Abstract
This work combines metallurgical thermodynamics and kinetics to train a high-accuracy and low-cost deep neural network (DNN) prediction model for hydrogen content in vacuum oxygen decarburization (VOD) process. The mean absolute error of the trained DNN model was 0.0258 ppm, and the R2 and root mean square errors were 0.9973 and 0.0329, respectively. The sensitivity of the model to single-feature and multi-feature coupling is tested, and the current VOD process is optimized through the model. It was found that by increasing the consumption of argon to 100 m3, controlling the initial hydrogen content below 8 ppm, and reducing the vacuum to 70 Pa, the final hydrogen content will be reduced to 0.99 ppm.
Similar content being viewed by others
References
A.H.S. Bueno, E.D. Moreira, and J.A.C.P. Gomes: Eng. Fail. Anal., 2014, vol. 36, pp. 423–31.
Z. Fu, T. Li, M. Shan, G. Gou, Z. Zhu, C. Ma, W. Gao, and Y. Hu: Corros. Sci., 2019, vol. 148, pp. 272–80.
J. Wei and Y. Li: Steel Res. Int., 2015, vol. 86, pp. 189–211.
K. Steneholm, M. Andersson, A. Tilliander, and P.G. Jönsson: Ironmak. Steelmak., 2019, vol. 40, pp. 199–205.
B. Kleimt, S. Köhle, K.P. Johann, A. Jungreithmeier, and J. Molinero: Scand. J. Metall., 2000, vol. 29, pp. 194–205.
S. Guo, J. Yu, X. Liu, C. Wang, and Q. Jiang: Comput. Mater. Sci., 2019, vol. 160, pp. 95–104.
C. Shen, C. Wang, X. Wei, Y. Li, S.V.D. Zwaag, and W. Xu: Acta Mater., 2019, vol. 179, pp. 201–14.
D. Cemernek, S. Cemernek, H. Gursch, A. Pandeshwar, T. Leitner, M. Berger, G. Klösch, and R. Kern: J. Intell. Manuf., 2021, vol. 1, pp. 1–9.
X. Li, C.C. Roth, and D. Mohr: Int. J. Plast, 2019, vol. 118, pp. 320–44.
K. Tsutsui, H. Terasaki, T. Maemura, K. Hayashi, K. Moriguchi, and S. Morito: Comput. Mater. Sci., 2019, vol. 159, pp. 403–11.
G. Zhai, Y. Narazaki, S. Wang, S. Shajihan, and B. Spencer: Smart Struct. Syst., 2022, vol. 29, pp. 237–50.
X. Gao, F. Deng, and X. Yue: Neurocomputing, 2020, vol. 396, pp. 487–94.
W. Chen, Y. Gao, L. Gao, and X. Li: Proc. CIRP, 2018, vol. 72, pp. 1069–72.
C. Shen, X. Wei, C. Wang, and W. Xu: Mater. Charact., 2021, vol. 180, 111392.
A. Kordijazi, S. Behera, D. Patel, P. Rohatgi, and M. Nosonovsky: Langmuir, 2021, vol. 37, pp. 3766–77.
L. Li, B. Xie, Q. Fang, and J. Li: Metall. Mater. Trans. B, 2021, vol. 52, pp. 439–48.
W. Mu, M. Rahaman, F.L. Rios, J. Odqvist, and P. Hedström: Mater. Des., 2021, vol. 197, 109199.
S. Yu and S. Louhenkilpi: Metall. Mater. Trans. B, 2012, vol. 44, pp. 459–68.
A. Teeuwsen: Vak. Forsch Prax., 2014, vol. 26, pp. 32–37.
R. Ding, B. Blanpain, P.T. Jones, and P. Wollants: Metall. Mater. Trans. B, 2000, vol. 31, pp. 197–206.
M. Tan: Special Steel Technol., 2017, vol. 23, pp. 36–38.
F. Karouni, B.P. Wynne, J. Talamantes-Silva, and S. Phillips: ISIJ Int., 2018, vol. 58, pp. 1679–86.
B. Kleimt, S. Köhle, and A. Jungreithmeier: Steel Res., 2001, vol. 72, pp. 337–45.
Y. Xu, Z. Chen, and G. Zhang: Metall. Mater. Trans. B, 2009, vol. 40, pp. 345–52.
M.A. Van Ende, Y.M. Kim, M.K. Cho, J. Choi, and I.H. Jung: Metall. Mater. Trans. B, 2011, vol. 42, pp. 477–89.
M.M. Bejani and M. Ghatee: Artif. Intell. Rev., 2021, vol. 54, pp. 6391–438.
S.A. Rebuffi, S. Gowal, and D.A. Calian: Adv. Neural. Inf. Process. Syst., 2021, vol. 34, pp. 477–89.
C. Shorten, T.M. Khoshgoftaar, and B. Furht: J. Big Data, 2021, vol. 8, pp. 1–34.
H.D. Linh and N.T. Anh: J. Sci. Technol. Inf. Secur., 2021, vol. 2, pp. 55–65.
D.K. Thara, B.G. PremaSudha, and F. Xiong: Patt. Recogn. Lett., 2019, vol. 128, pp. 544–50.
S. Cofre-Martel, E. LopezDroguett, and M. Modarres: Sensors, 2021, vol. 21, p. 6841.
T.S. Gunawan and M. Kartiwi: Indones. J. Electr. Eng. Comput. Sci., 2018, vol. 12, pp. 722–28.
I.M. Kamal, H. Bae, S. Sim, and H. Kim: ICIC Express Lett., 2019, vol. 13, pp. 427–34.
W. Haoxiang and S. Smys: J. Ubiquitous Comput. Commun. Technol., 2021, vol. 3, pp. 10–22.
K. Vijayakumar, V.J. Kadam, and S.K. Sharma: Concurr. Eng., 2021, vol. 29, pp. 275–84.
S.H. Wang, K. Muhammad, J. Hong, A.K. Sangaiah, and Y.D. Zhang: Neural Comput. Appl., 2020, vol. 32, pp. 665–80.
S.S. Lee, S.T. Choi, and S.I. Choi: Sensors, 2019, vol. 19, pp. 1–5.
Y. Li, N. Wang, J. Shi, X. Hou, and J. Liu: Pattern Recogn., 2018, vol. 80, pp. 1–24.
I. Nurhaida, V. Ayumi, D. Fitrianah, R.A.M. Zen, H. Noprisson, and H. Wei: Int. J. Electr. Comput. Eng., 2020, vol. 10, pp. 132–44.
I. Cortes-Ciriano and A. Bender: J. Chem. Inf. Model, 2019, vol. 59, pp. 1–25.
K. Wang, P. Wu, H. Cui, and H. Su: Comput. Electron. Agric., 2021, vol. 187, 106275.
J. Wang and J. Cao: Geophysics, 2021, vol. 86, pp. 185–96.
Q. Zhou, F. Lu, M. Xu, P.C. Peng, S. Liu, S. Shen, R. Zhang, S. Yao, J. Finkelstein, and G.K. Chang: IEEE Photon. Technol. Lett., 2018, vol. 30, pp. 1–4.
B. Zraibi, C. Okar, H. Chaoui, and M. Mansouri: IEEE Trans. Veh. Technol., 2021, vol. 70, pp. 4252–61.
S. Lee, Y. Lee, Y. Lee, M. Kim, S. Shin, J. Park, and K. Min: Int. J. Automot. Technol., 2020, vol. 21, pp. 571–78.
Y. Cui, S. Ma, Z. Yao, X. Chen, Z. Luo, W. Fan, and Y. Hong: Remote Sens., 2020, vol. 12, pp. 1–7.
Acknowledgments
The authors are grateful for the financial support of this work from the National Natural Science Foundation of China (No.51922003, U1810207, and FRF-TP-19-004C1).
Conflict of interest
On behalf of all authors, the corresponding author states that there is no conflict of interest.
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
Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Yang, W., Wang, L., Zhang, W. et al. Deep Neural Network Prediction Model of Hydrogen Content in VOD Process Based on Small Sample Dataset. Metall Mater Trans B 53, 3124–3135 (2022). https://doi.org/10.1007/s11663-022-02592-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11663-022-02592-5