Abstract
Non-metallic inclusions are unavoidably produced during steel casting resulting in lower mechanical strength and other detrimental effects. This study was aimed at developing a machine learning algorithm to classify castings of steel for tire reinforcement depending on the number and properties of inclusions, experimentally determined. 855 observations were available for training, validation and testing the algorithms, obtained from the quality control of the steel. 140 parameters are monitored during fabrication, which are the features of the analysis; the output is 1 or 0 depending on whether the casting is rejected or not. The following algorithms have been employed: Logistic Regression, K-Nearest Neighbors, Support Vector Classifier (linear and RBF kernels), Random Forests, AdaBoost, Gradient Boosting and Artificial Neural Networks. The reduced value of the rejection rate implies that classification must be carried out on an imbalanced dataset. Resampling methods and specific scores for imbalanced datasets (recall, precision and AUC rather than accuracy) were used. Random Forest was the most successful algorithm providing an AUC in the test set of 0.85. No significant improvements were detected after resampling. The optimized Random Forest allows the samples with a higher probability of being rejected to be selected, thus improving the effectiveness of the quality control. In addition, the optimized Random Forest has enabled to identify the most important features, which have been satisfactorily interpreted on a metallurgical basis.
Similar content being viewed by others
References
Ånmark, N., Karasev, A., & Jönsson, P. G. (2015). The effect of different non-metallic inclusions on the machinability of steels. Materials, 8(2), 751–783. https://doi.org/10.3390/ma8020751
Atkinson, H. V., & Shi, G. (2003). Characterization of inclusions in clean steels: A review including the statistics of extremes methods. Progress in Materials Science, 48(5), 457–520. https://doi.org/10.1016/S0079-6425(02)00014-2.
Boser, B. E., Guyon, I. M., & Vapnik, V. N. (1992). A training algorithm for optimal margin classifiers. In Proceedings of the fifth annual workshop on Computational learning theory - COLT ’92 (pp. 144–152). https://doi.org/10.1145/130385.130401.
Çaydaş, U., & Ekici, S. (2012). Support vector machines models for surface roughness prediction in CNC turning of AISI 304 austenitic stainless steel. Journal of Intelligent Manufacturing, 23(3), 639–650. https://doi.org/10.1007/s10845-010-0415-2.
Chen, S., Jiang, M., He, X., & Wang, X. (2012). Top slag refining for inclusion composition transform control in tire cord steel. International Journal of Minerals, Metallurgy, and Materials, 19(6), 490–498. https://doi.org/10.1007/s12613-012-0585-3.
Cheung, N., & Garcia, A. (2001). Use of a heuristic search technique for the optimization of quality of steel billets produced by continuous casting. Engineering Applications of Artificial Intelligence, 14(2), 229–238. https://doi.org/10.1016/S0952-1976(00)00075-0.
Choudhary, S. K., & Ghosh, A. (2009). Mathematical model for prediction of composition of inclusions formed during solidification of liquid steel. ISIJ International, 49(12), 1819–1827. https://doi.org/10.2355/isijinternational.49.1819
Cramer, J. S. (2002). The origins of logistic regression. https://doi.org/10.2139/ssrn.360300.
Cui, H., & Chen, W. (2012). Effect of boron on morphology of inclusions in tire cord steel. Journal of Iron and Steel Research International, 19(4), 22–27. https://doi.org/10.1016/S1006-706X(12)60082-X
Deshpande, P., Gautham, B., Cecen, A., Kalidindi, S. R., Agrawal, A., & Choudhary, A. (2013). Application of statistical and machine learning techniques for correlating properties to composition and manufacturing processes of steels. In M. L. C. T. H. Gumbsch (Ed.), 2nd World congress on integrated computational materials engineering (pp. 155–160).
Fileti, A. M. F., Pacianotto, T. A., & Cunha, A. P. (2006). Neural modeling helps the BOS process to achieve aimed end-point conditions in liquid steel. Engineering Applications of Artificial Intelligence, 19(1), 9–17. https://doi.org/10.1016/j.engappai.2005.06.002.
Galar, M., Fernandez, A., Barrenechea, E., Bustince, H., & Herrera, F. (2012). A review on ensembles for the class imbalance problem: Bagging-, boosting-, and hybrid-based approaches. IEEE Transactions on Systems, Man and Cybernetics Part C: Applications and Reviews, 42(4), 463–484. https://doi.org/10.1109/TSMCC.2011.2161285.
Gaye, H., Rocabois, P., Lehmann, J., & Bobadilla, M. (1999). Kinetics of inclusion precipitation during steel solidification. Steel Research, 70(8), 356–361. https://doi.org/10.1002/srin.199905653.
Geron, A. (2017). Hands-on nachine learning with scikit-learn and tensorflow. Newton: O’Reilly Media Inc.
Guido, S., & Müller, A. (2016). Introduction to machine learning with Python. A guide for data scientists. Newton: O’Reilly Media.
Hebb, D. (1949). The organization of behavior. New York: Wiley.
Holappa, L., & Wijk, O. (2014). Inclusion engineering. In S. Seetharaman (Ed.), Treatise on process metallurgy volume 3: Industrial processes (pp. 347–372). Amsterdam: Elsevier.
Holappa, L. E. K., & Helle, A. S. (1995). Inclusion control in high-performance steels. Journal of Materials Processing Technology, 53(1–2), 177–186. https://doi.org/10.1016/0924-0136(95)01974-J
Kirihara, K. (2011). Production technology of wire rod for high tensile strength steel cord. Kobelco Technology Review, 30, 62–65.
Lambrighs, K., Verpoest, I., Verlinden, B., & Wevers, M. (2010). Influence of non-metallic inclusions on the fatigue properties of heavily cold drawn steel wires. Procedia Engineering, 2(1), 173–181. https://doi.org/10.1016/j.proeng.2010.03.019.
Lehmann, J., Rocabois, P., & Gaye, H. (2001). Kinetic model of non-metallic inclusions’ precipitation during steel solidification. Journal of Non-Crystalline Solids, 282(1), 61–71. https://doi.org/10.1016/S0022-3093(01)00329-5.
Lipiński, T., & Wach, A. (2015). The effect of fine non-metallic inclusions on the fatigue strength of structural steel. Archives of Metallurgy and Materials, 60(1), 65–69. https://doi.org/10.1515/amm-2015-0010.
Maeda, S., Soejima, T., & Saito, T. (1989). Shape control of inclusions in wire rods for high tensile tire cord by refining with synthetic slag. In ISS (Ed.), Steelmaking conference proceedings (pp. 379–385). Warrendale, PA.
Mesa Fernández, J. M., Cabal, V. A., Montequin, V. R., & Balsera, J. V. (2008). Online estimation of electric arc furnace tap temperature by using fuzzy neural networks. Engineering Applications of Artificial Intelligence, 21(7), 1001–1012. https://doi.org/10.1016/j.engappai.2007.11.008.
Millman, S. (2004). Clean steel basic features and operation practices. In K. Wúnnenberg & S. Millman (Eds.), IISI study on clean steel (pp. 39–60). Brussels: IISI Committeee on Technology.
Mohamed, A. E. (2007). Comparative study of supervised machine learning techniques for intrusion detection. Acta Electrotechnica et Informatica, 14(3), 5–10. https://doi.org/10.15546/aeei-2014-0021
Mukherjee, U. (2017). How to handle imbalanced classification problems in machine learning? Analytics Vidhya. https://www.analyticsvidhya.com/blog/2017/03/imbalanced-classification-problem/.
Nilsson, N. J. (1965). Learning machines: Foundations of trainable pattern-classifying systems. New York: McGraw-Hill Companies.
Ordieres-Meré, J., Martínez-de-Pisón-Ascacibar, F. J., González-Marcos, A., & Ortiz-Marcos, I. (2010). Comparison of models created for the prediction of the mechanical properties of galvanized steel coils. Journal of Intelligent Manufacturing, 21(4), 403–421. https://doi.org/10.1007/s10845-008-0189-y.
Pfeiler, C., Wu, M., & Ludwig, A. (2005). Influence of argon gas bubbles and non-metallic inclusions on the flow behavior in steel continuous casting. Materials Science and Engineering A, 413–414, 115–120. https://doi.org/10.1016/j.msea.2005.08.178.
Santos, C. A., Spim, J. A., & Garcia, A. (2003). Mathematical modeling and optimization strategies (genetic algorithm and knowledge base) applied to the continuous casting of steel. Engineering Applications of Artificial Intelligence, 16(5–6), 511–527. https://doi.org/10.1016/S0952-1976(03)00072-1.
Schapire, R. E. (1990). The strength of weak learnability. Machine Learning, 5(2), 197–227. https://doi.org/10.1007/BF00116037
Tashiro, H., & Tarui, T. (2003). State of the art for high tensile strength steel cord. Shinnittetsu Giho, (88), 87–91. http://www.nssmc.com/en/tech/report/nsc/pdf/n8818.pdf. Accessed 18 June 2020.
Van Ende, M.-A. (2010). Formation and morphology of non-metallic inclusions in aluminium killed steels. Universite Catholique De Lovain. Retrieved from http://hdl.handle.net/2078.1/29072.
Vapnik, V., & Chervonenkis, A. (1964). A note on one class of perceptrons. Automation and Remote Control, 25, 103–109.
Wintz, M., Bobadilla, M., Lehmann, J., & Gaye, H. (1995). Experimental study and modeling of the precipitation of non-metallic inclusions during solidification of steel. ISIJ International, 35(6), 715–722. https://doi.org/10.2355/isijinternational.35.715
Wuest, T., Irgens, C., & Thoben, K.-D. (2014). An approach to monitoring quality in manufacturing using supervised machine learning on product state data. Journal of Intelligent Manufacturing, 25(5), 1167–1180. https://doi.org/10.1007/s10845-013-0761-y.
Yan, W., Xu, H. C., & Chen, W. Q. (2014). Study on inclusions in wire rod of tire cord steel by means of electrolysis of wire rod. Steel Research International, 85(1), 53–59. https://doi.org/10.1002/srin.201300045.
Yilmaz, M., & Ertunc, H. M. (2007). The prediction of mechanical behavior for steel wires and cord materials using neural networks. Materials and Design, 28(2), 599–608. https://doi.org/10.1016/j.matdes.2005.07.016.
Yoon, B. H., Heo, K. H., Kim, J. S., & Sohn, H. S. (2013). Improvement of steel cleanliness by controlling slag composition. Ironmaking & Steelmaking, 29(3), 214–217. https://doi.org/10.1179/030192302225004160
You, D., Michelic, S. K., Presoly, P., Liu, J., & Bernhard, C. (2017). Modeling inclusion formation during solidification of steel: a review. Metals, 7(11), 460. https://doi.org/10.3390/met7110460
Zhang, L., & Thomas, B. G. (2006). State of the art in the control of inclusions during steel ingot casting. Metallurgical and Materials Transactions B, 37(5), 733–761.
Acknowledgments
This Project was carried out with the financial grant of the program I + C = + C, 2017, FOMENTO de la TRANSFERENCIA TECNOLÓGICA. The financial contribution from SODERCAN and the European Union through the program FEDER Cantabria are gratefully acknowledged. The authors would also like to express their gratitude to the technical staff of GLOBAL STEEL WIRE and, specially, to Mr. Rafael Piedra, Mr. Santiago Pascual and Mr. Jean-Francois Fourquet, without whom it would not have been possible to conduct this research.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Cuartas, M., Ruiz, E., Ferreño, D. et al. Machine learning algorithms for the prediction of non-metallic inclusions in steel wires for tire reinforcement. J Intell Manuf 32, 1739–1751 (2021). https://doi.org/10.1007/s10845-020-01623-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10845-020-01623-9