Application of Machine Learning in Heat Treatment Process Design of Carburized Steel

Di Jiang; Yihao Zheng; Chunyang Luo; Xuefei Wang; Chi Zhang; Zhaodong Wang

doi:10.1002/mgea.70060

Materials Genome Engineering Advances ›› 2026, Vol. 4 ›› Issue (2) :e70060 DOI: 10.1002/mgea.70060

RESEARCH ARTICLE

Application of Machine Learning in Heat Treatment Process Design of Carburized Steel

Author information +

History +

PDF (3528KB)

Abstract

The heat treatment process of carburized steel is crucial for determining its service performance potential. To overcome the efficiency and accuracy bottlenecks inherent in traditional development methods, this paper proposes a machine-learning-based approach for performance prediction and process optimization. This study constructed a high-dimensional database encompassing chemical composition, physical properties, and multi-stage heat treatment process parameters. With hardness gradient and coefficient of friction (COF) as prediction targets, the DT algorithm was selected through multi-model comparison. Through feature selection, an optimized model was developed, achieving prediction errors of 2.7% and 4.3% for hardness and COF, respectively. Furthermore, the SHAP method was used for model interpretability analysis, identifying critical process parameters such as quenching/tempering temperatures. The optimized process design, based on this approach, was validated through physical experiments: hardness prediction error was below 6%, and the predicted COF trend highly matched the measured results. The study demonstrates that this method can accurately predict performance and guide process optimization, exhibiting excellent potential for engineering applications.

Keywords

carburized steel / experimental validation / feature screening / machine learning / process optimization / SHAP analysis

Cite this article

Download citation ▾

Di Jiang, Yihao Zheng, Chunyang Luo, Xuefei Wang, Chi Zhang, Zhaodong Wang. Application of Machine Learning in Heat Treatment Process Design of Carburized Steel. Materials Genome Engineering Advances, 2026, 4 (2) : e70060 DOI:10.1002/mgea.70060

登录浏览全文

4963

注册一个新账户忘记密码

References

Publishing order | Descend order by publishing year | Descend order by cited within

[1]	K. Li, “Research on Gas Carburizing Process of Shaft Parts for Aircraft Engine,” Heat Treatment Technology and Equipment 31 (2010): 45–47, https://doi.org/10.19382/j.cnki.1673-4971.2010.01.013.

[2]	J. Peng, S. Zhou, and F. Lou, “Current Status and Development Trend of Steel and Heat Treatment Process for Automotive Carburized Gears,” Heat Treatment Technology and Equipment 28 (2007): 3–6, https://doi.org/10.19382/j.cnki.1673-4971.2007.01.002.

[3]	A. Wang, J. Gao, and M. Gu, “Heat Treatment of New Type High Alloy Carburizing Gear Steel 17CrNiMo6,” Heat Treatment of Metals 35 (2010): 82–86, https://doi.org/10.13251/j.issn.0254-6051.2010.10.021.

[4]	M. Preciado, P. Bravo, and J. Alegre, “Effect of Low Temperature Tempering Prior Cryogenic Treatment on Carburized Steels,” Journal of Materials Processing Technology 176, no. 1–3 (2006): 41–44, https://doi.org/10.1016/j.jmatprotec.2006.01.011.

[5]	H. Wang, B. Wang, Z. Wang, Y. Tian, and R. Misra, “Optimizing the Low-Pressure Carburizing Process of 16Cr3NiWMoVNbE Gear Steel,” Journal of Materials Science and Technology 35, no. 7 (2019): 1218–1227, https://doi.org/10.1016/j.jmst.2019.02.001.

[6]	Y. Zhang, Z. Tang, and L. He, “Real-Time Prediction Method of Carbon Concentration in Carburized Steel Based on a BP Neural Network,” Heat Treatment and Surface Engineering 6 (2024): 2350184, https://doi.org/10.1080/25787616.2024.2350184.

[7]	Z. Zhu and Y. Liang, “Prediction of Residual Stress of Carburized Steel Based on Machine Learning,” Applied Sciences 10, no. 21 (2020): 7759, https://doi.org/10.3390/app10217759.

[8]	R. Liang, Z. Wang, S. Yang, and W. Chen, “Study on Hardness Prediction and Parameter Optimization for Carburizing and Quenching: An Approach Based on FEM, ANN and GA,” Materials Research Express 8, no. 11 (2021): 116501, https://doi.org/10.1088/2053-1591/ac3279.

[9]	X. Liu, Y. Chen, Y. Lu, et al., “Present Research Situation and Prospect of Multi-Scale Design in Novel Co-Based Superalloys,” Acta Metallurgica Sinica 56 (2020): 1–20, https://doi.org/10.11900/0412.1961.2019.00159.

[10]	Z. Liu, T. Wang, J. Li, et al., “Towards High Stiffness and Ductility—The Mg–Al–Y Alloy Design Through Machine Learning,” Journal of Materials Science and Technology 221 (2025): 194–203, https://doi.org/10.1016/j.jmst.2024.09.038.

[11]	Z. Qin, H. Zhao, S. Zhang, et al., “Design of High Performance Cu–Ni–Si Alloys via a Multiobjective Strategy Based on Machine Learning,” Materials Today Communications 39 (2024): 108833, https://doi.org/10.1016/j.mtcomm.2024.108833.

[12]	C. Hao, Y. Sui, Y. Yuan, P. Li, H. Jin, and A. Jiang, “Composition Optimization Design and High Temperature Mechanical Properties of Cast Heat-Resistant Aluminum Alloy via Machine Learning,” Materials and Design 250 (2025): 113587, https://doi.org/10.1016/j.matdes.2025.113587.

[13]	W. Chen, W. Gou, Y. Li, et al., “Machine Learning Design of 400 MPa Grade Biodegradable Zn–Mn Based Alloys With Appropriate Corrosion Rates,” International Journal of Minerals, Metallurgy and Materials 31, no. 12 (2024): 2727–2736, https://doi.org/10.1007/s12613-024-2995-4.

[14]	Q. Liu, H. Wu, M. Paul, et al., “Machine-Learning Assisted Laser Powder Bed Fusion Process Optimization for AlSi10Mg: New Microstructure Description Indices and Fracture Mechanisms,” Acta Materialia 201 (2020): 316–328, https://doi.org/10.1016/j.actamat.2020.10.010.

[15]	J. Wang, X. Xu, R. Liu, et al., “Optimization Research of Machine Learning in High Strength Automotive Steel Plate Process,” Angang Technology 2 (2025): 37–44, https://doi.org/10.3969/j.issn.1006-4613.2025.02.005.

[16]	H. Mohrbacher, “Metallurgical Concepts for Optimized Processing and Properties of Carburizing Steel,” Advanced Manufacturing 4, no. 2 (2016): 105–114, https://doi.org/10.1007/s40436-016-0142-9.

[17]	A. Wang, M. Gu, H. Xu, et al., “Effect of Overheated Tempering on Mechanical Properties of Carburized and Quenched Gears,” Heat Treatment of Metals 38 (2013): 88–91, https://doi.org/10.13251/j.issn.0254-6051.2013.11.026.

[18]	A. Bensely, A. Prabhakaran, D. Lal, and G. Nagarajan, “Enhancing the Wear Resistance of Case Carburized Steel (En 353) by Cryogenic Treatment,” Cryogenics 45, no. 12 (2005): 747–754, https://doi.org/10.1016/j.cryogenics.2005.10.004.

[19]	S. Huang, G. Zhang, M. Wang, et al., “Fatigue Properties of Heavy-Duty Gear Steel With Different Carburized Depth,” Journal of Iron and Steel Research International 24 (2012): 34–38, https://doi.org/10.13228/j.boyuan.issn1001-0963.2012.04.006.

[20]	P. Kula, K. Dybowski, E. Wolowiec, and R. Pietrasik, “Boost-Diffusion Vacuum Carburising–Process Optimisation,” Vacuum 99 (2014): 175–179, https://doi.org/10.1016/j.vacuum.2013.05.021.

[21]	Z. Gao and G. Liu, “Advances in Online Materials Databases and Case Studies of NIMS/MatWeb,” Journal of Materials Engineering 11 (2013): 89–96, https://doi.org/10.3969/j.issn.1001-4381.2013.11.015.

[22]	E. Spotte-Smith, O. Cohen, S. Blau, et al., “A Database of Molecular Properties Integrated in the Materials Project,” Digital Discovery 2, no. 6 (2023): 1862–1882, https://doi.org/10.1039/d3dd00153a.

[23]	Y. Han, Q. Li, Y. Xu, et al., “Research Progress of Vacuum Low Pressure Carburizing Technology,” Heat Treatment of Metals 43 (2018): 253–261, https://doi.org/10.13251/j.issn.0254-6051.2018.10.050.

[24]	Q. Wang, Z. Meng, S. Qi, et al., “Effect of Temperature on the Sliding Wear Behaviors of Carburized BG801 Bearing Steel,” Materials 19, no. 5 (March 2026): 1034, https://doi.org/10.3390/ma19051034.

[25]	P. Stratton, S. Bruce, and V. Cheetham, “Low-Pressure Carburizing Systems: A Review of Current Technology,” BHM Berg- und Hüttenmännische Monatshefte 151, no. 11 (2006): 451–456, https://doi.org/10.1007/BF03165206.

[26]	S. Wang, “Effect of Heat Treatment Conditions on Microstructure and Mechanical Properties of 20CrMnTi Carburized Steel,” (Ph.D. Thesis, Shenyang University of Chemical Technology, 2023), https://doi.org/10.27905/d.cnki.gsghy.2023.000098.

[27]	W. Feng and J. Qiao, “Effect of Carburizing Temperature on Carburizing Layer of 20CrMnTi Gear Ring,” Hot Working Technology 51 (2022): 153–157, https://doi.org/10.14158/j.cnki.1001-3814.20193530.

[28]	N. Saunders, Z. Guo, X. Li, A. P. Miodownik, and J. P. Schillé, “Using JMatPro to Model Materials Properties and Behavior,” JOM 55, no. 12 (2003): 60–65, https://doi.org/10.1007/s11837-003-0013-2.

[29]	J. Zhang, Z. Wang, and X. Li, “Effect of Quenching and Tempering Temperature on Microstructure of 6Cr13 Martensitic Stainless Steel,” Heat Treatment of Metals 38 (2013): 107–108, https://doi.org/10.13251/j.issn.0254-6051.2013.03.029.

[30]	B. Gao, T. Xu, L. Wang, et al., “Achieving a Superior Combination of Tensile Properties and Corrosion Resistance in AISI420 Martensitic Stainless Steel by Low-Temperature Tempering,” Corrosion Science 225 (2023): 111551, https://doi.org/10.1016/j.corsci.2023.111551.

[31]	B. Ren, Q. Mu, W. Liang, et al., “Effect of Surface Carburizing Temperature on Wear Resistance of Ti2AlNb Alloy,” Transactions of Materials and Heat Treatment 37 (2016): 151–156, https://doi.org/10.13289/j.issn.1009-6264.2016.09.027.

[32]	L. Yin, X. Ma, G. Tang, et al., “Characterization of Carburized 14Cr14Co13Mo4 Stainless Steel by Low Pressure Carburizing,” Surface & Coatings Technology 358 (2019): 654–660, https://doi.org/10.1016/j.surfcoat.2018.11.090.