A Review on Predicting Wear and Friction of PTFE Composites – Fillers to Machine Learning Models

Year : 2025 | Volume : 13 | Special Issue 04 | Page : 114 128
    By

    Abhijeet R. Deshpande,

  • Atul Kulkarni,

  • Prashant Anerao,

  • Swapnil Shah,

  • Pranav Kulkarni,

  1. Research Scholar, Department of Mechanical Engineering, Vishwakarma Institute of Information Technology, Pune, Maharshtra, India
  2. Professor, Department of Mechanical Engineering, Vishwakarma Institute of Technology, Pune, Maharshtra, India
  3. Assistant Professor, Department of Mechanical Engineering, Vishwakarma Institute of Technology, Pune, Maharshtra, India
  4. UG Scholar, Department of Mechanical Engineering, Vishwakarma Institute of Information Technology, Pune, Maharshtra, India
  5. UG Scholar, Department of Mechanical Engineering, Vishwakarma Institute of Information Technology, Pune, Maharshtra, India

Abstract

Polytetrafluoroethylene (PTFE) composites, a self-lubricating material with low friction, became an indispensable material in engineering applications where load carrying capacity and wear are crucial. The pure PTFE has poor mechanical strength and wear resistance which can be enhanced by the addition of fillers in appropriate volume fraction. The wear performance is dependent on various factors such as fillers, operating parameters, environmental conditions as well as manufacturing attributes. This makes the analysis of any tribological system more complex with nonlinear interactions with different influencing elements. This limitation focuses the need of adopting a data driven machine learning (ML) approach to provide more accurate understanding of the tribo-system and provide more accurate prediction of wear.ML techniques have emerged as an effective tool for understanding wear mechanisms and accurately predicting the wear rate and coefficient of friction (COF). These ML algorithms are data driven, learn from the experimental data finds the trends in material composition with different fillers and operating circumstances for accurate forecasts.  Gradient boosting model (GB) shown high predictive accuracy (R² values up to 0.95) for PTFE composites, outperforming traditional models by capturing non-linear interactions and adapting to varied conditions. ML techniques offer interpretability, critical for understanding the impact of each material parameter as well as providing robustness with smaller datasets, making it suitable for applications where data availability is limited. These models provide stability and accuracy in forecasting wear behaviour, which is essential in real-world applications where complex material interactions are present This review identifies current challenges, such as data quality and model validation, and emphasizes the need for hybrid models that combine the strengths of ML and numerical methods. Future research should focus on expanding the predictive capability of these models through more comprehensive datasets and advanced algorithms, aiming for sustainable, cost-effective, and high-performance tribological solutions in PTFE composite applications across automotive, aerospace, and medical industries

Keywords: PTFE, wear, coefficient of friction, fillers, machine learning.

[This article belongs to Special Issue under section in Journal of Polymer and Composites (jopc)]

How to cite this article:
Abhijeet R. Deshpande, Atul Kulkarni, Prashant Anerao, Swapnil Shah, Pranav Kulkarni. A Review on Predicting Wear and Friction of PTFE Composites – Fillers to Machine Learning Models. Journal of Polymer and Composites. 2025; 13(04):114-128.
How to cite this URL:
Abhijeet R. Deshpande, Atul Kulkarni, Prashant Anerao, Swapnil Shah, Pranav Kulkarni. A Review on Predicting Wear and Friction of PTFE Composites – Fillers to Machine Learning Models. Journal of Polymer and Composites. 2025; 13(04):114-128. Available from: https://journals.stmjournals.com/jopc/article=2025/view=210540


Browse Figures

References

  1. Friedrich K, Zhang Z, Schlarb AK. Effects of various fillers on the sliding wear of polymer composites. Composites Science and Technology. 2005;65(15-16):2329-2343. https://doi.org/10.1016/j.compscitech.2005.05.028
  2. Conte M, Pinedo B, Igartua A. Role of crystallinity on wear behavior of PTFE composites. 2013;307(1-2):81-86. https://doi.org/10.1016/j.wear.2013.08.019
  3. Cui W, Raza K, Zhao Z, Yu C, Tao L, Zhao W, et al. Role of transfer film formation on the tribological properties of polymeric composite materials and spherical plain bearing at low temperatures. Tribology International. 2020;152:106569.https://doi.org/10.1016/j.triboint.2020.106569
  4. Amenta F, Bolelli G, D’Errico F, Ottani F, Pedrazzi S, Allesina G, Lusvarghi L. Tribological behaviour of PTFE composites: Interplay between reinforcement type and counterface material. 2022;510:204498. https://doi.org/10.1016/j.wear.2022.204498
  5. Fidan S, Korkusuz OB, Toker PÖ, Gültürk E, Ateş BH, Sınmazçelik T. Effect of filling materials on the tribological performance of polytetrafluoroethylene in different wear modes. Polymer Composites. 2024;45(15):13561-13577. https://doi.org/10.1002/pc.28718
  6. Yan Y, Du J, Ren S, Shao M. Prediction of the tribological properties of polytetrafluoroethylene composites based on experiments and machine learning. 2024;16:356. https://doi.org/10.3390/polym16030356
  7. Deshpande AR, Kulkarni AP, Wasatkar N, Gajalkar V, Abdullah M. Prediction of wear rate of glass-filled PTFE composites based on machine learning approaches. 2024;16(18):2666. https://doi.org/10.3390/polym16182666
  8. Song F, Wang Q, Wang T. Effects of glass fiber and molybdenum disulfide on tribological behaviors and PV limit of chopped carbon fiber reinforced polytetrafluoroethylene composites. Tribology International. 2016;104:392-401. https://doi.org/10.1016/j.triboint.2016.07.014
  9. Aderikha VN. On the effect of the chemical composition of a steel counterbody on the wear rate of a low-filled PTFE/SiO₂ composite. Journal of Friction and Wear. 2022;43(4):221-228. https://doi.org/10.3103/S1068366622040023
  10. Amenta F, Bolelli G, D’Errico F, Ottani F, Pedrazzi S, Allesina G, Lusvarghi L. Sliding wear behaviour of fiber-reinforced PTFE composites against coated and uncoated steel. 2021;486:204097. https://doi.org/10.1016/j.wear.2021.204097
  11. Johansson P, Marklund P, Björling M, Shi Y. Effect of humidity and counterface material on the friction and wear of carbon fiber reinforced PTFE composites. Tribology International. 2021;157:106869. https://doi.org/10.1016/j.triboint.2020.106869
  12. Lu G, Liang Z, Qi X, Wang G, Liu Y, Kang WB, Kim DE. Enhancement of tribological performance of PTFE/aramid fabric liner under high-temperature and heavy-load through incorporation of microcapsule/CF multilayer composite structure. Tribology International. 2024:110239. https://doi.org/10.1016/j.triboint.2024.110239
  13. Conte M, Fernandez B, Igartua A. Effect of surface temperature on tribological behavior of PTFE composites. In: Proceedings of the Surface Effects and Contact Mechanics X (pp. 219-230). WIT Press, UK; 2011. https://doi.org/10.2495/SECM110191
  14. Conte M, Pinedo B, Igartua A. Role of crystallinity on wear behavior of PTFE composites. 2013;307(1-2):81-86. https://doi.org/10.1016/j.wear.2013.07.016
  15. Homayoun MR, Golchin A, Emami N. Effect of hygrothermal ageing on tribological behaviour of PTFE-based composites. 2018;6(4):103. https://doi.org/10.3390/lubricants6040103
  16. Salunkhe S, Chandankar P. Friction and wear analysis of PTFE composite materials. In: Innovative Design, Analysis and Development Practices in Aerospace and Automotive Engineering (I-DAD 2018) Volume 2 (pp. 415-425). Springer Singapore; 2019. https://doi.org/10.1007/978-981-13-5770-3_40
  17. Basavarajappa S, Arun KV, Davim JP. Effect of filler materials on dry sliding wear behavior of polymer matrix composites—A Taguchi approach. Journal of Minerals and Materials Characterization and Engineering. 2009;8(5):379-392. https://doi.org/10.4236/jmmce.2009.85032
  18. Wang Z, Wu S, Ni J. Influence of SiO2/MoS2/graphite content on the wear properties of PTFE composites under natural seawater lubrication. Proceedings of the Institution of Mechanical Engineers, Part J: Journal of Engineering Tribology. 2018;232(5):607–618.https://doi.org/10.1177/1350650117697022
  19. Lin YX, Gao CH, Li Y. Effects of CaCO3 whisker on the sliding wear behavior of poly(etheretherketone) under water-lubricated conditions. Proceedings of the Institution of Mechanical Engineers, Part J: Journal of Engineering Tribology. 2010;224(12):1255–1259. https://doi.org/10.1243/13506501JET871
  20. Sujuan Y, Xingrong Z. Tribological properties of PTFE and PTFE composites at different temperatures. Tribology Transactions. 2014;57(3):382–386. https://doi.org/10.1080/10402004.2014.894324
  21. Valente CAGS, Boutin FF, Rocha LPC, do Vale JL, da Silva CH. Effect of graphite and bronze fillers on PTFE tribological behavior: A commercial materials evaluation. Tribology Transactions. 2020;63(2):356-370. https://doi.org/10.1080/10402004.2019.1695032
  22. Sawae Y, Miyakoshi E, Doi S, Watanabe H, Kurono Y, Sugimura J. Friction and wear of bronze filled PTFE and graphite filled PTFE in 40 MPA hydrogen gas. In: International Joint Tribology Conference. 2011 Jan; Vol. 54747, pp. 249-251. https://doi.org/10.1115/IJTC2011-61215
  23. Fidan S, Korkusuz OB, Toker PÖ, Gültürk E, Ateş BH, Sınmazçelik T. Effect of filling materials on the tribological performance of polytetrafluoroethylene in different wear modes. Polymer Composites. https://doi.org/10.1002/pc.28718
  24. Huang TC, Lin CY, Liao KC. Experimental and numerical investigations of the wear behavior and sealing performance of PTFE rotary lip seals based on the elasto-hydrodynamic analysis with considerations of the asperity contact. Tribology International. 2023;187:108747. https://doi.org/10.1016/j.triboint.2023.108747
  25. Huang TC, Lin CY, Liao KC. Sealing performance assessments of PTFE rotary lip seals based on the elasto-hydrodynamic analysis with the modified Archard wear model. Tribology International. 2022;176:107917. https://doi.org/10.1016/j.triboint.2022.107917
  26. Bochkareva SA, Panin SV, Lyukshin BA, Lyukshin PA, Grishaeva NY, Matolygina NY, Aleksenko VO. Simulation of frictional wear with account of temperature for polymer composites. Physical Mesomechanics. 2020;23:147-159. https://doi.org/10.1134/S102995992002006X
  27. Gong R, Wan X, Zhang X. Tribological properties and failure analysis of PTFE composites used for seals in the transmission unit. Journal of Wuhan University of Technology-Mater. Sci. Ed. 2013;28(1):26-30. https://doi.org/10.1007/s11595-013-0634-4
  28. Bhosale AB, Walame MV, Lathesh M. Influence of different parameters on the specific wear rate of PTFE composites in the steam environment. In: IOP Conference Series: Materials Science and Engineering. 2022 Dec; Vol. 1272, No. 1, p. 012019. IOP Publishing. https://doi.org/10.1088/1757-899X/1272/1/012019
  29. Wang J, Huang X, Wang W, Han H, Duan H, Yu S, Zhu M. Effects of PTFE coating modification on tribological properties of PTFE/aramid self-lubricating fabric composite. Materials Research Express. 2022;9(5):055302. https://doi.org/10.1088/2053-1591/ac587a
  30. Wu S, Yan Z, Sun H, Liu Z, Xue L, Sun T. Tribological performance study of low-friction PEEK composites under different lubrication conditions. Applied Sciences. 2024;14(9):3723.https://doi.org/10.3390/app14093723
  31. Ain QU, Wani MF, Sehgal R, Singh MK. Tribological and mechanical characterization of carbon-nanostructures based PEEK nanocomposites under extreme conditions for advanced bearings: A molecular dynamics study. Tribology International. 2024;196:109702.https://doi.org/10.1016/j.triboint.2024.109702
  32. Kiran MD, BR LY, Babbar A, Kumar R, HS SC, Shetty RP, Sudeepa KB, Kaur R, Alkahtani MQ, Islam S. Tribological properties of CNT-filled epoxy-carbon fabric composites: Optimization and modelling by machine learning. Mater. Res. Technol. 2024;28:2582–2601.https://doi.org/10.1016/j.jmrt.2023.12.175
  33. Zhang Z, Friedrich K, Velten K. Prediction on tribological properties of short fiber composites using artificial neural networks. 2002;252:668–675. https://doi.org/10.1016/S0043-1648(02)00023-6
  34. Hasan MS, Kordijazi A, Rohatgi PK, Nosonovsky M. Triboinformatics approach for friction and wear prediction of Al-graphite composites using machine learning methods. Tribol. 2022;144:011701. https://doi.org/10.1115/1.4050525
  35. Ibrahim MA, Gidado AY, Balarabe F. A Novel Model for Prediction of Wear and Coefficient of Friction Characteristics of Glass Fiber Reinforced Polytetrafluoroethylene Composites. Journal of Sustainable Engineering and Technology. 2024;1(1):82–97.
  36. Dhande DY, Phate MR, Sinaga N. Comparative analysis of abrasive wear using response surface method and artificial neural network. Inst. Eng. Ser. D. 2021;102:27–37.https://doi.org/10.1007/s40033-021-00250-9
  37. Wang Q, Wang X, Zhang X, Li S, Wang T. Tribological properties study and prediction of PTFE composites based on experiments and machine learning. Int. 2023;188:108815. https://doi.org/10.1016/j.triboint.2023.108815
  38. Wang Y, Nie R, Liu X, Wang S, Li Y. Tribological Behavior Analysis of Valve Plate Pair Materials in Aircraft Piston Pumps and Friction Coefficient Prediction Using Machine Learning. 2024;14:701. https://doi.org/10.3390/met14030701
  39. Wu D, Jennings C, Terpenny J, Gao RX, Kumara S. A comparative study on machine learning algorithms for smart manufacturing: Tool wear prediction using random forests. Manuf. Sci. Eng. 2017;139:071018. https://doi.org/10.1115/1.4036350
  40. Mesbahi AH, Semnani D, Khorasani SN. Performance prediction of a specific wear rate in epoxy nanocomposites with various composition content of polytetrafluoroethylene (PTFE), graphite, short carbon fibers (CF) and nano-TiO2 using adaptive neuro-fuzzy inference system (ANFIS). Composites Part B: Engineering. 2012;43(2):549–558.https://doi.org/10.1016/j.compositesb.2011.08.011
  41. Ibrahim MA, Yahya MN, Şahin Y. Predicting the mass loss of polytetrafluoroethylene-filled composites using artificial intelligence techniques. Bayero J. Eng. Technol. 2021;16:80–93.
  42. Kordijazi A, Roshan HM, Dhingra A, Povolo M, Rohatgi PK, Nosonovsky M. Machine-learning methods to predict the wetting properties of iron-based composites. Innov. 2020;9:111–119.https://doi.org/10.1680/jsuin.20.00008
  43. Mohammed AJ, Mohammed AS, Mohammed AS. Prediction of Tribological Properties of UHMWPE/SiC Polymer Composites Using Machine Learning Techniques. 2023;15:4057. https://doi.org/10.3390/polym15204057
  44. Kolev M. XGB-COF: A machine learning software in Python for predicting the friction coefficient of porous Al-based composites with Extreme Gradient Boosting. Impacts. 2023;17:100531.https://doi.org/10.1016/j.simpa.2023.100531
  45. Hasan MS, Kordijazi A, Rohatgi PK, Nosonovsky M. Triboinformatic modeling of dry friction and wear of aluminum base alloys using machine learning algorithms. Int. 2021;161:107065. https://doi.org/10.1016/j.triboint.2021.107065
  46. Kharate N, Anerao P, Kulkarni A, Abdullah M. Explainable AI Techniques for Comprehensive Analysis of the Relationship between Process Parameters and Material Properties in FDM-Based 3D-Printed Biocomposites. Manuf. Mater. Process. 2024;8:171.https://doi.org/10.3390/jmmp8040171
  47. Parikh HH, Gohil PP. Sliding wear experimental investigation and prediction using response surface method: fillers filled fiber reinforced composites. Today: Proc. 2019;18:5388–5393.https://doi.org/10.1016/j.matpr.2019.07.566
  48. Chang BP, Akil HM, Nasir RB, Khan A. Optimization on wear performance of UHMWPE composites using response surface methodology. Int. 2015;88:252–262.https://doi.org/10.1016/j.triboint.2015.03.028
  49. Khan MJ, Gandotra H, Saleem SS, Wani MF. Effect of material hardness, counter-face hardness and load on the tribological properties of virgin and glass filled PTFE using Taguchi Approach. Phys. Conf. Ser. 2019;1240(1):012106. https://doi.org/10.1088/1742-6596/1240/1/012106
  50. Şahin Y. Analysis of abrasive wear behavior of PTFE composite using Taguchi’s technique. Cogent Eng. 2015;2(1):1000510. https://doi.org/10.1080/23311916.2014.1000510
Special Issue Subscription Review Article
Volume 13
Special Issue 04
Received 16/01/2025
Accepted 26/02/2025
Published 20/05/2025
Publication Time 124 Days
649

Login


My IP

PlumX Metrics