J. Mater. Sci. Technol. ›› 2022, Vol. 128: 31-43.DOI: 10.1016/j.jmst.2022.04.014
• Research Article • Previous Articles Next Articles
Wang Chenchonga, Zhu Kaiyua, Hedström Peterb, Li Yonga, Xu Weia,*()
Received:
2022-01-27
Revised:
2022-03-19
Accepted:
2022-04-04
Published:
2022-11-20
Online:
2022-11-22
Contact:
Xu Wei
About author:
* xuwei@ral.neu.edu.cn (W. Xu)Wang Chenchong, Zhu Kaiyu, Hedström Peter, Li Yong, Xu Wei. A generic and extensible model for the martensite start temperature incorporating thermodynamic data mining and deep learning framework[J]. J. Mater. Sci. Technol., 2022, 128: 31-43.
Empty Cell | Input and Output | Minimum | Maximum | Mean | Standard deviation |
---|---|---|---|---|---|
Input | Carbon (wt.%) | 0.004 | 1.2 | 0.412 | 0.196 |
Manganese (wt.%) | 0 | 10.24 | 0.918 | 0.899 | |
Silicon (wt.%) | 0 | 3.8 | 0.421 | 0.481 | |
Chromium (wt.%) | 0 | 17.98 | 1.310 | 2.488 | |
Nickel (wt.%) | 0 | 21.67 | 0.959 | 1.689 | |
Molybdenum (wt.%) | 0 | 4.69 | 0.308 | 0.474 | |
Vanadium (wt.%) | 0 | 2.1 | 0.062 | 0.214 | |
Cobalt (wt.%) | 0 | 16.08 | 0.144 | 1.251 | |
Aluminum (wt.%) | 0 | 1.58 | 0.016 | 0.128 | |
Tungsten (wt.%) | 0 | 18.38 | 0.171 | 1.292 | |
Copper (wt.%) | 0 | 0.4 | 0.020 | 0.057 | |
Niobium (wt.%) | 0 | 0.11 | 0.0016 | 0.009 | |
Titanium (wt.%) | 0 | 0.14 | 0.00057 | 0.007 | |
Boron (wt.%) | 0 | 0.004 | 0.000033 | 0.0003 | |
Nitrogen (wt.%) | 0 | 0.293 | 0.0034 | 0.0218 | |
Df (J/mol) | 1933 | 5618 | 3884 | 500.3 | |
NRE (J/mol) | −261 | 15.06 | −131.3 | 37.52 | |
Wf (Ms) (J/mol) | 7.84 | 2096 | 814.9 | 485.5 | |
Wf (300 K) (J/mol) | 1259 | 11,275 | 8069 | 1674 | |
Output | Ms (K) | 323 | 708 | 572.8 | 62.87 |
Table 1. Input and output ranges in the hierarchical database.
Empty Cell | Input and Output | Minimum | Maximum | Mean | Standard deviation |
---|---|---|---|---|---|
Input | Carbon (wt.%) | 0.004 | 1.2 | 0.412 | 0.196 |
Manganese (wt.%) | 0 | 10.24 | 0.918 | 0.899 | |
Silicon (wt.%) | 0 | 3.8 | 0.421 | 0.481 | |
Chromium (wt.%) | 0 | 17.98 | 1.310 | 2.488 | |
Nickel (wt.%) | 0 | 21.67 | 0.959 | 1.689 | |
Molybdenum (wt.%) | 0 | 4.69 | 0.308 | 0.474 | |
Vanadium (wt.%) | 0 | 2.1 | 0.062 | 0.214 | |
Cobalt (wt.%) | 0 | 16.08 | 0.144 | 1.251 | |
Aluminum (wt.%) | 0 | 1.58 | 0.016 | 0.128 | |
Tungsten (wt.%) | 0 | 18.38 | 0.171 | 1.292 | |
Copper (wt.%) | 0 | 0.4 | 0.020 | 0.057 | |
Niobium (wt.%) | 0 | 0.11 | 0.0016 | 0.009 | |
Titanium (wt.%) | 0 | 0.14 | 0.00057 | 0.007 | |
Boron (wt.%) | 0 | 0.004 | 0.000033 | 0.0003 | |
Nitrogen (wt.%) | 0 | 0.293 | 0.0034 | 0.0218 | |
Df (J/mol) | 1933 | 5618 | 3884 | 500.3 | |
NRE (J/mol) | −261 | 15.06 | −131.3 | 37.52 | |
Wf (Ms) (J/mol) | 7.84 | 2096 | 814.9 | 485.5 | |
Wf (300 K) (J/mol) | 1259 | 11,275 | 8069 | 1674 | |
Output | Ms (K) | 323 | 708 | 572.8 | 62.87 |
Empty Cell | Input and Output | Minimum | Maximum | Mean | Standard deviation |
---|---|---|---|---|---|
Input | Carbon (wt.%) | 0.0024 | 1.28 | 0.468 | 0.346 |
Manganese (wt.%) | 0 | 30.57 | 6.49 | 10.0 | |
Silicon (wt.%) | 0 | 11.51 | 1.94 | 2.77 | |
Chromium (wt.%) | 0 | 13.4 | 2.66 | 3.50 | |
Nickel (wt.%) | 0 | 5.6 | 0.713 | 1.34 | |
Molybdenum (wt.%) | 0 | 1.07 | 0.142 | 0.236 | |
Vanadium (wt.%) | 0 | 0.42 | 0.013 | 0.056 | |
Cobalt (wt.%) | 0 | 1.6 | 0.101 | 0.359 | |
Aluminum (wt.%) | 0 | 3.03 | 0.063 | 0.393 | |
Tungsten (wt.%) | 0 | 0.99 | 0.015 | 0.123 | |
Copper (wt.%) | 0 | 1.1 | 0.076 | 0.244 | |
Df (J/mol) | −63.48 | 4504 | 2708 | 1375 | |
NRE (J/mol) | −177 | 164 | −43.1 | 103 | |
Wf (J/mol) | −7740 | 10,302 | 3969 | 5220 | |
Output | Ms (K) | 245 | 680 | 460.3 | 121 |
Table 2. Input and output ranges in the validation database.
Empty Cell | Input and Output | Minimum | Maximum | Mean | Standard deviation |
---|---|---|---|---|---|
Input | Carbon (wt.%) | 0.0024 | 1.28 | 0.468 | 0.346 |
Manganese (wt.%) | 0 | 30.57 | 6.49 | 10.0 | |
Silicon (wt.%) | 0 | 11.51 | 1.94 | 2.77 | |
Chromium (wt.%) | 0 | 13.4 | 2.66 | 3.50 | |
Nickel (wt.%) | 0 | 5.6 | 0.713 | 1.34 | |
Molybdenum (wt.%) | 0 | 1.07 | 0.142 | 0.236 | |
Vanadium (wt.%) | 0 | 0.42 | 0.013 | 0.056 | |
Cobalt (wt.%) | 0 | 1.6 | 0.101 | 0.359 | |
Aluminum (wt.%) | 0 | 3.03 | 0.063 | 0.393 | |
Tungsten (wt.%) | 0 | 0.99 | 0.015 | 0.123 | |
Copper (wt.%) | 0 | 1.1 | 0.076 | 0.244 | |
Df (J/mol) | −63.48 | 4504 | 2708 | 1375 | |
NRE (J/mol) | −177 | 164 | −43.1 | 103 | |
Wf (J/mol) | −7740 | 10,302 | 3969 | 5220 | |
Output | Ms (K) | 245 | 680 | 460.3 | 121 |
Parameter | Value | Parameter | Value |
---|---|---|---|
4009 J/mol | 21,216 J/mol | ||
1980 J/mol | 4107 J/mol | ||
1879 J/mol | 3867 J/mol | ||
1868 J/mol | 3923 J/mol | ||
172 J/mol | 345 J/mol | ||
1418 J/mol | 2918 J/mol | ||
1618 J/mol | 3330 J/mol | ||
−352 J/mol | −724 J/mol | ||
280 J/mol | 576 J/mol | ||
714 J/mol | 1469 J/mol | ||
752 J/mol | 1548 J/mol | ||
1653 J/mol | 3402 J/mol | ||
1473 J/mol | 3031 J/mol | ||
3097 J/mol | 16,986 J/mol | ||
928 J/mol | 836 J/mol | ||
0.5 | 2 |
Table 3. Value of the parameters used in the research.
Parameter | Value | Parameter | Value |
---|---|---|---|
4009 J/mol | 21,216 J/mol | ||
1980 J/mol | 4107 J/mol | ||
1879 J/mol | 3867 J/mol | ||
1868 J/mol | 3923 J/mol | ||
172 J/mol | 345 J/mol | ||
1418 J/mol | 2918 J/mol | ||
1618 J/mol | 3330 J/mol | ||
−352 J/mol | −724 J/mol | ||
280 J/mol | 576 J/mol | ||
714 J/mol | 1469 J/mol | ||
752 J/mol | 1548 J/mol | ||
1653 J/mol | 3402 J/mol | ||
1473 J/mol | 3031 J/mol | ||
3097 J/mol | 16,986 J/mol | ||
928 J/mol | 836 J/mol | ||
0.5 | 2 |
Fig. 2. Performance of the SVM models for Wf prediction: (a) the mean results on the training set; (b) the best results on the training set; (c) the mean results on the testing set; (d) the best results on the testing set.
Fig. 3. Distribution of the data in the hierarchical database (n represents the crowding degree): (a) the composition distribution; (b) the composition distribution with a range of 0-5 wt.%; (c) the distribution of the 2nd and 3rd level information.
Fig. 4. Ms prediction results by the DDM-CNN models for the hierarchical database: (a) the mean results on the training set; (b) the mean results on the testing set; (c) the optimal results on the training set; (d) the optimal results on the testing set.
Fig. 6. Comparison of the prediction results by different models on the validation database within the composition range of the original database: (a) the samples in the area of low-alloy steels; (b) the samples in the area of high-alloy steels; (c) the samples beyond the composition range of the original database. (d) Relationship between the MAE and crowding degree of the samples in the validation database.
Fig. 8. (a) Pearson's linear correlation coefficient heat map for different elements. (b) Pearson's linear correlation coefficient of the different models. (c) Comparison of the total error.
[1] |
J.G. Speer, E. De Moor, K.O. Findley, D.K. Matlock, B.C. De Cooman, D.V. Ed- monds, Metall. Mater. Trans. A 42 (2011) 3591-3601.
DOI URL |
[2] |
L. Huang, W. Lin, K. Wang, S. Song, C. Guo, Y. Chen, Y. Li, F. Liu, Acta Mater. 154 (2018) 56-70.
DOI URL |
[3] |
G. Liu, Z. Dai, Z. Yang, C. Zhang, J. Li, H. Chen, J. Mater. Sci. Technol. 49 (2020) 70-80.
DOI URL |
[4] |
R. Ding, Z. Dai, M. Huang, Z. Yang, C. Zhang, H. Chen, Acta Mater. 147 (2018) 59-69.
DOI URL |
[5] | J.S. Wang, M.D. Mulholland, G.B. Olson, D.N. Seidman, Acta Mater. 61 (2013) 4 939-4 952. |
[6] |
Y. Zhang, D. Zhan, X. Qi, Z. Jiang, J. Mater. Sci. Technol. 35 (2019) 1240-1249.
DOI URL |
[7] |
C. Wang, C. Zhang, Z. Yang, J. Su, Y. Weng, Mater. Sci. Eng. A 646 (2015) 1-7.
DOI URL |
[8] | L.A. Carapella, Met. Prog. 46 (1944) 108. |
[9] | P. Payson, C.H. Savage, Trans. ASM 33 (1944) 261-280. |
[10] | A.E. Nehrenberg, Trans. AIME 167 (1946) 4 94-4 98. |
[11] | W. Steven, A.G. Haynes, J. Iron Steel Inst. 183 (1956) 349-359. |
[12] |
E.I. Galindo-Nava, Scr. Mater. 138 (2017) 6-11.
DOI URL |
[13] |
S.J. Lee, K.S. Park, Metall. Mater. Trans. A 44 (2013) 3423-3427.
DOI URL |
[14] |
E.H. Foo, C.H.P. Lupis, Acta Metall. 21 (1973) 1409-1430.
DOI URL |
[15] | R.H. Fowler, E.A. Guggenheim, Statistical Thermodynamics, Cambridge Univer- sity Press, New York, 1939. |
[16] |
D. Hsu, A.D. Keedwell, Pac. J. Math. 117 (1985) 291-312.
DOI URL |
[17] | G. Ghosh, G.B. Olson, Acta Mater. 42 (1994) 3361-3370. |
[18] |
C. Capdevila, F.G. Caballero, C. García De Andrés, Mater. Sci. Technol. 19 (2003) 581-586.
DOI URL |
[19] |
T. Sourmail, C.G. Mateo, Comput. Mater. Sci. 34 (2005) 323-334.
DOI URL |
[20] |
W.G. Vermeulen, P.J. van der Wolk, A.P. de Weijer, S. van der Zwaag, J. Mater. Eng. Perform. 5 (1996) 57-63.
DOI URL |
[21] |
O. Eyercioglu, E. Kanca, M. Pala, E. Ozbay, J. Mater, Process. Technol. 200 (2008) 146-152.
DOI URL |
[22] |
E. Bélisle, Z. Huang, S.L. Digabel, A.E. Gheribi, Comput. Mater. Sci. 98 (2015) 170-177.
DOI URL |
[23] |
Y. Li, D.S. Martín, J. Wang, C. Wang, W. Xu, J. Mater. Sci. Technol. 91 (2021) 200-214.
DOI URL |
[24] |
A. Stormvinter, A. Borgenstam, J. ˚Agren, Metall. Mater. Trans. A 43 (2012) 3870-3879.
DOI URL |
[25] |
Q. Luo, H. Chen, W. Chen, C. Wang, W. Xu, Q. Li, Scr. Mater. 187 (2020) 413-417.
DOI URL |
[26] |
X. Zhang, T. Hickel, J. Rogal, S. Fähler, R. Drautz, J. Neugebauer, Acta Mater. 99 (2015) 281-289.
DOI URL |
[27] |
M.R. Fellinger, L.G. Hector Jr, D.R. Trinkle, Comput. Mater. Sci. 164 (2019) 116-126.
DOI URL |
[28] |
K. Limmer, J.E. Medvedeva, D.C. Van Aken, N. Medvedeva, Comput. Mater. Sci. 99 (2015) 253-255.
DOI URL |
[29] |
K. Nie, M.P. Li, W.P. Wu, Q.P. Sun, Int. J. Solids Struct. 221 (2021) 31-41.
DOI URL |
[30] |
G.B. Olson, Acta Mater. 61 (2013) 771-781.
DOI URL |
[31] |
G.B. Olson, C.J. Kuehmann, Scr. Mater. 70 (2014) 25-30.
DOI URL |
[32] |
S. M.C.V. Bohemen, L. Morsdorf, Acta Mater. 125 (2017) 401-415.
DOI URL |
[33] |
Q. Zeng, C. Yang, D. Tang, J. Li, Z. Feng, J. Liu, K. Guan, J. Mater. Sci. Technol. 35 (2019) 2751-2755.
DOI URL |
[34] |
X.X. Geng, H. Wang, W.H. Xue, S. Xiang, H.L. Huang, L. Meng, G. Ma, Comput. Mater. Sci. 171 (2020) 109235.
DOI URL |
[35] |
C. Capdevila, F.G. Caballero, C.G.D. Andres, ISIJ Int. 42 (2002) 894-902.
DOI URL |
[36] |
Z. Guo, W. Sha, Comput. Mater. Sci. 29 (2004) 12-28.
DOI URL |
[37] |
X. Huang, H. Wang, W. Xue, S. Xiang, H. Huang, L. Meng, G. Ma, A. Ullah, G. Zhang, Comput. Mater. Sci. 171 (2020) 109282.
DOI URL |
[38] |
M. Rahaman, W. Mu, J. Odqvist, P. Hedström, Metall. Mater. Trans. A 50 (2019) 2081-2091.
DOI URL |
[39] |
C. Wang, C. Shen, Q. Cui, C. Zhang, W. Xu, J. Nucl. Mater. 529 (2020) 151823.
DOI URL |
[40] |
Q. Lu, S. Liu, W. Li, X. Jin, Mater. Des. 192 (2020) 108696.
DOI URL |
[41] |
X. Wei, D. Fu, M. Chen, W. Wu, D. Wu, C. Liu, J. Mater. Sci. Technol. 64 (2021) 222-232.
DOI URL |
[42] |
C.G. Shen, C.C. Wang, X.L. Wei, Y. Li, W. Xu, Acta Mater. 179 (2019) 201-214.
DOI URL |
[43] | A. Agrawal, A. Saboo, W. Xiong, G. Olson, A. Choudhary,in:Proceedings to 2019 IEEE International Conference on Data Science and Advanced Analytics (DSAA), Washington, DC, U.S., 2019 October 5-8. |
[44] |
C. Garcia-Mateo, C. Capdevila, F.G. Caballero, C.G. de Andrés, J. Mater. Sci. 42 (2007) 5391-5397.
DOI URL |
[45] | Materials Algorithms Project (MAP),Materials Data Library, Accessed Novem- ber 11, 2020. https://www.phase-trans.msm.cam.ac.uk/map/data/data-index.html#neural. |
[46] | Materials Algorithms Project (MAP), Program Library, MAP_DATA_STEEL_ MS_ 2004, Accessed November 11 2020,. https://www.phase-trans.msm.cam.ac.uk/map/data/materials/Ms_data_2004.html. |
[47] |
C. Wang, C. Shen, X. Huo, C. Zhang, W. Xu, Nucl. Eng. Technol. 52 (2019) 1008-1012.
DOI URL |
[48] | S. Van Bohemen, Mater. Sci. Technol. 28 (2012) 4 87-4 95. |
[49] |
C. Garcia-Mateo, H. K.D.H. Bhadeshia, Mater. Sci. Eng. A 378 (2004) 289-292.
DOI URL |
[50] | Y. Wen, M. Yan, N. Li, Scr. Mater. 50 (2004) 441-444. |
[51] | Z. Wang, J. Zhu, Wear 256 (2004) 66-72. |
[52] |
Y.S. Zhang, X. Lu, X. Tian, Z. Qin, Mater. Sci. Eng. A 334 (2002) 19-27.
DOI URL |
[53] |
C. Garcia-Mateo, F.G. Caballero, H. K.D.H. Bhadeshia, ISIJ Int. 43 (2003) 1821-1825.
DOI URL |
[54] |
F.G. Caballero, H. K.D.H. Bhadeshia, Curr. Opin. Solid State Mater. Sci. 8 (2004) 251-257.
DOI URL |
[55] | G.F.V. Voort,in: Atlas of Time-temperature Diagrams For Irons and Steels, 1st ed., ASM International, 1991, pp. 6-38. |
[56] | J. Orlich, H. Pietrzeniuk, W.V.D. Eisenhüttenleute, M.P.I. Eisenforschung, in: At- las Zur Wärmebehandlung der Stähle, 1st ed., Düsseldorf: Verlag Stahleisen, Germany, 1954, pp. 1-20. |
[57] | U.S.S. Corporation,in: Atlas of Isothermal Transformation Diagrams, 1st ed., Iron and Steel Institute, Pittsburgh, 1953, pp. 33-72. |
[58] | G. Ghosh, G.B. Olson, Metall. Trans. A 7 (1976) 1905-1914. |
[59] | S. Allain, J.P. Chateau, O. Bouaziz, S. Migot, N. Guelton, Mater. Sci. Eng. A 387 (2004) 158-162. |
[60] | P. Volosevich, V. Gridnev, Y. Petrov, Phys. Met. Metallogr. 42 (1976) 126-130. |
[61] |
Y. Sun, H. Bai, M. Li, W. Wang, J. Phys. Chem. Lett. 8 (2017) 3434-3439.
DOI PMID |
[62] | D. Xue, P.V. Balachandran, J. Hogden, J. Theiler, D. Xue, T. Lookman, Nat. Com- mun. 7 (2016) 1-9. |
[63] | K.W. Andrews, J. Iron Steel Inst. 203 (1965) 721-729. |
[64] |
D.V. Doane, J. Heat Treat. 1 (1979) 5-30.
DOI URL |
[65] |
J. Trzaska, Arch. Metall. Mater. 61 (2016) 981-986.
DOI URL |
[66] |
G. Ghosh, G.B. Olson, Acta Metall. 42 (1994) 3371-3379.
DOI URL |
[67] | J. Wang, P.J. van der Wolk, S. van der Zwaag, Mater. Trans. JIM 41 (2000) 769-776. |
[68] |
D. Barbier, Adv. Eng. Mater. 16 (2014) 122-127.
DOI URL |
[69] |
G. Chen, S.N. Srihari, Pattern Recogn. Lett. 140 (2020) 214-221.
DOI URL |
[70] |
T. Masumura, N. Nakada, T. Tsuchiyama, S. Takaki, T. Koyano, K. Adachi, Acta Mater. 84 (2015) 330-338.
DOI URL |
[71] |
M. Izumiyama, M. Tsuchiya, Y. Lmai, J. Jpn. Inst. Met. 34 (1970) 291-295.
DOI URL |
[72] |
X. Wang, W. Xiong, Sci. Technol. Adv. Mater. 21 (2020) 626-634.
DOI URL |
[1] | Chunguang Shen, Chenchong Wang, Minghao Huang, Ning Xu, Sybrandvan der Zwaag, Wei Xu. A generic high-throughput microstructure classification and quantification method for regular SEM images of complex steel microstructures combining EBSD labeling and deep learning [J]. J. Mater. Sci. Technol., 2021, 93(0): 191-204. |
[2] | Ruoxian Wang, Gaowu Qin, Erlin Zhang. Effect of Cu on Martensite Transformation of CoCrMo alloy for biomedical application [J]. J. Mater. Sci. Technol., 2020, 52(0): 127-135. |
[3] | Yingkui GUO, Yu ZHOU, Dongbo LI, Xiaoming DUAN, Tingquan LEI. Microstructure and Performance of 2Y-PSZ/TRIP Steel Composites [J]. J Mater Sci Technol, 2003, 19(02): 137-140. |
[4] | Wenge LIU+;Min ZHU;Dazhi YANG, Dept. of Materials Engineering, Dalian University of Technology, Dalian, 116024, ChinaZhongguang WANG, State Key Laboratory for Fatigue and Fracture of Materials, Institute of Metal Research, Academia Sinica, Shenyang, 11001. First Cycle Effect of Polycrystalline CuZnAl Shape Memory Alloy during Thermal-Mechanical Cycling [J]. J Mater Sci Technol, 1993, 9(2): 101-106. |
[5] | JIAO Chengge;ZHANG Baoqi;WU Gaohui;YAO Zhongkai Harbin Institute of Technology, Harbin, China. Daqing Petroleum College, Anda, China.. The Acoustic Emission Effects of Martensite Transformation in Alloys Cr12MoV and Fe-33Ni-4Ti-10Co [J]. J Mater Sci Technol, 1989, 5(2): 130-134. |
Viewed | ||||||
Full text |
|
|||||
Abstract |
|
|||||