Abstract
The surface tension, as a crucial property of molten slags, affects a broad range of high-temperature industrial processes. In this study, we developed a structure–thermodynamics-informed artificial neural network (STIANN) to predict the surface tension of molten slags over a broad range of composition and temperature. First, we constructed a brand-new database that included not only conventional laboratory-based variable information but also quantitative structural and thermodynamic features at different scales, including second-nearest-neighbor bonds, oxygen species, degree of depolymerization (NBO/T), oxide activities, and Gibbs free energies. Then, the four-layer feed-forward backpropagation artificial neural networks were carefully designed to build the surface tension models. Next, three models were built using the different configurations of training features. The analysis results of structural information indicate the high concentration of bridging oxygen generally contributes to the low surface tension when non-bridging oxygen and free oxygen do the opposite. Statistically, the surface tension is positively correlated with the NBO/T of system. The thermodynamic features of \({\Delta }_{\text{mix}}{G}_{\text{m}}^{\text{re}}\) and \({\Delta }_{\text{mix}}{G}_{\text{m}}^{\text{E}}\) vary in the range of 0 to − 70 and 0 to − 55 kJ/mol, respectively, and both decrease first and then increase with the increase in NBO/T. The STIANN model integrated with both structural and thermodynamic information exhibits an unprecedented and excellent predictive performance. The analysis of feature importance confirms the prominent contribution of structural and thermodynamic features to the STIANN model.
Similar content being viewed by others
References
P. Li, M. Zhang, Z. Wang, and S. Seetharaman: J. Eur. Ceram. Soc., 2015, vol. 35, pp. 1307–15.
Z. Zhang, L. Teng, and W. Li: J. Eur. Ceram. Soc., 2007, vol. 27, pp. 319–26.
D. Zhao, Z. Zhang, L. Liu, and X. Wang: Metall. Mater. Trans. B., 2014, vol. 46B, pp. 993–1001.
D. Shi, D. Li, and G. Gao: Metall. Mater. Trans. B., 2008, vol. 39B, pp. 46–55.
H. Liu, H. Lu, D. Chen, H. Wang, H. Xu, and R. Zhang: Ceram. Int., 2009, vol. 35, pp. 3181–84.
X. Miao, Z. Bai, G. Qiu, S. Tang, M. Guo, F. Cheng, and M. Zhang: J. Eur. Ceram. Soc., 2020, vol. 40, pp. 3249–61.
Y. Sun, H. Shen, H. Wang, X. Wang, and Z. Zhang: Energy., 2014, vol. 76, pp. 761–67.
H. Zhang, L. Fu, J. Qi, and W. Xuan: Metall. Mater. Trans. B., 2019, vol. 50B, pp. 1852–61.
Y.N. Starodubtsev and V.S. Tsepelev: Metall. Mater. Trans. B., 2021, vol. 52B, pp. 1886–90.
J. Xin, N. Wang, and M. Chen: ISIJ Int., 2020, vol. 60, pp. 2306–15.
R.E. Boni and G. Derge: JOM., 1956, vol. 8, pp. 53–59.
J.B. Kim, J.K. Choi, I.W. Han, and I. Sohn: J. Non-Cryst. Solids., 2016, vol. 432, pp. 218–26.
T. Tanaka and S. Hara: Steel Res., 2001, vol. 72, pp. 439–45.
J. Xu, D. Chen, W. Weng, M. Sheng, J. Zhang, and F. Lü: J. Cent. South Univ., 2017, vol. 48, pp. 1413–19.
R. Zhang, Z. Wang, Y. Meng, S. Jiao, J. Jia, Y. Min, and C. Liu: Chem. Eng. Sci., 2021, vol. 245, art. no. 116870.
M. Hanao, T. Tanaka, M. Kawamoto, and K. Takatani: ISIJ Int., 2007, vol. 47, pp. 935–39.
M.P. Deosarkar and V.S. Sathe: Powder Technol., 2012, vol. 219, pp. 264–70.
H.R. Ansari, M.J. Zarei, S. Sabbaghi, and P. Keshavarz: Int. Commun. Heat Mass Transfer., 2018, vol. 91, pp. 158–64.
M. Hemmat Esfe, S. Saedodin, N. Sina, M. Afrand, and S. Rostami: Int. Commun. Heat Mass Transfer., 2015, vol. 68, pp. 50–57.
B. Peng, X. Tang, L. Gou, Y. Hu, M. Guo, and M. Zhang: J. Univ. Sci. Technol. Beijing., 2014, vol. 36, pp. 1335–40.
Z. Qiao, L. Yan, Z. Cao, and Y. Xie: J. Alloys Compd., 2001, vol. 325, pp. 180–89.
S.P. Pigarev, L.B. Tsymbulov, E.N. Selivanov, V.M. Chumarev, and S.A. Krasikov: Russ. Metall., 2012, vol. 11, pp. 919–23.
M. Sajid, C. Bai, M. Aamir, Z. You, Z. Yan, and X. Lv: ISIJ Int., 2019, vol. 59, pp. 1153–66.
Y. Min, S. Jiao, R. Zhang, J. Jia, J. Qi, and C. Liu: ISIJ Int., 2021, vol. 61, pp. 1022–28.
G. Kaptay: Langmuir., 2019, vol. 35, pp. 10987–92.
G. Lu, M. He, and Z. Kang: Fluid Phase Equilib., 2016, vol. 427, pp. 345–52.
J. Leitner and D. Sedmidubský: Appl. Surf. Sci., 2020, vol. 525, art. no. 146498.
C. Bermúdez-Salguero and J. Gracia-Fadrique: Fluid Phase Equilib., 2014, vol. 375, pp. 367–72.
A.D. Pelton and P. Chartrand: Metall. Mater. Trans. A., 2001, vol. 32A, pp. 1355–60.
J.D. Olden and D.A. Jackson: Ecol. Model., 2002, vol. 154, pp. 135–50.
J.D. Olden, M.K. Joy, and R.G. Death: Ecol. Model., 2004, vol. 178, pp. 389–97.
C. Wang, K.-C. Chou, and Z.-G. Yu: J. Solution Chem., 2020, vol. 49, pp. 863–74.
T. Matsushita, I. Belov, D. Siafakas, A.E.W. Jarfors, and M. Watanabe: J. Mater. Sci., 2021, vol. 56, pp. 7811–22.
T. Gancarz, Z. Moser, W. Gąsior, J. Pstruś, and H. Henein: Int. J. Thermophys., 2011, vol. 32, pp. 1210–33.
M. Wegener, L. Muhmood, S. Sun, and A.V. Deev: Metall. Mater. Trans. B., 2014, vol. 46B, pp. 316–27.
R. Jiang and L. Zhang: Chem., 2016, vol. 79, pp. 792–97.
German Association of Steel Engineers: Slag Atlas, Metallurgical Industry Press, Beijing, 1989, pp. 301–40.
R. Diao: Acta Metall. Sin., 1995, vol. 31, pp. 247–50.
F. Aoliveira, A. Miller, and J. Madias: Rev. Metal., 1999, vol. 35, pp. 91–99.
J. Xu, J. Zhang, T. Zeng, J. Li, and K. Chou: International Conference on Molten Slags, 2012.
L. Zhang, Z. Li, H. Wang, Z. Liao, and J. Li: J. Anhui Univ. Technol., 2015, vol. 32, pp. 12–15.
Z. Yan, X. Lv, Z. Pang, X. Lv, and C. Bai: Metall. Mater. Trans. B., 2018, vol. 49B, pp. 1322–30.
K. Ogino, T. Suetaki, R. Tsukuda, and A. Adachi: Tetsu to Hagane., 1966, vol. 52, pp. 1427–29.
T. Koshida, T. Ogasawara, and H. Kishidaka: Tetsu to Hagane., 1981, vol. 67, pp. 1491–97.
A. Staronka and M. Piekarska: Arch. Hutn., 1978, vol. 23, pp. 119–23.
Y. Liu, X. Lv, C. Bai, and B. Yu: ISIJ Int., 2014, vol. 54, pp. 2154–61.
J. Xu, J. Zhang, D. Chen, M. Sheng, and W. Weng: J. Cent. South Univ., 2017, vol. 23, pp. 3079–84.
S. Sukenaga, T. Higo, H. Shibata, N. Saito, and K. Nakashima: ISIJ Int., 2015, vol. 55, pp. 1299–304.
T. Tanaka, T. Kitamura, and I.A. Back: ISIJ Int., 1998, vol. 46, pp. 400–06.
I.A. Magidson, A.V. Basov, and N.A. Smirnov: Russ. Metall., 2010, vol. 2009, pp. 631–35.
Z. Chen, H. Wang, Y. Sun, L. Liu, and X. Wang: Metall. Mater. Trans. B., 2019, vol. 50B, pp. 2930–41.
M. Suzuki and E. Jak: ISIJ Int., 2014, vol. 54, pp. 2134–43.
Y. Sun, H. Wang, and Z. Zhang: Metall. Mater. Trans. B., 2018, vol. 49B, pp. 677–87.
Z. Chen, H. Wang, R. Ji, L. Liu, C. Cheeseman, and X. Wang: Ceram. Int., 2019, vol. 45, pp. 15057–64.
Z. Chen, M. Wang, Z. Meng, H. Wang, L. Liu, and X. Wang: Ceram. Int., 2021, vol. 47, pp. 30691–701.
Z. Chen, M. Wang, H. Wang, L. Liu, and X. Wang: Constr. Build. Mater., 2022, vol. 319, art. no. 126010.
Z. Chen, H. Wang, M. Wang, L. Liu, and X. Wang: J. Clean. Prod., 2022, vol. 339, art. no. 130548.
C.B. Shi, X.M. Yang, J.S. Jiao, C. Ll, and H.J. Guo: ISIJ Int., 2010, vol. 50, pp. 1362–72.
Acknowledgments
This research was funded by the National Key Research and Development Plan of China (2018YFC1901503 and 2018YFC1901505), Shanxi Unveiling Bidding Project (20191101007), Ministry of Land and Resources Public Welfare Industry Research Project (201511062-02), and National Natural Science Foundation of China (51672006).
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.
Supplementary Information
Below is the link to the electronic supplementary material.
11663_2022_2479_MOESM1_ESM.pdf
Supplementary file1 The model database containing structural and thermodynamic information are available in Supplementary material. Twenty-three second-nearest-neighbor bonds with great relevance to the surface tension were screened and finally selected, which process is described in detail in Supplementary material. The weight and bias values of the ANN, SIANN, STIANN models are also available in Supplementary material. (PDF 1151 kb)
Rights and permissions
About this article
Cite this article
Chen, Z., Wang, M., Wang, H. et al. Designing Structure–Thermodynamics-Informed Artificial Neural Networks for Surface Tension Prediction of Multi-component Molten Slags. Metall Mater Trans B 53, 2018–2029 (2022). https://doi.org/10.1007/s11663-022-02479-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11663-022-02479-5