Deep Learning-Based Prediction of Tribological Properties in Mg-Cu and Mg-Zn Alloys for Biomedical Applications

Abstract

Incorporating Cu and Zn at low concentrations into a magnesium matrix provides antibacterial properties and biodegradability advantages for biomedical applications. However, the complex effects of these alloying additions on microstructural and tribological behaviours and their optimal ratios have not yet been fully elucidated. This study developed a deep learning-based regression model to predict the wear properties of Mg-Cu and Mg-Zn alloys. Experimental data were obtained from wear tests conducted under 5–20 N loads and a sliding distance of 250 m in dry and simulated body fluid environments. Microstructural parameters, including grain size, density, hardness, crystallite size, microstrain, and dislocation density, were used as model inputs. In contrast, volume loss, coefficient of friction, and specific wear rate were used as output variables. The developed Deep Multilayer Perceptron model with optimised hyperparameters demonstrated high predictive performance on both the training and test datasets, preventing overfitting. Model evaluation yielded R² values of 0.9912 for volume loss, 0.9935 for coefficient of friction, and 0.9545 for specific wear rate, with RMSE values of 0.58, 0.011, and 0.61, respectively, confirming model reliability. Error analyses proved a narrow distribution and high correlation between predicted and experimental data. Sensitivity analysis results indicated that load, environment, hardness, and grain size are the most critical factors determining wear behaviour. This work presents a machine learning framework for tribological prediction in biodegradable Mg alloys, which may contribute to alloy design and optimisation of ortho-paedic implant materials.

Keywords

• Biodegredable Alloys
• Deep Learning
• Powder Metallurgy
• Tribological Performance
• Wear Prediction

Ethical Statement

The authors declared that they complied with the scientific, ethical and citation rules of the International Journal of Pure and Applied Sciences throughout the entire process of the study.

Thanks

The author(s) would like to thank the referees and journal boards of the International Journal of Pure and Applied Sciences. They would also like to thank the technical staff of the Karabük University Central Research Laboratory for their support in the microstructural and tribological characterizations.

References

1. L. D. C. Gutiérrez Púa, J. C. Rincón Montenegro, A. M. Fonseca Reyes, H. Zambrano Rodríguez, and V. N. Paredes Méndez, “Biomaterials for orthopedic applications and techniques to improve corrosion resistance and mechanical properties for magnesium alloy: a review,” J Mater Sci, vol. 58, no. 9, pp. 3879–3908, Feb. 2023, doi: 10.1007/S10853-023-08237-5.
2. A. Nirala et al., “Study of biodegradable magnesium metal matrix composite A review,” Mater Today Proc, vol. 46, pp. 6592–6595, Jan. 2021, doi: 10.1016/J.MATPR.2021.04.063.
3. H. C. Ozdemir, E. Bedir, R. Yilmaz, M. B. Yagci, and D. Canadinc, “Machine learning-assisted design of biomedical high entropy alloys with low elastic modulus for orthopedic implants,” J Mater Sci, vol. 57, no. 24, pp. 11151–11169, Jun. 2022, doi: 10.1007/S10853-022-07363-W.
4. R. Tekin Ünver, C. Bayraktar, and B. Demir, “The regression analysis of dry - wet wear outcomes and materials properties of biodegradable MgCu and MgZn, made by P/M, using machine learning models,” Appl Phys A, vol. 131, no. 4, pp. 311-, Mar. 2025, doi: 10.1007/S00339-025-08452-8.
5. X. Gu, Y. Zheng, Y. Cheng, S. Zhong, and T. Xi, “In vitro corrosion and biocompatibility of binary magnesium alloys,” Biomaterials, vol. 30, no. 4, pp. 484–498, Feb. 2009, doi: 10.1016/J.BIOMATERIALS.2008.10.021.
6. F. Witte et al., “Degradable biomaterials based on magnesium corrosion,” Curr Opin Solid State Mater Sci, vol. 12, no. 5–6, pp. 63–72, Oct. 2008, doi: 10.1016/J.COSSMS.2009.04.001.
7. N. Li and Y. Zheng, “Novel Magnesium Alloys Developed for Biomedical Application: A Review,” J Mater Sci Technol, vol. 29, no. 6, pp. 489–502, Jun. 2013, doi: 10.1016/J.JMST.2013.02.005.
8. N. Pulido-González, P. Hidalgo-Manrique, S. García-Rodríguez, B. Torres, and J. Rams, “Effect of heat treatment on the mechanical and biocorrosion behaviour of two Mg-Zn-Ca alloys,” J Magnes Alloy, vol. 10, no. 2, pp. 540–554, Feb. 2022, doi: 10.1016/J.JMA.2021.06.022.

9. S. Jin, L. Ren, and K. Yang, “Bio-Functional Cu Containing Biomaterials: a New Way to Enhance Bio-Adaption of Biomaterials,” J Mater Sci Technol, vol. 32, no. 9, pp. 835–839, Sep. 2016, doi: 10.1016/J.JMST.2016.06.022.
10. M. Lotfpour et al., “In- vitro corrosion behavior of the cast and extruded biodegradable Mg-Zn-Cu alloys in simulated body fluid (SBF),” J Magnes Alloy, vol. 9, no. 6, pp. 2078–2096, Nov. 2021, doi: 10.1016/J.JMA.2021.01.002.
11. R. Tekin, B. Demir, and A. N. Saud, “Tribological Behavior of MgZn Alloys Produced by Powder Metallurgy: Influence of Zn in Dry and Simulated Body Fluid Environments,” J Mater Eng Perform, vol. 34, no. 23, pp. 27901–27924, Apr. 2025, doi: 10.1007/S11665-025-11192-8.
12. R. A. Youness and M. A. Taha, “Tuning biodegradability, bone-bonding capacity, and wear resistance of zinc-30% magnesium intermetallic alloy for use in load-bearing bone applications,” Sci Reports, vol. 14, no. 1, pp. 2425, Jan. 2024, doi: 10.1038/s41598-024-52648-6.
13. J. S. Suh, B.-C. Suh, J. H. Bae, and Y. M. Kim, “Machine Learning-Based Design of Biodegradable Mg Alloys for Load-Bearing Implants,” SSRN Electron J, Aug. 2022, doi: 10.2139/SSRN.4179090.
14. P. Valipoorsalimi, Y. A. Sari, and M. Pekguleryuz, “Mechanical Property Design of Bio-compatible Mg alloys using Machine-Learning Algorithms,” May 2023, Accessed: Jan. 20, 2026. [Online]. Available: https://arxiv.org/pdf/2305.12060
15. C. Pan et al., “Novel machine learning driven design strategy for high strength Zn Alloys optimization with multiple constraints,” npj Comput Mater, vol. 11, no. 1, pp. 169-, Jun. 2025, doi: 10.1038/s41524-025-01666-7.
16. F. Aydın, K. M. Karaoğlan, H. Y. Pektürk, B. Demir, V. Karakurt, and H. Ahlatçı, “The comparative evaluation of the wear behavior of epoxy matrix hybrid nano-composites via experiments and machine learning models,” Tribol Int, vol. 204, p. 110451, Apr. 2025, doi: 10.1016/J.TRIBOINT.2024.110451.
17. T. Kokubo, H. Kushitani, S. Sakka, T. Kitsugi, and T. Yamamuro, “Solutions able to reproduce in vivo surface‐structure changes in bioactive glass‐ceramic A‐W3,” J Biomed Mater Res, vol. 24, no. 6, pp. 721–734, Jun. 1990, doi: 10.1002/JBM.820240607.
18. R. K. Mishra, G. Y. S. Reddy, and H. Pathak, “The Understanding of Deep Learning: A Comprehensive Review,” Math Probl Eng, vol. 2021, no. 1, p. 5548884, Jan. 2021, doi: 10.1155/2021/5548884.
19. T. Patil, S. Pandey, and K. Visrani, “A Review on Basic Deep Learning Technologies and Applications,” Lect Notes Data Eng Commun Technol, vol. 52, pp. 565–573, 2021, doi: 10.1007/978-981-15-4474-3_61.
20. I. H. Sarker, “Deep Learning: A Comprehensive Overview on Techniques, Taxonomy, Applications and Research Directions,” SN Comput Sci, vol. 2, no. 6, pp. 420, Aug. 2021, doi: 10.1007/S42979-021-00815-1.
21. E. Bisong, Building Machine Learning and Deep Learning Models on Google Cloud Platform: A Comprehensive Guide for Beginners. Berkeley, CA: Apress Media LLC, 2019. doi: 10.1007/978-1-4842-4470-8.
22. K. Markov, “Multilayer Perceptron with Backpropagation, HDL Coder, and FPGA Technology: An Integrated Approach for Efficient Neural Network Implementation,” Probl Eng Cybern Robot, vol. 80, pp. 13–22, 2023, doi: 10.7546/PECR.80.23.02.
23. A. Wichert and L. Sa-Couto, “Multilayer Perceptron,” in Machine Learning — A Journey to Deep Learning, WORLD SCIENTIFIC, 2021, pp. 223–249. doi: 10.1142/9789811234064_0006.
24. S. Wan, Y. Liang, Y. Zhang, and M. Guizani, “Deep Multi-Layer perceptron classifier for behavior analysis to estimate Parkinson’s disease severity using smartphones,” IEEE Access, vol. 6, pp. 36825–36833, Jul. 2018, doi: 10.1109/ACCESS.2018.2851382.
25. U. Köse and Ö. Deperlioğlu, Python ile Makine Öğrenmesi: Temel Kavramlar, Sınıflandırma, Regresyon, Kümeleme. Ankara: Seçkin Yayıncılık, 2024.
26. J. Qi, J. Du, S. M. Siniscalchi, X. Ma, and C. H. Lee, “On Mean Absolute Error for Deep Neural Network Based Vector-to-Vector Regression,” IEEE Signal Process Lett, vol. 27, pp. 1485–1489, 2020, doi: 10.1109/LSP.2020.3016837.
27. L. Rutkowski, M. Jaworski, and P. Duda, Stream Data Mining: Algorithms and Their Probabilistic Properties, vol. 56. in Studies in Big Data, vol. 56. Cham: Springer International Publishing, 2020. doi: 10.1007/978-3-030-13962-9.
28. I. Nabillah and I. Ranggadara, “Mean Absolute Percentage Error untuk Evaluasi Hasil Prediksi Komoditas Laut,” JOINS (Journal Inf Syst), vol. 5, no. 2, pp. 250–255, Nov. 2020, doi: 10.33633/JOINS.V5I2.3900.
29. A. Singh, T. Agarwal, V. Gambhir, and A. Harinaiha, “Estimation of Attrition Loss Due to Spray-On Coatings for Mg Alloys Using a Novel Machine Learning Approach,” Nanotechnol Perceptions, vol. 20, no. S3, pp. 291-303–291–303, May 2024, doi: 10.62441/NANO-NTP.V20IS3.590.
30. M. B. Pasha, R. N. Rao, S. Ismail, M. Gupta, and P. S. Prasad, “Tribo-informatics approach to predict wear and friction coefficient of Mg/Si3N4 composites using machine learning techniques,” Tribol Int, vol. 196, p. 109696, Aug. 2024, doi: 10.1016/J.TRIBOINT.2024.109696.
31. F. Aydin, R. Durgut, M. Mustu, and B. Demir, “Prediction of wear performance of ZK60 / CeO2 composites using machine learning models,” Tribol Int, vol. 177, p. 107945, Jan. 2023, doi: 10.1016/J.TRIBOINT.2022.107945.
32. T. Gurgenc, O. Altay, M. Ulas, and C. Ozel, “Extreme learning machine and support vector regression wear loss predictions for magnesium alloys coated using various spray coating methods,” J Appl Phys, vol. 127, no. 18, May 2020, doi: 10.1063/5.0004562/280815.
33. N. Bagherieh, M. Noori, D. Li, and M. Nouri, “Critical Factors Governing the Frictional Coefficient in Mg Alloys—Learn From Machine Learning,” Eng Reports, vol. 7, no. 5, p. e70140, May 2025, doi: 10.1002/ENG2.70140.