Abstract
Steel tubes produced in steelmaking plants are generally subjected to severe in-service conditions. Hence, quality control plays a key role in this process. The bottleneck is that this information is made available only after tube production from laboratory analysis. Given process complexity and current data availability, this work employs a series of machine learning techniques, namely neural networks, random forests and gradient boosting trees, to predict critical mechanical properties for steel tubes, namely yield strength, ultimate tensile strength and hardness. The model performance was kept high by combining different variable selection procedures. The prediction error was less than the inherent variability of each mechanical property, i.e., it is equal to 20 MPa for yield strength and ultimate tensile strength, and to 2 HRC, for hardness. This information in advance allows interventions before complete tube production contributing to more stable operations and, ultimately, to reduce rework and customer lead time. In sequence, an optimization problem for set point definition is illustrated. The neural predictive model previously identified for the yield strength was used in this application, exploring its predictive capabilities. The optimal solution yielded to lower amount of molybdenum and tube exit temperature from the tempering furnace, while keeping quality aspects, which means reduction in material and energy costs. Concluding, steelmaking processes, which are complex by nature, can strongly benefit from data-driven approaches, since data availability and computational processing are no longer a problem.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
W. Smith and J. Hashemi, Foundations of Materials Science and Engineering, 5th ed., McGraw-Hill, New York, 2009
G. Totten and M. Howes, Steel Heat Treatment Handbook, 2nd ed., CRC Press, Boca Raton, 1997
S. Pattanayak, S. Dey, S. Chatterjee, S. Chowdhury, and S. Datta, Computational Intelligence Based Designing of Microalloyed Pipeline Steel, Comput. Mater. Sci., 2015, 104, p 60–68
P. Sampaio, R. Corrêa, A. Braga, Modelagem das propriedades mecânicas de tubos de aço utilizando redes neurais artificiais (Mechanical properties modeling of steel tubes using artificial neural networks). Automation and IT Seminar, ABM (Brazilian Association of Metallurgy, Materials and Mining), 2015
A. Agrawal, P. Deshpande, A. Cecen, G. Basavarsu, A. Choudhary, and S. Kalidindi, Exploration of Data Science Techniques to Predict Fatigue Strength of Steel from Composition and Processing Parameters, Integr. Mater. Manuf. Innov., 2014, 3, p 3–8
D. Jones, J. Watson, and K. Brown, Comparison of Hot Rolled Steel Mechanical Property Prediction Models Using Linear Multiple Regression, Non-linear Multiple Regression and Non-linear Artificial Neural Networks, Comput. Mater. Sci., 2013, 32(5), p 435–442
J. Mori and V. Mahalec, Planning and Scheduling of Steel Plates Production. Part II: Scheduling of Continuous Casting, Comput. Chem. Eng., 2017, 101(9), p 312–325
J. Mori and V. Mahalec, Planning and Scheduling of Steel Plates Production. Part I: Estimation of Production Times via Hybrid Bayesian Networks for Large Domain of Discrete Variables, Comput. Chem. Eng., 2015, 79(4), p 113–134
L. Tang, J. Liu, A. Rong, and Z. Yang, A Review of Planning and Scheduling Systems and Methods for Integrated Steel Production, Eur. J. Oper. Res., 2001, 133(1), p 1–20
X. Chen, X. Chen, J. She, and M. Wu, A Hybrid Just-In-Time Soft Sensor for Carbon Efficiency of Iron Ore Sintering Process Based on Feature Extraction of Cross-sectional Frames at Discharge End, J. Process Control, 2017, 54, p 14–24
D. Laha, Y. Ren, and P. Suganthan, Modelling of Steelmaking Process with Effective Machine Learning Techniques, Expert Syst. Appl., 2015, 42(10), p 4687–4696
M. Bevilacqua, E. Bottani, F.E. Ciarapica, F. Costantino, L. di Donato, A. Ferraro, G. Mazzuto, A. Monteriù, G. Nardini, M. Ortenzi, M. Paroncini, M. Pirozzi, M. Prist, E. Quatrini, M. Tronci, and G. Vignali, Digital Twin Reference Model Development to Prevent Operators’ Risk in Process Plants, Sustainability, 2020, 12(1088), p 1–17
N.A. Carvalho, L.F. Scavarda, and L.J. Lustosa, Implementing Finite Capacity Production Scheduling: Lessons from a Practical Case, Int. J. Prod. Res., 2014, 52(4), p 1215–1230
R, The R Project for Statistical Computing, 2020. http://www.r-project.org/. Accessed 5 Oct 2019
F. Coelho, A.P. Braga, and M. Verleysen, A Mutual Information Estimator for Continuous and Discrete Variables Applied to Feature Selection and Classification Problems, Int. J. Comput. Intell. Syst., 2016, 9(4), p 726–733
F. Coelho, A.P. Braga, and M. Verleysen, Multi-objective semi-supervised feature selection and model selection based on Pearson’s correlation coefficient, Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications. Lecture Notes in Computer Science, Vol 6419, I. Bloch and R.M. Cesar, Ed., Springer, Berlin, 2010
I. Guyon, S. Gunn, M. Nikravesh, and L. Zaded, Feature Extraction: Foundations and Applications, Springer, New York, 2006
D.C. Montgomery, E.A. Peck, and G.G. Vining, Introduction to Linear Regression Analysis, Wiley, New York, 2012
S. Haykin, Neural Networks: A Comprehensive Foundation, Prentice Hall, Upper Saddle River, 1999
G. James, D. Witten, T. Hastie, and R. Tibshirani, An Introduction to Statistical Learning with Applications in R, Springer, New York, 2013
C. Gomes, A.L. Kaiser, J.P. Bas, A. Aissaoui, and M. Piette, Predicting the Mechanical Properties of a Quenched and Tempered Steel Thanks to a Tempering Parameter, Rev. Métall., 2010, 107, p 293–302
W. Callister, Materials Science and Engineering: An Introduction, Wiley, New York, 2007
M. Song, C. Sun, Y. Chen, Z. Shang, J. Li, Z. Fan, K.T. Hartwig, and X. Zhang, Grain Refinement Mechanisms and Strength-Hardness Correlation of Ultra-fine Grained Grade 91 Steel Processed by Equal Channel Angular Extrusion, Int. J. Press. Vessels Pip., 2019, 172, p 212–219
S.H. Hashemi, Strength–Hardness Statistical Correlation in API, X65 Steel, Mater. Sci. Eng. A, 2011, 528(3), p 1648–1655
M.-L. Zhu and F.-Z. Xuan, Correlation Between Microstructure, Hardness and Strength in HAZ of Dissimilar Welds of Rotor Steels, Mater. Sci. Eng. A, 2010, 527(16–17), p 4035–4042
E.J. Pavlina and J. Van Tyne, Correlation of Yield Strength and Tensile Strength with Hardness for Steels, J. Mater. Eng. Perform., 2008, 17, p 888–893
I.T. Jolliffe, Principal Component Analysis, Springer, New York, 2002
Y.S. Aurelio, G.M. Almeida, C.L. Castro, and A.P. Braga, Learning from Imbalanced Data Sets with Weighted Cross-entropy Function, Neural Process. Lett., 2019, 50, p 1937–1949
E. Krause, Taxicab Geometry: An Adventure in Non-Euclidean Geometry, Dover Publications, New York, 1987
S. Rao, Engineering Optimization: Theory and Practice, Wiley, New York, 2009
L. Scrucca, GA: A Package for Genetic Algorithms in R, J. Stat. Softw., 2013, 53(4), p 1–37
Acknowledgments
The authors thank the Vallourec unit in Brazil for both the data sets and the financial support. They also thank Rodolfo Dollinger, a data scientist in this steelmaking plant, for his contribution with respect to process data analysis. Antonio P. Braga thanks CNPq for the financial support.
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
Carneiro, M.V., Salis, T.T., Almeida, G.M. et al. Prediction of Mechanical Properties of Steel Tubes Using a Machine Learning Approach. J. of Materi Eng and Perform 30, 434–443 (2021). https://doi.org/10.1007/s11665-020-05345-0
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11665-020-05345-0