Abstract
The development of steels requires multiples manufacturing steps and involves a high number of variables and non-linear processes. Although there are data-driven models used to predict such steels’ mechanical properties, their design often requires specialized Machine Learning knowledge, hampering the application of such models. In this paper, an Automated Machine Learning (AutoML) framework, namely Auto-Keras, was employed to generate and train a data-driven model on a steel data-set through Neural Architecture Search. This paper proposes predicting the mechanical properties of steels applying Artificial Neural Networks (ANN) as a multivariate regression problem using AutoML. The results show that even with a vast parameter search space, it is possible to generate ANNs with different architectures that provide high performance with free and open-source AutoML. Three ANNs with different activation functions were optimized using Auto-Keras and compared.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Abiodun, O.I., Jantan, A., Omolara, A.E., Dada, K.V., Mohamed, N.A., Arshad, H.: State-of-the-art in artificial neural network applications: a survey. Heliyon 4(11), e00938 (2018)
Saltelli, A., Ratto, M., Andres, T., Campolongo, F., Cariboni, J., Gatelli, D., Michaela Saisana, S.T.: Global Sensitivity Analysis: The Primer, vol. 76 (2008)
van Bohemen, S.M.: Exploring the correlation between the austenite yield strength and the bainite lath thickness. Mater. Sci. Eng. A 731, 119–123 (2018)
Chai, Q., Gong, G.: Verifiable symmetric searchable encryption for semi-honest-but-curious cloud servers. In: IEEE International Conference on Communications, pp. 917–922 (2012)
Chen, L.C., Collins, M.D., Zhu, Y., Papandreou, G., Zoph, B., Schroff, F., Adam, H., Shlens, J.: Searching for efficient multi-scale architectures for dense image prediction. In: Advances in Neural Information Processing Systems (NIPS), December 2018, pp. 8699–8710 (2018)
Deng, Y., Qiao, L., Zhu, J., Yang, B.: Mechanical performance and microstructure prediction of hypereutectoid rail steels based on BP neural networks. IEEE Access 8, 41905–41912 (2020)
Eres-Castellanos, A., Toda-Caraballo, I., Latz, A., Caballero, F.G., Garcia-Mateo, C.: An integrated-model for austenite yield strength considering the influence of temperature and strain rate in lean steels. Mater. Des. 188, 108435 (2020)
Filho, J.F.D.S.: Efeitos da adição de Cr, Mo, Si e parâmetros de processos na transformação de fases e propriedades mecânicas de aços bifásicos. Ph.D. thesis, UFSC (2016)
Hayakawa, Y., Szpunar, J.A.: A comprehensive model of recrystallization for interstitial free steel. Acta Materialia 45(9), 3721–3730 (1997)
Jha, D., Ward, L., Paul, A., Keng Liao, W., Choudhary, A., Wolverton, C., Agrawal, A.: ElemNet: deep learning the chemistry of materials from only elemental composition. Sci. Rep. 8(1), 1–13 (2018)
Jin, H., Song, Q., Hu, X.: Auto-keras: an efficient neural architecture search system. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 1946–1956. ACM (2019)
Lipovetsky, S., Conklin, M.: Analysis of regression in game theory approach. Appl. Stoch. Models Bus. Ind. 17(4), 319–330 (2001)
Mohammadi, S.: Neural network for univariate and multivariate nonlinearity tests. Stat. Anal. Data Min.: ASA Data Sci. J. 13(1), 50–70 (2020)
Reddy, N.S., Krishnaiah, J., Hong, S.G., Lee, J.S.: Modeling medium carbon steels by using artificial neural networks. Mater. Sci. Eng. A 508(1–2), 93–105 (2009)
Shen, C., Wang, C., Wei, X., Li, Y., van der Zwaag, S., Xu, W.: Physical metallurgy-guided machine learning and artificial intelligent design of ultrahigh-strength stainless steel. Acta Materialia 179, 201–214 (2019)
Takechi, H.: Metallurgical aspects on interstitial free sheet steel from industrial viewpoints. ISIJ Int. 34(1), 1–8 (1994)
Tan, M., Le, Q.V.: EfficientNet: rethinking model scaling for convolutional neural networks. In: 36th International Conference on Machine Learning, ICML 2019, June 2019, pp. 10691–10700 (2019)
Xiong, J., Zhang, T.Y., Shi, S.Q.: Machine learning of mechanical properties of steels. Sci. China Technol. Sci. 63(7), 1247–1255 (2020)
Zoph, B., Le, Q.V.: Neural architecture search with reinforcement learning. In: 5th International Conference on Learning Representations, ICLR 2017 - Conference Track Proceedings, pp. 1–16 (2017)
Acknowledgements
The authors are thankful to ArcelorMittal Vega (Sao Francisco do Sul, SC, Brazil) and the FAPESC agency for providing financial support. We gratefully acknowledge the support of NVIDIA Corporation with the donation of the Titan V GPU used for this research.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Sgrott, D.M., Cerqueira, F.M., Miranda, F.J.F., Filho, J.F.S., Parpinelli, R.S. (2021). Modelling IF Steels Using Artificial Neural Networks and Automated Machine Learning. In: Abraham, A., Hanne, T., Castillo, O., Gandhi, N., Nogueira Rios, T., Hong, TP. (eds) Hybrid Intelligent Systems. HIS 2020. Advances in Intelligent Systems and Computing, vol 1375. Springer, Cham. https://doi.org/10.1007/978-3-030-73050-5_64
Download citation
DOI: https://doi.org/10.1007/978-3-030-73050-5_64
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-73049-9
Online ISBN: 978-3-030-73050-5
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)