Eng
Ukr
  1. Publishing House
  2. Journals
  3. Electrometallurgy Today
  4. 2026

Electrometallurgy Today, 2026, №03

Print
2026 №03 (05) 2026 №03 (07)

Electrometallurgy Today 2026 №03


"Suchasna Elektrometallurgiya" (Electrometallurgy Today), 2026, #3, 42-51 pages

Influence of statistical analysis methods on prediction of the microstructure and properties of high-strength low-alloy steels

V.A. Kostin

E.O. Paton Electric Welding Institute of the NAS of Ukraine 11 Kazymyr Malevych Str., 03150, Kyiv, Ukraine. E-mail: valerykostinepwi@gmail.com

Abstract
The paper presents complex statistical analysis of the properties of high-strength low-alloy steels (HSLA, HSA, SSHA, ASSHA) with application of a wide data base. The modern methods of data analysis, including correlation analysis, principal component analysis (PCA), as well as machine learning (Random Forest, XGBoost) and SHAP values and interpreted matrices were used to study the interrelation between the chemical composition, microstructure and mechanical properties of steels. Key elements and parameters, having the maximal impact on strength, ductility and thermal resistance were determined for each group of steels. Optimal ranges of C, Nb, V, Ni content, as well as heat treatment modes, including austenitization temperature and cooling rate were substantiated. The results demonstrate that complex control of the composition and heat treatment allows developing steels with an excellent balance of service characteristic. Practical recommendations section presents specific tips as to metallurgical design of new steels, including the use of machine learning models for acceleration of development and optimization of steels. The work also discusses the research gaps, such as the need to standardize the data, study complex interaction of alloying elements, phase transformation dynamics, and prospects for implementation of AI methods. 12 Ref., 8 Fig.
Keywords: high-strength low-alloy steels, statistical, correlation, cluster analysis, machine learning, microstructure, prediction of properties

Received: 02.10.2025
Received in revised form: 27.01.2026
Accepted: 14.07.2026
Posted online: 24.07.2026

References

1. Rashid, M.S. (1980) High-strength, low-alloy steels. Science, 208, 862–869. DOI: https://doi.org/10.1126/science.208.4446.862
2. Kuziak, R., Kawalla, R., Waengler, S. (2008) Advanced high strength steels for automotive industry. Archives of Civil and Mechanical Engineering, 8(2), 103–117. DOI: https://doi.org/10.1016/S1644-9665(12)60197-6
3. Muhammed, M., Mustapha, M. et al. (2020) Statistical review of microstructure-property correlation of stainless steel: Implication for pre- and post-weld treatment. Processes, 8(7), 811. DOI: https://doi.org/10.3390/pr8070811
4. Siwar Chibani, François-Xavier Coudert (2020) Machine learning approaches for the prediction of materials properties. APL Materials, 8(8), 080701. DOI: https://doi.org/10.1063/5.0018384
5. Chunyuan Cui, Guangming Cao (2023) A strategy combining machine learning and physical metallurgical principles to predict mechanical properties for hot rolled Ti micro-alloyed steels, J. of Materials Processing Technology, 311, 117810. DOI: https://doi.org/10.1016/j.jmatprotec.2022.117810
6. Agrawal, A., Choudhary, A. (2016) Perspective: Materials informatics and big data: Realizing the promise of data-driven materials science. APL Materials, 4(5), 053208. DOI: https://doi.org/10.1063/1.4946894
7. Harwarth, M, Brauer, A. et al. (2021) Influence of carbon on the microstructure evolution and hardness of Fe–13Cr–xC (x = 0–0.7 wt.%) stainless steel. Materials, 14(17), 5063. DOI: https://doi.org/10.3390/ma14175063
8. Bhadeshia, H.K.D.H., Honeycombe, R.W.K. (2006) Steels: Structure, properties, and design. 3th Ed. Butterworth-Heine mann (Ed.). DOI: https://doi.org/10.1016/B978-0-7506-8084-4.X5000-6
9. Li, G.Q., Shen, Y.F. et al. (2022) Microstructural evolution and mechanical properties of a micro-alloyed low-density δ-TRIP steel. Materials Science and Engineering: A, 848, 143430. DOI: https://doi.org/10.1016/j.msea.2022.143430
10. Di Schino, A., Testani, C. (2021) Heat treatment of steels. Metals, 11(8), 1168. DOI: https://doi.org/10.3390/met11081168
11. Xueyun, G., Haiyan, W., Huijie, T. rt al. (2023) Data-driven machine learning for alloy research: Recent applications and prospects. Materials Today Communications, 36, 106697. DOI: https://doi.org/10.1016/j.mtcomm.2023.106697
12. Chen, J, Shi, Z, Luo, X et al. (2025) Micro-alloying effects on microstructure and weldability of high-strength low-alloy steel: A Review. Materials, 18(5), 1036. DOI: https://doi.org/10.3390/ma18051036
This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Suggested Citation

V.A. Kostin (2026) Influence of statistical analysis methods on prediction of the microstructure and properties of high-strength low-alloy steels. Electrometallurgy Today, 03, 42-51.