The 42CrMo4 low-alloy steel shafts, gears, and other high-strength parts used in the automotive industry offer a strong balance of toughness, strength, and surface quality. Traditionally, alloy development has relied on empirical knowledge and repeated experimental trials to adjust chemical composition and achieve targeted mechanical properties. In this study, we developed a machine learning model to predict the mechanical properties of 42CrMo4 steel from its chemical composition. Our dataset comprised 1,000 heat measurements listed as weight percentages, along with tensile strength, yield strength, proof stress at 0.2%, and surface roughness (R_a) from machining. After removing anomalous data with extreme or inconsistent compositional values, nine key alloying elements, Ti, Ni, Cr, Mo, Cu, Mn, P, Si, and C, were selected as input parameters for the machine learning model.

Different machine learning models were trained separately for each identified property, ensuring tailored predictions. We tune their hyperparameters using a five-fold cross-validation grid search, helping us find the best settings. The Gradient Boosting Regressor algorithm performs well, showcasing its effectiveness and reliability, with R² values ranging from 0.64 to 0.73 across the four targets, indicating reliable predictions. Additionally, error metrics such as root mean squared error and mean absolute error indicate that proposed predictions remain within practical engineering limits, providing confidence in their accuracy.

To improve the model, we employed important grouped features and correlation heatmaps for our analyses. These show that Ti, Ni, Cr, and Mo contribute most to strength properties, while Mn, P, and Si have a greater impact on R_a. Further, the results are comparable to the metallurgical information on solid-solution strengthening, carbide formation, and surface finish sensitivity. The suggested framework demonstrates that composition-based machine learning models can support alloy design, reduce experimental trials, and provide a digital tool for predicting the mechanical properties of 42CrMo4 steel.

42CrMo4 steel, low-alloy steel, machine learning algorithms, Gradient Boosting Regressor, mechanical properties

Ahmed, R., Kumar, V., Faisal, N. H., Al-Marri, M. J., & Davies, S. (2025). Influence of alloy composition on the tribomechanical properties of 50% blend of CoCrWMoCFeNiSiMn (Stellite 1) and CoCrMoCFeNiSiMn (Stellite 21) alloys. Journal of Materials Engineering and Performance. https://doi.org/10.1007/s11665-025-11034-7

Ammar, M. H. A. (2021). Advanced digital twins for condition monitoring, diagnosis, and predictive remaining life using artificial intelligence (Doctoral dissertation, Brunel University London). Brunel University Research Archive. https://bura.brunel.ac.uk/bitstream/2438/28074/1/FulltextThesis.pdf

Bilbao, O., Loizaga, I., Alonso, J., Girot, F., & Torregaray, A. (2023). 42CrMo4 steel flow behavior characterization for high temperature closed dies hot forging in automotive components applications. Heliyon, 9(11), e22256. https://doi.org/10.1016/j.heliyon.2023.e22256

Cheng, H., He, Z., Ge, M., Che, L., Zheng, K., Si, T., & Zhao, F. (2024). Composition design and optimization of Fe–C–Mn–Al steel based on machine learning. Physical Chemistry Chemical Physics, 26(10), 8219. https://doi.org/10.1039/d3cp05453e

Colla, V., Vannucci, M., Matino, I., & Valentini, R. (2023). A deep learning-based approach to the estimation of Jominy profile of medium-carbon quench hardenable steels. Steel Research International, 95(2). https://doi.org/10.1002/srin.202300374

Dong, J., Pei, W., Ji, H., Long, H., Fu, X., & Duan, H. (2020). Fatigue crack propagation experiment and numerical simulation of 42CrMo steel. Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science, 234(14), 2852. https://doi.org/10.1177/0954406220910458

D’Urso, D., Chiacchio, F., Cavalieri, S., Gambadoro, S., & Khodayee, S. M. (2023). Predictive maintenance of standalone steel industrial components powered by a dynamic reliability digital twin model with artificial intelligence. Reliability Engineering & System Safety, 243, 109859. https://doi.org/10.1016/j.ress.2023.109859

Duda, M., Rozumek, D., Lesiuk, G., Smolnicki, M., Babiarczuk, B., & Warycha, J. (2021). Fatigue crack growth under mixed-mode I + II and I + III in heat treated 42CrMo4 steel. International Journal of Fracture, 234, 235. https://doi.org/10.1007/s10704-021-00585-0

Gladman, T. (1997). The physical metallurgy of microalloyed steels. The Institute of Materials.

Guo, K., Yang, Z., Yu, C., & Buehler, M. J. (2020). Artificial intelligence and machine learning in design of mechanical materials. Materials Horizons, 8(4), 1153. https://doi.org/10.1039/d0mh01451f

Honeycombe, R. W. K., & Bhadeshia, H. K. D. H. (2006). Steels: Microstructure and properties (3rd ed.). Elsevier Butterworth-Heinemann.

Huang, J., Ando, D., & Sutou, Y. (2024). Heat-resistant aluminum alloy design using explainable machine learning. Materials & Design, 243, 113057. https://doi.org/10.1016/j.matdes.2024.113057

Javed, M. F., Fawad, M., Lodhi, R. H., Najeh, T., & Gamil, Y. (2024). Forecasting the strength of preplaced aggregate concrete using interpretable machine learning approaches. Scientific Reports, 14(1), 8381. https://doi.org/10.1038/s41598-024-57896-0

Kaur, R., Kumar, R., & Aggarwal, H. (2025). Systematic review of artificial intelligence, machine learning, and deep learning in machining operations: Advancements, challenges, and future directions. Archives of Computational Methods in Engineering, 32, 4983–5036. https://doi.org/10.1007/s11831-025-10290-z

Lee, J.-W., Park, C., Lee, B. D., Park, J., Goo, N. H., & Sohn, K. (2021). A machine-learning-based alloy design platform that enables both forward and inverse predictions for thermo-mechanically controlled processed (TMCP) steel alloys. Scientific Reports, 11(1). https://doi.org/10.1038/s41598-021-90237-z

Leni, D., Earnestly, F., Sumiati, R., Adriansyah, A., & Kusuma, Y. P. (2023). Evaluasi sifat mekanik baja paduan rendah berdasarkan komposisi kimia dan suhu perlakuan panas menggunakan teknik exploratory data analysis (EDA). Dinamika Teknik Mesin, 13(1), 74. https://doi.org/10.29303/dtm.v13i1.624

Li, Z., Wang, Z., Wang, Z., Qin, Z., Liu, F., Tan, L., Jin, X., Fan, X., & Huang, L. (2022). Quantifying solid solution strengthening in nickel-based superalloys via high-throughput experiment and machine learning. Computer Modeling in Engineering & Sciences, 135(2), 1521. https://doi.org/10.32604/cmes.2022.021639

Ling, J., Hutchinson, M., Antono, E., DeCost, B., Holm, E. A., & Meredig, B. (2017). Building data-driven models with microstructural images: Generalization and interpretability. Materials Discovery, 10, 19–27. https://doi.org/10.1016/j.md.2018.03.002

Mazini, J. P., Filho, A. I., Ávila, B. M. R., da Silva, R. V., & de Oliveira, P. G. B. (2022). Microstructure and mechanical properties of microalloyed steels containing molybdenum. Materials Research, 25. https://doi.org/10.1590/1980-5373-mr-2021-0608

Mohanty, T., Chandran, K. S. R., & Sparks, T. D. (2022). Machine learning guided optimal composition selection of niobium alloys for high temperature applications. ChemRxiv. https://doi.org/10.26434/chemrxiv-2022-1d9k0

Mudda, S., Hegde, A., Sharma, S., Gurumurthy, B. M., Shettar, M., & Shankar, M. C. G. (2025). Effect of various heat treatment methods and optimization of their parameters on mechanical properties of AISI 4140 steel. Scientific Reports, 15(1), 31854. https://doi.org/10.1038/s41598-025-17299-1

Muhammad, W., Kang, J., Ibragimova, O., & Inal, K. (2022). Experimental investigation and development of a deep learning framework to predict process-induced surface roughness in additively manufactured aluminum alloys. Welding in the World, 67(4), 897. https://doi.org/10.1007/s40194-022-01445-8

Pathan, M. V., Ponnusami, S. A., Pathan, J., Pitisongsawat, R., Erice, B., Petrinic, N., & Tagarielli, V. L. (2019). Predictions of the mechanical properties of unidirectional fibre composites by supervised machine learning. Scientific Reports, 9(1). https://doi.org/10.1038/s41598-019-50144-w

Peng, J., Yamamoto, Y., Hawk, J. A., Lara-Curzio, E., & Shin, D. (2020). Coupling physics in machine learning to predict properties of high-temperature alloys. npj Computational Materials, 6(1). https://doi.org/10.1038/s41524-020-00407-2

Romanov, V., & Hawk, J. A. (2019). Data analytics for designing Fe-9Cr steels. U.S. Department of Energy Office of Scientific and Technical Information. https://www.osti.gov/biblio/1569972

Sivakumar, E. R., Krishna, R., Senthilkumar, P., & Çolak, İ. (2022). Influence of mechanical properties of coating and substrate on wear performance of HDLC and TiN-coated AISI 5140 alloy steel. Proceedings of the Institution of Mechanical Engineers, Part E: Journal of Process Mechanical Engineering. https://doi.org/10.1177/09544089221132434

Tan, R. R., Li, Z., Zhao, S., & Birbilis, N. (2023). A primitive machine learning tool for the mechanical property prediction of multiple principal element alloys. arXiv. https://doi.org/10.48550/arxiv.2308.07649

Tiwari, S., Ahn, H. S., Reddy, M. H., Park, N., & Reddy, N. S. (2025). Mechanical property prediction of industrial low-carbon hot-rolled steels using artificial neural networks. Materials, 18(13), 2966. https://doi.org/10.3390/ma18132966

Totten, G. E. (2006). Steel heat treatment: Metallurgy and technologies. CRC Press.

Trent, E. M., & Wright, P. K. (2000). Metal cutting (4th ed.). Butterworth-Heinemann.

Wang, C., Shen, C., Cui, Q., Zhang, C., & Xu, W. (2019). Tensile property prediction by feature engineering guided machine learning in reduced activation ferritic/martensitic steels. Journal of Nuclear Materials, 529, 151823. https://doi.org/10.1016/j.jnucmat.2019.151823

Wang, K., Gupta, V., Lee, C. S., Mao, Y., Kilic, M. N. T., Li, Y., Huang, Z., Liao, W.-K., Choudhary, A., & Agrawal, A. (2024). XElemNet: Towards explainable AI for deep neural networks in materials science. Scientific Reports, 14, 25178. https://doi.org/10.1038/s41598-024-76535-2

Wei, Q., Xiong, J., Sun, S., & Zhang, T. (2021). Multi-objective machine learning of four mechanical properties of steels. Scientia Sinica Technologica, 51(6), 722. https://doi.org/10.1360/sst-2020-0475

Xiong, J., Zhang, T., & Shi, S. (2020). Machine learning of mechanical properties of steels. Science China Technological Sciences, 63(7), 1247. https://doi.org/10.1007/s11431-020-1599-5

Yang, X., El-Fallah, G. M. A. M., Tao, Q., Fu, J., Leng, C., Shepherd, J., & Dong, H. (2022). Dimensionality reduction for machine learning using statistical methods: A case study on predicting mechanical properties of steels. Materials Today Communications, 34, 105162. https://doi.org/10.1016/j.mtcomm.2022.105162

Yarasu, V., & Podgornik, B. (2025). An optimized machine-learning tool to predict heat treatment response of hot-work tool steels. Results in Engineering, 26, 105260. https://doi.org/10.1016/j.rineng.2025.105260

Zhang, C., Gu, X., Bhandari, U., Lei, J., Guo, S., Kourouma, M., Karoui, A., & Yang, S. (2022). Machine learning prediction of the mechanical properties of refractory multicomponent alloys based on a dataset of phase and first principles simulation. Frontiers in Metals and Alloys, 1. https://doi.org/10.3389/ftmal.2022.1036656

Zhang, Y., Sun, C., Gao, L., Yue, Z., Shabbir, S., Xu, W., Wu, M., & Yu, J. (2020). Determination of minor metal elements in steel using laser-induced breakdown spectroscopy combined with machine learning algorithms. Spectrochimica Acta Part B: Atomic Spectroscopy, 166, 105802. https://doi.org/10.1016/j.sab.2020.105802