2022;29(5):3341-3385. doi:10.1007/s11831-021-09700-9
  3. Champa-Bujaico E, García-Díaz P, Díez-Pascual AM. Machine Learning for Property Prediction and Optimization of Polymeric Nanocomposites: A State-of-the-Art. International Journal of Molecular Sciences. 2022;23(18):10712. doi:10.3390/ijms231810712
  4. Mamodiya U, Kishor I. A Comparative Study on the Performance of DualAxis Solar Tracking Systems and Fixed Solar Arrays. Proceedings of the 5th International Conference on Information Management & Machine Intelligence. 2023:1-4. doi:10.1145/3647444.3647943
  5. Nawafleh N, AL-Oqla FM. Artificial neural network for predicting the mechanical performance of additive manufacturing thermoset carbon fiber composite materials. Journal of the Mechanical Behavior of Materials. 2022;31(1):501-513. doi:10.1515/jmbm-2022-0054
  6. Pugar JA, Gang C, Huang C, Haider KW, Washburn NR. Predicting Young’s Modulus of Linear Polyurethane and Polyurethane–Polyurea Elastomers: Bridging Length Scales with Physicochemical Modeling and Machine Learning. ACS Applied Materials & Interfaces. 2022;14(14):16568-16581. doi:10.1021/acsami.1c24715
  7. Sunori SK, Arora S, Agarwal P, Mittal A, Mamodiya U, Juneja P. SA based Optimization of Controller Parameters for Crystallization Unit of Sugar Factory. 2022 6th International Conference on Trends in Electronics and Informatics (ICOEI). 2022:341-346. doi:10.1109/icoei53556.2022.9776904
  8. Moumen A, Lakhdar A, Laabid Z, Mansouri K. Towards smart modeling of mechanical properties of a bio composite based on a machine learning. International Journal of Electrical and Computer Engineering (IJECE). 2022;12(3):3138. doi:10.11591/ijece.v12i3.pp3138-3145
  9. Baturynska I. Application of Machine Learning Techniques to Predict the Mechanical Properties of Polyamide 2200 (PA12) in Additive Manufacturing. Applied Sciences. 2019;9(6):1060. doi:10.3390/app9061060
  10. Isabona, L. L. Ibitome, A. L. Imoize, U. Mamodiya, A. Kumar, M. M. Hassan, et al., "Statistical characterization and modeling of radio frequency signal propagation in mobile broadband cellular next generation wireless networks", Computational Intelligence and Neuroscience, vol. 2023, no. 1, pp. 5236566, 2023 S. K. Sunori,
  11. Cassola S, Duhovic M, Schmidt T, May D. Machine learning for polymer composites process simulation – a review. Composites Part B: Engineering. 2022;246:110208. doi:10.1016/j.compositesb.2022.110208
  12. Mamodiya and N. Tiwari, "Design and implementation of an intelligent single axis automatic solar tracking system", Mater. today Proc., vol. 81, pp. 1148-1151, 2023
  13. Deepak Kumar B N,, Mahesh Dutt K. A Study On Mechanical Properties Of 3d Printed Hybrid Polymer Composites. Journal of Namibian Studies : History Politics Culture. 2023;33:3951-3969. doi:10.59670/btwhrn64
  14. Kishor I. A prototype framework for customizing virtual reality interactions for paralyzed patients integrating physical and rehabilitation modalities. Recent Advances in Sciences, Engineering, Information Technology & Management. 2024:338-344. doi:10.1201/9781003598152-47
  15. Greco PF, Pepi C, Gioffré M. A novel biocomposite material for sustainable constructions: Metakaolin lime mortar and Spanish broom fibers. Journal of Building Engineering. 2024;83:108425. doi:10.1016/j.jobe.2023.108425
  16. Soo XYD, Muiruri JK, Wu WY, Yeo JCC, Wang S, Tomczak N, et al. Bio‐Polyethylene and Polyethylene Biocomposites: An Alternative toward a Sustainable Future. Macromolecular Rapid Communications. 2024;45(14). doi:10.1002/marc.202400064
  17. Zulfiqar A, Shah AUR, Khalil MS, Azad MM, Zulfiqar Y, Naseem MS, et al. Enhancing properties of jute/starch bio-composite material through incorporation of magnesium carbonate hydroxide pentahydrate: A sustainable approach. Materials Chemistry and Physics. 2024;314:128690. doi:10.1016/j.matchemphys.2023.128690
  18. Wang S, Muiruri JK, Soo XYD, Liu S, Thitsartarn W, Tan BH, et al. Bio‐Polypropylene and Polypropylene‐based Biocomposites: Solutions for a Sustainable Future. Chemistry – An Asian Journal. 2022;18(2). doi:10.1002/asia.202200972
  19. Rehman NU, Ullah KS, Sajid M, Ihsanullah I, Waheed A. Preparation of Sustainable Composite Materials from Bio‐Based Domestic and Industrial Waste: Progress, Problems, and Prospects‐ A Review. Advanced Sustainable Systems. 2024;8(8). doi:10.1002/adsu.202300587
  20. McNeill DC, Pal AK, Mohanty AK, Misra M. High biomass filled biodegradable plastic in engineering sustainable composites. Composites Part C: Open Access. 2023;12:100388. doi:10.1016/j.jcomc.2023.100388
  21. Bindiya Jain, Mr Jeetandra Singh, Dr. Udit Mamodiya. Improving Polymer Composite Properties through Reinforcement Learning guided Prototyping a Novel Approach for Material Engineering. Journal of Polymer and Composites. 2024; https://journals.stmjournals.com/jopc/article=2024/view=156890
  22. Palanisamy S, Kalimuthu M, Palaniappan M, Alavudeen A, Rajini N, Santulli C, et al. Characterization of Acacia caesia Bark Fibers (ACBFs). Journal of Natural Fibers. 2021;19(15):10241-10252. doi:10.1080/15440478.2021.1993493
  23. Almeshaal M, Palanisamy S, Murugesan TM, Palaniappan M, Santulli C. Physico-chemical characterization of Grewia Monticola Sond (GMS) fibers for prospective application in biocomposites. Journal of Natural Fibers. 2022;19(17):15276-15290. doi:10.1080/15440478.2022.2123076
Support