DOI QR코드

DOI QR Code

Artificial neural network modelling for predicting tribological properties of Al8090/TiB2/C composites using optimized hyperparameters

  • Mohamed Zakaulla (Department of Mechanical Engineering, H.K.B.K College of Engineering, Visvesvaraya Technological University)
  • Received : 2024.09.26
  • Accepted : 2024.12.26
  • Published : 2025.01.25

Abstract

This study introduces a new framework that utilizes artificial neural networks (ANN) to analyze data and forecast the tribological properties of Al8090/TiB2/C composites. For training a multi-layered artificial neural network (ANN), a total of 1920 input datasets are used. These datasets are created by combining six input parameters, including the volume of Al8090 matrix, Titanium diboride, and Graphene, as well as the load, sliding speed, and sliding distance. The corresponding output consists of specific wear rate and coefficient of friction. A surrogate model for predicting the tribological properties has been developed by optimizing the hyperparameters to enhance the accuracy of the model's predictions. The results of the ANN-based approach validate that the proposed model has a mean absolute percentage error of 3.42% for the predictions of specific wear rate in dry sliding wear test scenarios, and a MAPE of 0.28% for the predictions of coefficient of friction.

Keywords

Acknowledgement

The funding was received for conducting this study from AICTE.

References

  1. Afape, J.O., Willoughby, A.A., Sanyaolu, M.E., Obiyemi, O.O., Moloi, K., Jooda, J.O. and Dairo, O.F. (2024), "Improving milimetre-wave path loss estimation using automated hyperparameter-tuned stacking ensemble regression machine learning", Results Eng., 22, 102289. https://doi.org/101016/j.rineng.2024.102289. 101016/j.rineng.2024.102289
  2. Akin, I. and Kaya, O. (2017), "Microstructures and properties of silicon carbide- and graphene nanoplatelet-reinforced titanium diboride composites", J. Alloys Compd., 729, 949-959. https://dci.org/10.1016/j.jallcom.2017.09.244.
  3. Anuar, N.F.B.W., Omar, M.Z., Salleh, M.S., Zamri, W.F.H.W. and Ali, A.M. (2024), "Effect of graphene addition on microstructure and wear behaviour of the A356-based composite fabricated by thixoforming process", J. Mater. Res. Technol., 30, 4813-4831. https://doiorg/10.1016/j.jmrt.2024.04.192.
  4. Azad, M.M. and Kim, H.S. (2024), "Hybrid deep convolutional networks for the autonomous damage diagnosis of laminated composite structures", Compos. Struct., 329, 117792. https://doioog/10.1016/j.compstruct.2023.117792.
  5. Babaei, M., Atasoy, A., Hajirasouliha, I., Mollaei, S. and Jalilkhani, M. (2022), "Numerical solution of beam equation using neural networks and evolutionary optimization tools", Adv Comput. Des., 7, 1-17. https://doi.org/10.12989/acd.2022.7.1.001
  6. Babu, R.R., Rajendran, C., Saiyathibrahim, A. and Velu, R. (2024), "Influence of B4C and ZrB2 reinforcements on microstructural, mechanical and wear behaviour of AA 2014 aluminium matrix hybrid composites", Defence Technol., 2024. https://doi.org/10.1016/j.dt.2024.05.009.
  7. Cheung, H.L., Uvdal, P. and Mirkhalaf, M. (2024), "Augmentation of scarce data-A new approach for deep-learning modeling of composites", Compos. Sci. Technol., 249, 110491. https://doi.org/10.1016/j.compscitech.2024.110491.
  8. Fei, Z., Wu, Z., Xiao, Y., Ma, J. and He, W. (2020), "A new short-arc fitting method with high precision using Adam optimization algorithm", Optik, 212, 164788. https://doi.org/101016/j.ijleo.2020.164788. 101016/j.ijleo.2020.164788
  9. González, A., Martin, J. and Llorca, J. (2004), "Effect of temperature on the fracture mechanisms of 8090 AI-Li alloy and 8090 AI-Li/SiC composite", Scripta Materialia, 51, 1111-1115. https://doi.org/10.1016/j.scriptamat.2004.07.025.
  10. Hasan, M.M., Rahman, M.M., Islam, M.S., Chan, W.H., Alginahi, Y.M., Kabir, M.N., Bakar, A. and Ramasamy, D. (2024), "Artificial neural network modeling for predicting thermal conductivity of EG/Water-based CNC nanofluid for engine cooling using different activation functions", Front. Heat Mass Transf., 22, 537-556. https://doi.org/10.32604/fhmt.2024.047428.
  11. He, W., Li, H., Han, X., Wang, X., Wang, G., Zhang, X. and Shcheretskyi, O. (2024), "High-temperature dry sliding friction and wear behavior of in-situ (Al3Zr+ZrB2)/AA6016 aluminum matrix composites", Mater. Today Commun., 39, 108951. https://doi.org/10.1016/j.mtcomm.2024.108951.
  12. Jung, K.C. and Chang, S.H. (2021), "Advanced deep learning model-based impact characterization method for composite laminates", Compos. Sci. Technol., 207, 108713. https://doi.org/10.1016/j.compscitech.2021,108713.
  13. Kazi, M.K., Eljack, F. and Mahdi (2020), "Predictive ANN models for varying filler content for cotton fiber/PVC composites based on experimental load displacement curves", Compos. Struct., 254, 112885. https://doi.org/10.1016/j.compstruct.2020.112885.
  14. Kumar, J.L., Gurusamy, P., Gayathri, N. and Muthuraman, V. (2024), "Influence of graphene nanoplates and titanium diboride particulate on wear and interfacial bonding properties of sintered aluminium alloy composites", Diamond Related Mater., 144, 111035. https://doi.org/10.1016/j.diamond.2024.111035.
  15. Lima, J.P.S., Evangelista Jr., F. and Soares, C.G. (2023), "Hyperparameter-optimized multi-fidelity deep neural network model associated with subset simulation for structural reliability analysis", Reliabil. Eng. Svst. Safe., 239, 109492. https://doi.org/101016/j.ress.2023.109492. 101016/j.ress.2023.109492
  16. Lujan-Moreno, G.A., Howard, P.R., Rojas, O.G. and Montgomery, D.C. (2018), "Design of experiments and response surface methodology to tune machine learning hyperparameters, with a random forest case-study", Exp. Svst. Appl., 109, 195-205. https://doiorg/10.1016/j.eswa.2018.05.024.
  17. Lynch, P., Muddle, B.C. and Pasang, T. (2001), "Ductile-to-brittle fracture transitions in 8090 AI-Li alloys", Acta Materialia, 49, 2863-2874. https://doi.org/10.1016/S1359-6454(01)00217-8.
  18. Manu, M., Aravind, J., Mohammed, S.B., Roy, K.E.R., Ali, M.M. and Shaik, U. (2024), "Optimization of tribological characteristics in cryo-treated plastic/graphene oxide modified CFRP via ANN-based predictive modeling for aerospace applications", Compos. Sci. Technol., 250, 110520. https://doi.org/101016/j.compscitech.2024110520. 101016/j.compscitech.2024110520
  19. Protyai, M.I.H., Adib, F.M., Taher, T.I., Karim, M.R., Rashid, A.B. and Mahmud, F. (2024), "Performance evaluation of Kevlar fiber reinforced epoxy composite by depositing graphene/SiC/AI2O3 Nanoparticles", Hybr. Adv., 6, 100245. https://doi.org/10.1016/j.hybadv.2024,100245.
  20. Provencher, B., Badran, A., Kroll, J. and Marsh, M. (2024), "Hyperparameter tuning for deep learning semantic image segmentation of microcomputed tomography scanned fiber-reinforced composites", Tomography Mater. Struct., 3, 100032. https://doi.org/101016/j.tnater.2024.100032. 101016/j.tnater.2024.100032
  21. Santo, J., Pradhik, V., Kalakoti, S., Saravanan, P. and Penumakala, P.K. (2024), "Effect of composite processing technique on tribological properties of 3D printed PLA-graphene composites", Tribol. Int., 2024, 109895. https://doi.org/10.1016/j.triboint.2024.109895.
  22. Singh, L.B., Jinu, G.R., Manoj, M. and Perumal, E. (2022), "Tribological behaviour of AI 8090-SiC metal matrix composites with dissimilar B4C addition", Silicon, 14, 8895-8908. https://doi.org/101007/s12633-021-01608-0. 101007/s12633-021-01608-0
  23. Sivaprasad, H., Lekkala, M.R., Latheef, M., Seo, J., Yoo, K., Jin, C. and Kim, D.K. (2023), "Fatigue damage prediction of top tensioned riser subjected to vortex-induced vibrations using artificial neural networks", Ocean Eng., 268, 113393. https://doi.org/10.1016/j.oceaneng.2022.113393.
  24. Wang, W.C., Nguyen, N.M. and Cao, M.T. (2022), "Smart ensemble machine learner with hyperparameter-free for predicting bond capacity of FRP-to-concrete interface: Multi-national data", Constr. Build. Mater., 345, 128158 https://doiorg/10.1016/j.conbtildmat.2022.128158.
  25. Wang, B., Li, N., Bao, Q., Cheng, S., Feng, J., Li, M., Wang, N., Wang, Z., Jiang, B., Chen, L., Hong, H. and Jian, X. (2024), "Graphene at different scales to synergistically optimize the thermal and mechanical properties of CF/PPBESK composites", Compos. Part B Eng., 284, 111692. https://doi.org/101016/j.compositesb.2024111692. 101016/j.compositesb.2024111692
  26. Wang, Z., Zhao, C., Yang, Z., Wang, K., Dong, G. and Starostenkov, M.D. (2024), "Multi-scale collaborative prediction of optimal configuration for carbon fiber woven composites based on deep learning neural networks", Compos. Struct., 339, 118165. https://doi.org/10.1016/j.compstruct.2024.118165.
  27. Yu, X., Jiang, R., Gao, Y., Li, Y., Gong, W., Li, X. and Li, W. (2024), "Microstructure and wear-resistant behaviors of A1203-TIO2 reinforced Ni-based composite coating plasma-sprayed on 6061 aluminum alloy", Surf. Coatings Technol., 487, 131032. https://doi.org/10.1016/j.surfcoat.2024.131032.
  28. Zhang, Y., Lv, Z., Cao, J., Tong, Y., Sun, M., Cui, C. and Wang, X. (2024), "Effect of SiC and TiC content on microstructure and wear behavior of Ni-based composite coating manufactured by laser cladding on Ti-6A1-4V", Wear, 15, 205431. https://doi.org/10.1016/j.wear.2024.205431.
  29. Zhou, S., Zhang, W., Liu, M., Ren, W., Zhou, Q., Wei, J. and Wu, P. (2023), "Strength-toughness combination in nickel matrix composites reinforced by hybrid graphene nanoplatelets-titanium diboride", Carbon, 201, 1137-1148. https://doi.org/101016/j.carbon.2022.10.033. 101016/j.carbon.2022.10.033