Application of machine learning methods for predicting outcomes of titanium powder treatment in ethanol under high-voltage electro-discharge conditions

Keywords

machine learning, Random forest, logistic regression, high voltage electric discharge, titanium.

Cite as

Prystash М. S., Torpakov А. S., Lypian Ye. V., Syzonenko О. М., and Prystash S. F. Application of machine learning methods for predicting outcomes of titanium powder treatment in ethanol under high-voltage electro-discharge conditions. Physicochemical Mechanics of Materials. 2026. 62(2), 107-113.

https://doi.org/10.15407/pcmm2026.02.107

Abstract

Based on experimental data from high-voltage electro-discharge treatment of titanium powder in ethanol with spark discharge implementation, the feasibility of using machine learning algorithms – Random Forest and Logistic Regression – is demonstrated for the case of a fixed single-discharge energy of 1 kJ. The changes in discharge channel pressure, pressure on the walls of the processing chamber, average titanium par¬ticle diameter, the number of spherical particles, and the amount of synthesized titanium carbide, depending on the specific energy input and the interelectrode gap, where the energy is applied, are predicted with an accuracy of up to 70%.

References

1. H. Darwish, W. Darwish, and H. Darwish, “Artificial Intelligence, Machine Learning, and Deep Learning Applications in the Engineering Fields – A Comprehensive Review,” Sigma J. of Eng. and Natural Sci., 43, Is. 15, 1-37 (2025).
2. J. Jelenka Savkovic-Stevanovic, “Modeling Principles, Theory and Methods,” Sci. Res., 3, Is. 3, 72-78 (2015). https://doi.org/10.11648/j.sr.20150303.15
3. K. Chung, S. Lee, Y.S. Hwang, and C.Y. Kim, “Modeling of pulsed spark discharge in water and its application to well cleaning,” Current Appl. Physics, 15, Is. 9, 977-986 (2015). https://doi.org/10.1016/j.cap.2015.05.010
4. M.S. Prystash, S.F. Prystash, A.S. Torpakov, Ye.V. Lypian, O.M. Syzonenko, and R.K. Janutienė, “The use of machine learning methods to predict the processes and results of high-voltage electric discharge treatment of titanium powder in kerosene,” Machines. Technol. Materials, 16, Is. 8, 267-269 (2022).
5. T. Carneiro, R.V. Medeiros Da NóBrega, T. Nepomuceno, G.-B. Bian, V.H.C. De Albuquerque, and P.P.R. Filho, “Performance analysis of google colaboratory as a tool for accelerating deep learning Applications,” IEEE Access., 6, 61677-61685 (2018). https://doi.org/10.1109/ACCESS.2018.2874767
6. F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, E. Duchesnay, and G. Louppe, “Scikit-learn: Machine Learning in Python,” J. of Machine Learning Res., 12, 2826-2830 (2012).
7. P. Contreras, J. Orellana-Alvear, P. Muñoz, J. Bendix, and R. Céller, “Influence of Random Forest Hyperparameterization on Short-Term Runoff Forecasting in an Andean Mountain Catchment,” Atmosphere, 12 (2021) Art. no. 238. https://doi.org/10.3390/atmos12020238
8. J. Awwalu, and F. Ogwueleka, “On holdout and cross validation: a comparison between neural network and support vector machine,” Int. J. of Trend in Res. and Development, 6, Is. 2, 235-239 (2019).
9. O.M. Syzonenko, P.I. Loboda, A.D. Zaichenko, Y.V. Solodkyi, A.S. Torpakov, M.S. Prystash, and V.O. Trehub, “The influence of high-voltage electrical discharge on dispersion and structure of B4C powder,” J. of Superhard Mater., 39, 243-250 (2017). https://doi.org/10.3103/S1063457617040049
10. О.М. Sizonenko, M.S. Prystash, E.І. Таftai, A.S. Torpakov, and Y.V. Lypian, “Modeling of electric-discharge processes in the course of treatment of titanium in hydrocarbon liquids,” Mater. Sci., 57, Is. 2, 209-214 (2021). https://doi.org/10.1007/s11003-021-00533-2
11. S.S. Kozyrev, and L.Yu. Ovchinnikova, “Analysis of the dynamics of the control system for electroexplosive energy conversion based on fuzzy logic,” Visnyk Kharkivskogo Natsionalnogo Universytetu “Kharkivskyi Politekhnichnyi Instytut” [in Ukrainian], 11, 53-56 (2009).
12. S. Yousefi, and M. Poornajaf, “Analysis of accuracy metric of machine learning algorithms in predicting heart disease,” Frontiers in Health Informatics, 12 (2023). Art. no. 135 https://doi.org/10.30699/fhi.v12i0.402
13. I. Perez, M.K. Knyazyev, and J. San Jose, “Experimental investigation of electric discharge parameters in correlation with peak pressure at industrial electrohydraulic forming,” SN Appl. Sci., 1 (2019). Art. no. 1299. https://doi.org/10.1007/s42452-019-1336-0
14. S. Chikosha, T.C. Shabalala, and H. Chikwanda, “Effect of particle morphology and size on roll compaction of Ti-based powders,” Powder Technol., 264, 310-319 (2014). https://doi.org/10.1016/j.powtec.2014.05.033
15. A. Jurov, J. Zavasnik, and U. Cvelbar, “Investigation of carbon nanostructure synthesis pathway with plasma treatment of ethanol,” ECS Meeting Abstracts, 897 (2022). https://doi.org/10.1149/MA2022-0219897mtgabs
16. P. Jacquot, M. Buvron, and J.P. Souchard, “Plasma nitriding and plasma carburizing of pure titanium and Ti6Al4V alloy,” Mater. Sci. Forum, 102-104, 301-318 (1992). https://doi.org/10.4028/www.scientific.net/MSF.102-104.301