Optimizing prediction of stainless steel mechanical properties with random forest: a comparison of feature selection methods

Maimuzar Maimuzar; Hendra Hendra; Syarif Khan; Desmarita Leni; Islahuddin Islahuddin

doi:10.30811/jpl.v22i5.5381

Optimizing prediction of stainless steel mechanical properties with random forest: a comparison of feature selection methods

Maimuzar Maimuzar, Hendra Hendra, Syarif Khan, Desmarita Leni, Islahuddin Islahuddin

Abstract

In machine learning, predicting the mechanical properties of stainless steel, such as Yield Strength (YS), Ultimate Tensile Strength (UTS), and Elongation (EL), requires many input variables, such as chemical composition, type of heat treatment, heating duration, and cooling method. However, the complexity and number of these variables can increase processing time and reduce model accuracy. This study aims to explore the impact of selecting the most influential input variables to improve prediction accuracy. We compared two feature selection techniques: Recursive Feature Elimination (RFE), which systematically removes less important features, and Information Gain (IG), which measures the contribution of each variable to the target prediction. Both techniques were implemented using the random forest algorithm, chosen for its robustness in handling large datasets and its ability to capture complex interactions between variables. Parameter optimization was performed using a grid search. The analysis showed that the RFE-based model outperformed both the IG-based model and the model without feature selection. In predicting YS, RFE identified 13 out of 21 influential variables, achieving a Mean Absolute Error (MAE) of 9.91, Root Mean Square Error (RMSE) of 14.20, and R-squared value of 0.89. For UTS, RFE identified 8 out of 21 variables, with an MAE of 12.89, RMSE of 16.97, and R-squared of 0.97. In predicting EL, RFE identified 14 out of 21 variables, with an MAE of 3.82, RMSE of 6.10, and an R-squared value of 0.85. The high R-squared values (>0.85) across all properties indicate the model’s strong predictive capabilities, making it suitable for practical applications in predicting the mechanical properties of stainless steel.

Keywords

Optimization,stainless steel, mechanical properties, random forest.

Full Text:

PDF

References

. [1] Momeni, M. M., &Motalebian, M. (2021). Chromium-doped titanium oxide nanotubes grown via one-step anodization for efficient photocathodic protection of stainless steel. Surface and Coatings Technology, 420, 127304.

. Rabi, MM (2020). Analysis and design of stainless steel reinforced concrete structural elements (Doctoral dissertation, Brunel University London).

. Tabrizikahou, A., Kuczma, M., Łasecka-Plura, M., Farsangi, E.N., Noori, M., Gardoni, P., & Li, S. (2022). Application and modeling of Shape-Memory Alloys for structural vibration control: State-of-the-art review. Construction and Building Materials, 342, 127975.

. Kumar, P., Jayaraj, R., Suryawanshi, J., Satwik, U.R., McKinnell, J., &Ramamurty, U. (2020). Fatigue strength of additively manufactured 316L austenitic stainless steel. ActaMaterialia, 199, 225-239.

. Morini, A. A., Ribeiro, M. J., &Hotza, D. (2019). Early-stage materials selection based on embodied energy and carbon footprint. Materials & Design, 178, 107861.

. Wang, C., Zhu, P., Lu, Y. H., & Shoji, T. (2022). Effect of heat treatment temperature on microstructure and tensile properties of austenitic stainless 316L using wire and arc additive manufacturing. Materials Science and Engineering: A, 832, 142446.

. Pan, M., Zhang, X., Chen, P., Su, X., &Misra, RDK (2020). The effect of chemical composition and annealing conditions on the microstructure and tensile properties of a resource-saving duplex stainless steel. Materials Science and Engineering: A, 788, 139540.

. Leni, D. (2023). Prediction Modeling of Low Alloy Steel Based on Chemical Composition and Heat Treatment Using Artificial Neural Network. Polymachinery Journal, 21(5), 54-61.

. Leni, D., Karudin, A., Abbas, M. R., Sharma, J. K., &Adriansyah, A. (2024). Optimizing stainless steel tensile strength analysis: through data exploration and machine learning design with Streamlit. EUREKA: Physics and Engineering, (5), 73-88.

. Laleh, M., Sadeghi, E., Revilla, R.I., Chao, Q., Haghdadi, N., Hughes, A.E., ...& Tan, M.Y. (2023). Heat treatment for metal additive manufacturing. Progress in Materials Science, 133, 101051.

. Vorontsov, A., Astafurov, S., Melnikov, E., Moskvina, V., Kolubaev, E., &Astafurova, E. (2021). The microstructure, phase composition and tensile properties of austenitic stainless steel in a wire-feed electron beam melting combined with ultrasonic vibration. Materials Science and Engineering: A, 820, 141519.

. Luo, M., Zhou, G.Y., Shen, H., Wang, X.T., Li, M.C., Zhang, Z.H., & Cao, G.H. (2022). Effect of Tempering Temperature on Microstructure and Sulfide Stress Cracking of 125 Ksi Grade Casing Steel. Materials, 15(7), 2589.

. Packwood, D., Nguyen, LTH, Cesana, P., Zhang, G., Staykov, A., Fukumoto, Y., & Nguyen, D.H. (2022). Machine learning in materials chemistry: An invitation. Machine learning with applications, 8, 100265.

. Leni, D., Sumiati, R., Angelia, N., & Nofriyanti, E. (2023). The Influence of Heatmap Correlation-based Feature Selection on Predictive Modeling of Low Alloy Steel Mechanical Properties Using Artificial Neural Network (ANN) Algorithm. Journal of Energy, Materials, and Instrumentation Technology, 4(4), 152-162.

. Liu, W., & Wang, J. (2021). Recursive elimination–election algorithms for wrapper feature selection. Applied Soft Computing, 113, 107956.

. Jiang, X., Jia, B., Zhang, G., Zhang, C., Wang, X., Zhang, R., ...& Ma, H. (2020). A strategy combining machine learning and multiscale calculation to predict tensile strength for pearlitic steel wires with industrial data. ScriptaMaterialia, 186, 272-277.

. Agrawal, A., &Choudhary, A. (2018). An online tool for predicting fatigue strength of steel alloys based on ensemble data mining. International Journal of Fatigue, 113, 389-400.

. Ruiz, E., Ferreño, D., Cuartas, M., López, A., Arroyo, V., & Gutiérrez-Solana, F. (2020). Machine learning algorithms for the prediction of the strength of steel rods: an example of data-driven manufacturing in steelmaking. International Journal of Computer Integrated Manufacturing, 33(9), 880-894.

. Narayana, PL, Lee, SW, Park, CH, Yeom, JT, Hong, JK, Maurya, AK, & Reddy, NS (2020). Modeling high-temperature mechanical properties of austenitic stainless steels by neural networks. Computational Materials Science, 179, 109617.

. The British Steelmakers Creep Committee: BSCC High Temperature Data; The Iron and Steel Institute: London, UK, 1973.

. Materials Algorithms Project. Available online: https://www.phase-trans.msm.cam.ac.uk/map (accessed on 11 April 2022).

. Leni, D., Kesuma, D. S., Maimuzar, Haris, &Afriyani, S. (2024). Prediction of Mechanical Properties of Austenitic Stainless Steels with the Use of Synthetic Data via Generative Adversarial Networks. Engineering Proceedings, 63(1), 4.

. AGRAWAL, Ankit, et al. Exploration of data science techniques to predict fatigue strength of steel from composition and processing parameters. Integrating Materials and Manufacturing Innovation, 2014, 3: 90-108.

. Deepa, B., & Ramesh, K. (2022). Epileptic seizure detection using deep learning through min max scaler normalization. Int. J. Health Sci, 6, 10981-10996.

. Jeon, H., & Oh, S. (2020). Hybrid-recursive feature elimination for efficient feature selection. Applied Sciences, 10(9), 3211.

. Lin, X., Yang, F., Zhou, L., Yin, P., Kong, H., Xing, W., ...&Xu, G. (2012). A support vector machine-recursive feature elimination feature selection method based on artificial contrast variables and mutual information. Journal of chromatography B, 910, 149-155.

. Pham, BT, Jaafari, A., Avand, M., Al-Ansari, N., Dinh Du, T., Yen, HPH, ...&Tuyen, TT (2020). Performance evaluation of machine learning methods for forest fire modeling and prediction. Symmetry, 12(6), 1022.

. Hu, M., Tan, Q., Knibbe, R., Wang, S., Li, X., Wu, T., ...& Zhang, MX (2021). Prediction of mechanical properties of wrought aluminum alloys using feature engineering assisted machine learning approach. Metallurgical and Materials Transactions A, 52(7), 2873-2884.

. Xiong, J., Zhang, T., & Shi, S. (2020). Machine learning of mechanical properties of steels. Science China Technological Sciences, 63(7), 1247-1255.

. Zhang, S., Jiang, Z., Li, H., Zhang, B., Fan, S., Li, Z., ...& Zhu, H. (2018). Precipitation behavior and phase transformation mechanism of super austenitic stainless steel S32654 during isothermal aging. Materials characterization, 137, 244-255.

. Moniruzzaman, F.M., Shakil, S.I., Shaha, S.K., Kacher, J., Nasiri, A., Haghshenas, M., &Hadadzadeh, A. (2023). Study of direct aging heat treatment of additively manufactured PH13–8Mo stainless steel: role of the manufacturing process, phase transformation kinetics, and microstructure evolution. Journal of Materials Research and Technology, 24, 3772-3787.

. Niu, M. C., Yang, K., Luan, J. H., Wang, W., & Jiao, Z. B. (2022). Cu-assisted austenite reversion and enhanced TRIP effect in maraging stainless steels. Journal of Materials Science & Technology, 104, 52-58.

. Bleck, W., Guo, X., & Ma, Y. (2017). The TRIP effect and its application in cold formable sheet steels. Steel Research International, 88(10), 1700218.

. Cronemberger, MER, Mariano, NA, Coelho, MF, Pereira, JN, Ramos, É. C., de Mendonça, R., ...&Maestrelli, S.C. (2014, December). Study of cooling rate influence on SAF 2205 duplex stainless steel solution

. Probst, P., &Boulesteix, A.L. (2018). To tune or not to tune the number of trees in random forest. Journal of Machine Learning Research, 18(181), 1-18.

. Probst, P., Wright, M.N., &Boulesteix, A.L. (2019). Hyperparameters and tuning strategies for random forests. Wiley Interdisciplinary Reviews: data mining and knowledge discovery, 9(3), e1301.

. Probst, P., &Boulesteix, A.L. (2018). To tune or not to tune the number of trees in random forest. Journal of Machine Learning Research, 18(181), 1-18.

. Lin, S., Zheng, H., Han, B., Li, Y., Han, C., & Li, W. (2022). Comparative performance of eight ensemble learning approaches for the development of models of slope stability prediction. ActaGeotechnica, 17(4), 1477-1502.

. Ibrahim, M. (2022). Evolution of Random Forest from Decision Trees and Bagging: A Bias-Variance Perspective. Dhaka University Journal of Applied Science and Engineering, 7(1), 66-71.

. Lamba, R., Gulati, T., & Jain, A. (2022). A hybrid feature selection approach for Parkinson's detection based on mutual information gain and recursive feature elimination. Arabian Journal for Science and Engineering, 47(8), 10263-10276.

. Wang, X., Guo, B., Shen, Y., Zhou, C., &Duan, X. (2019). Input feature selection method based on feature set equivalence and mutual information gain maximization. IEEE Access, 7, 151525-151538.

. Raschka, S. (2018). Model evaluation, model selection, and algorithm selection in machine learning. arXiv preprint arXiv:1811.12808.

DOI: http://dx.doi.org/10.30811/jpl.v22i5.5381