The use of regressors for knowledge discovery on the ambient tensile test

• Keila de C. Freitas USIMINAS / Federal University of Ouro Preto (UFOP)
• Kairo de B. Guimarães USIMINAS
• Luxmar A. Xavier USIMINAS
• Thiago A. de O. Silva Federal University of Ouro Preto (UFOP)

DOI: https://doi.org/10.5753/sbbd.2023.231741

Abstract

The ambient tensile test is responsible for evaluating mechanical properties in the steelmaking process, which returns results such as: resistance limit (LR), yield strength (LE) and elongation (ALO). The objective is to build models for each property, using process variables and chemical composition data, to predict the test responses, helping in the analyzes carried out by specialists. Nine different regression algorithms with satisfactory determination coefficients for the three indicators were adjusted. The resulting models contribute to the decision making of the test by obtaining gains in sample evaluation time and also by proposing a method that identifies false positives.

Keywords: Ambient Tensile Testing, Industry Applications, Regressors

References

Alpaydin, E. (2020). Introduction to machine learning. MIT press.

Bahrami, A., Anijdan, S. M., and Ekrami, A. (2005). Prediction of mechanical properties of dp steels using neural network model. Journal of alloys and compounds, 392(1-2):177–182.

Chollet, F. et al. (2015). Keras. https://keras.io.

de Souza, S. A. (1989). Composição química dos aços. Editora Blucher.

Fayyad, U. M., Piatetsky-Shapiro, G., Smyth, P., et al. (1996). Knowledge discovery and data mining: Towards a unifying framework. In Proceedings of KDD-96, pages 82–88.

Johnson, G. R. and Cook, W. H. (1985). Fracture characteristics of three metals subjected to various strains, strain rates, temperatures and pressures. Engineering fracture mechanics, 21(1):31–48.

Kliauga, A. M. and Ferrante, M. (2009). Metalurgia basica para ourives e designers: do metal à joia. Editora Blucher.

Lin, Y., Chen, X.-M., and Liu, G. (2010). A modified johnson–cook model for tensile behaviors of typical high-strength alloy steel. Materials Science and Engineering: A, 527(26):6980–6986.

Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., and Duchesnay, E. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12:2825–2830.

Raschka, S. (2015). Python machine learning. Packt publishing ltd.

Zhang, C. and Ma, Y. (2012). Ensemble machine learning: methods and applications. Springer.