Please wait a minute...
J. Mater. Sci. Technol.  2020, Vol. 49 Issue (0): 202-210    DOI: 10.1016/j.jmst.2020.01.044
Research Article Current Issue | Archive | Adv Search |
An improved deep forest model for forecast the outdoor atmospheric corrosion rate of low-alloy steels
Yuanjie Zhia, Tao Yanga,*(), Dongmei Fua,b,*()
a School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing, 100083, China
b Beijing Engineering Research Center of Industrial Spectrum Imaging, University of Science and Technology Beijing, Beijing 100083, China
Download:  HTML  PDF(1971KB) 
Export:  BibTeX | EndNote (RIS)      
Abstract  

The paper proposes a new deep structure model, called Densely Connected Cascade Forest-Weighted K Nearest Neighbors (DCCF-WKNNs), to implement the corrosion data modelling and corrosion knowledge-mining. Firstly, we collect 409 outdoor atmospheric corrosion samples of low-alloy steels as experiment datasets. Then, we give the proposed methods process, including random forests-K nearest neighbors (RF-WKNNs) and DCCF-WKNNs. Finally, we use the collected datasets to verify the performance of the proposed method. The results show that compared with commonly used and advanced machine-learning algorithms such as artificial neural network (ANN), support vector regression (SVR), random forests (RF), and cascade forests (cForest), the proposed method can obtain the best prediction results. In addition, the method can predict the corrosion rates with variations of any one single environmental variable, like pH, temperature, relative humidity, SO2, rainfall or Cl-. By this way, the threshold of each variable, upon which the corrosion rate may have a large change, can be further obtained.

Key words:  Random forests      Deep forest model      Low-alloy steels      Outdoor atmospheric corrosion      Prediction and data-mining     
Received:  30 June 2019     
Corresponding Authors:  Tao Yang,Dongmei Fu     E-mail:  yangtao@ustb.edu.cn;fdmustb@ustb.edu.cn

Cite this article: 

Yuanjie Zhi, Tao Yang, Dongmei Fu. An improved deep forest model for forecast the outdoor atmospheric corrosion rate of low-alloy steels. J. Mater. Sci. Technol., 2020, 49(0): 202-210.

URL: 

https://www.jmst.org/EN/10.1016/j.jmst.2020.01.044     OR     https://www.jmst.org/EN/Y2020/V49/I0/202

Alloy Element Compositions (wt.%)
Mn S P Si Cr Cu Ni Fe
06CuPCrNiMo 0.40 0.023 0.050 0.17 0 0.17 0 Balance
09CuPCrNiA 0.40 0.023 0.015 0.26 0.10 0.05 0.02 Balance
09CuPTiRe 0.40 0.019 0.080 0.28 0 0.29 0 Balance
09MnNb(s) 1.18 0.024 0.027 0.20 0.10 0.05 0.10 Balance
10CrCuSiV 0.31 0.002 0.010 0.62 0.83 0.25 0.10 Balance
10CrMoAl 0.45 0.002 0.012 0.35 0.98 0.09 0 Balance
14MnMoNbB 1.53 0.010 0.022 0.34 0.10 0.05 0 Balance
15MnMoVN 1.52 0.004 0.026 0.40 0.10 0.05 0 Balance
16Mn 1.40 0.025 0.009 0.36 0.10 0.05 0 Balance
16MnQ 1.37 0.023 0.030 0.30 0.10 0.07 0.05 Balance
D36 1.40 0.018 0.022 0.39 0.05 0.05 0 Balance
JN235(RE) 0.52 0.025 0.030 0.30 0.10 0.07 0 Balance
JN255 0.67 0.006 0.016 0.07 0.02 0.05 0.05 Balance
JN255(RE) 0.39 0.005 0.010 0.62 0.83 0.25 0.10 Balance
JN345 0.39 0.005 0.110 0.05 0.90 0.40 0.65 Balance
JN345(RE) 0.36 0.011 0.089 0.28 0 0.29 0 Balance
JY235(RE) 0.27 0.010 0.089 0.28 0 0.29 0 Balance
Table 1  Element compositions of 17 LAS in collected datasets.
Factors Average Minimum Maximum
Average Relative Humidity, RH (s%) 75.09 56.17 87.71
Average Temperature,T (℃) 17.58 11.08 26.05
Rainfall (mm/month) 159.74 45.64 753.00
SO2 concentration, SO2 (mg/cm3) 0.09 0.02 0.30
pH of rain (pH) 6.14 5.11 6.97
Chloride concentration, Cl- (mg/cm3) 0.22 0 1.97
Table 2  Environmental factors and their statistical values.
Fig. 1.  Corrosion rates of LAS versus exposure time in Beijing.
Fig. 2.  Framework of RF-WKNNs. (a) Example of CART model; (b) Training phase of RF-WKNNs; (c) Testing phase of RF-WKNNs.
Fig. 3.  Framework of proposed DCCF-WKNNs model.
Fig. 4.  Choice of number of layers using MAPE.
Methods Fitting Results (Training samples) Generalization Results (Testing samples)
MAPE (%) RMSE R2 MAPE (%) RMSE R2
ANN 0.28 0.08 1.000 28.16 8.35 0.785
SVR 3.66 3.33 0.960 25.16 7.45 0.823
RF 6.02 2.32 0.980 16.21 5.46 0.908
RF-WKNNs 6.02 2.32 0.980 15.31 5.36 0.911
cForest 0.78 0.43 1.000 15.22 5.09 0.920
DCGF-WKNNs 0.89 0.44 1.000 12.95 4.95 0.924
Table 3  Comparison of different methods for fitting and generalization.
Fig. 5.  Performances of different time periods of 6 methods: (a) RMSE results of 6 methods in sub-datasets with different exposure time; (b) R2 results of 6 methods in sub-datasets with different exposure time; (c) MAPE results of 6 methods in sub-datasets with different exposure time.
Fig. 6.  Prediction corrosion rate curve with changing single environmental variable: Effects of pH thresholds (a), temperature thresholds (b), RH thresholds (c), SO2 thresholds (d), rainfall thresholds (e) and Cl- thresholds (f).
[1] M. Cao, L. Liu, Z. Yu, L. Fan, Y. Li, F. Wang, J. Mater, Sci. Technol. 35 (2019) 651-659.
[2] Z.Y. Liu, X.G. Li, C.W. Du, L. Lu, Y.R. Zhang, Y.F. Cheng, Corros. Sci. 51 (2009) 895-900.
doi: 10.1016/j.corsci.2009.01.007
[3] X.G. Li, D.W. Zhang, Z.Y. Liu, Z. Li, C.W. Du, C.F. Dong, Nature 527 (2015) 441-442.
doi: 10.1038/527441a pmid: 26607528
[4] G. Schmitt, World Corrosion Organization, New York, 2009.
[5] J. Shi, J. Wang, D.D. Macdonald, Corros. Sci. 89 (2014) 69-80.
[6] D. Mareci, G.D. Suditu, R. Chelariu, L.C. Trinc$\check{a}$, S. Curteanu, Mater. Corros. 67 (2016) 1213-1219.
[7] M. Kamrunnahar, M. Urquidi-Macdonald, Corros. Sci. 52 (2010) 669-677.
[8] M. Kamrunnahar, M. Urquidi-Macdonald, Corros. Sci. 53 (2011) 961-967.
doi: 10.1016/j.corsci.2010.11.028
[9] L. Sadowski, M. Nikoo, Neural Comput. Appl. 25 (2014) 1627-1638.
doi: 10.1007/s00521-014-1645-6 pmid: 25395736
[10] X. Xia, J. Nie, C. Davies, W. Tang, S. Xu, N. Birbilis, Mater. Des. 90 (2016) 1034-1043.
[11] A.Z. Shirazi, Z. Mohammadi, Neural Comput. Appl. 28 (2017) 3455-3464.
doi: 10.1007/s00521-016-2251-6
[12] M.J. Jiménez-Come, I. Turias, F.J. Trujillo, Mater. Des. 56 (2014) 642-648.
[13] M.J. Jiménez-Come, I.J. Turias, J.J. Ruiz-Aguilar, F.J. Trujillo, J. Chemometr. 28 (2014) 181-191.
doi: 10.1002/cem.v28.3
[14] M.J. Jiménez-Come, I.J. Turias, J.J. Ruiz-Aguilar, Mater. Corros. 66 (2015) 915-924.
[15] M.J. Jiménez-Come, I.J. Turias, V. Matres, J. Chemometr 31 (2017) e2936.
[16] Y.M. Panchenko, A. Marshakow, Corros. Sci. 109 (2016) 217-229.
[17] E. Possan, J.J.D.O. Andrade, Mater. Res-Ibero-Am. J. 17 (2014) 593-602.
[18] M. Anoop, K.B. Rao, Sadhana-Acad. P. Eng. S. 41 (2016) 887-899.
[19] C.I. Ossai, B. Boswell, I. Davies, Eng. Fail. Anal. 60 (2016) 209-228.
[20] A. Brenna, F. Bolzoni, L. Lazzari, M. Ormellese, Mater. Corros. 69 (2018) 348-357.
[21] Y.N. Shi, D.M. Fu, X.Y. Zhou, T. Yang, Y.J. Zhi, Z.B. Pei, D.W. Zhang, L.Z. Shao, Corros. Sci. 133 (2018) 443-450.
doi: 10.1016/j.corsci.2018.02.005
[22] L. Breiman, Mach. Learn. 45 (2001) 5-32.
doi: 10.1023/A:1010933404324
[23] Z.H. Zhou, Ensemble Methods Foundations and Algorithms, Chapman and Hall/CRC, Boca Raton, 2012.
[24] M. Fernández-Delgado, E. Cernadas, S. Barro, D. Amorim, J. Mach, Learn. Res. 15 (2014) 3133-3181.
[25] R. Genuer, J.M. Poggi, C. Tuleau-Malot, Pattern Recogn. Lett. 31 (2010) 2225-2236.
doi: 10.1016/j.patrec.2010.03.014
[26] E. Oh, R. Liu, A. Nel, K.B. Gemill, M. Bilal, Y. Cohen, I.L. Medintz, Nat. Nanotechnol. 11 (2016) 479-493.
pmid: 26925827
[27] B. Yang, J.M. Cao, D.P. Jiang, J.D. Lv, Multimed. Tools Appl. 77 (2018) 20477-20499.
[28] O. Rahmati, H.R. Pourghasemi, A.M. Melesse, Catena 137 (2016) 360-372.
doi: 10.1016/j.catena.2015.10.010
[29] D. Quintana, Y. Sáez, P. Isasi, Appl. Sci. 7 (2017) 636-651.
doi: 10.3390/app7060636
[30] E. Yuk, S. Park, C.S. Park, J.G. Baek, Appl. Sci. 8 (2018) 932-945.
doi: 10.3390/app8060932
[31] S. Park, J. Im, E. Jang, J. Rhee, Agric. For. Meteorol. 216 (2016) 157-169.
[32] Y. Hou, C. Aldrich, K. Lepkova, L. Machuca, B. Kinsella, Electrochim. Acta 256 (2017) 337-347.
[33] Y. Hou, C. Aldrich, K. Lepkova, B. Kinsella, Electrochim. Acta 274 (2018) 160-169.
doi: 10.1016/j.electacta.2018.04.037
[34] I. Naladala, A. Raju, C. Aishwarya, G.K. Shashidhar, Proceedings of IEEE International Conference on Advances in Computing, Communications and Informatics, Bangalore, India, 2018,September 19-22.
[35] D.E. Brown, J.T. Burns, JOM 70 (2018) 1168-1174.
[36] Y.J. Zhi, D.M. Fu, D.W. Zhang, T. Yang, X.G. Li, Metals 9 (2019) 383.
[37] N. Morizet, N. Godin, J. Tang, E. Maillet, M. Fregonese, B. Mech, Mech. Syst. Signal Proc. 70-71 (2016) 1026-1037.
[38] Z.H. Zhou, J. Feng, Proceeding of the 26th International Joint Conference on Artificial Intelligence, Melbourne, Australia, 2017,August 19-25.
[39] B. Liu, X. Mu, Y. Yang, L. Hao, X. Ding, J. Dong, Z. Zhang, H. Hou, W. Ke, J. Mater, Sci. Technol. 35 (2019) 1228-1239.
[40] F. Mansfeld, Mater. Corros. 30 (1979) 38-42.
[41] M. Morcillo, B. Chico, I. Díaz, H. Cano D. de la Fuente, Corros. Sci. 77 (2013) 6-24.
[42] Z.F. Wang, J.R. Liu, L.X. Wu, R.D. Han, Y.Q. Sun, Corros. Sci. 67 (2013) 1-10.
doi: 10.1016/j.corsci.2012.09.020
[43] Y.B. Hu, C.F. Dong, M. Sun, K. Xiao, P. Zhong, X.G. Li, Corros. Sci. 53 (2011) 4159-4165.
doi: 10.1016/j.corsci.2011.08.024
[44] D. Wicke, T.A. Cochrane A.D. O’Sullivan, S. Cave, M. Derksen, Water Sci. Technol. 69 (2014) 2166-2173.
doi: 10.2166/wst.2014.124 pmid: 24845335
[45] Y.F. Wang, G.X. Cheng, W. Wu, Q. Qiao, Y. Li, X.F. Li, Appl. Surf. Sci. 349 (2015) 746-756.
[46] A.A. Casta˜neda, F. Corvo, D. Fernández, C. Valdés, Eng. J. 21 (2017) 43-62.
doi: 10.4186/ej
[47] S.C. Chung, A.S. Lin, J.R. Chang, H.C. Shih, Corros. Sci. 42 (2000) 1599-1610.
[48] F. Corvo, J. Minotas, J. Delgado, C. Arroyave, Corros. Sci. 47 (2005) 883-892.
doi: 10.1016/j.corsci.2004.06.003
[49] Y.Q. Zhu, J.S. Ou, G. Chen, H.P. Yu, Neural Comput. Appl. 20 (2011) 309-317.
doi: 10.1007/s00521-010-0372-x
[50] Y. Liu, Z.Q. Ge, J. Process. Control 64 (2018) 62-70.
No related articles found!
[1] Chunni Jia, Chengwu Zheng, Dianzhong Li. Cellular automaton modeling of austenite formation from ferrite plus pearlite microstructures during intercritical annealing of a C-Mn steel[J]. J. Mater. Sci. Technol., 2020, 47(0): 1 -9 .
[2] Yanan Pu, Wenwen Dou, Tingyue Gu, Shiya Tang, Xiaomei Han, Shougang Chen. Microbiologically influenced corrosion of Cu by nitrate reducing marine bacterium Pseudomonas aeruginosa[J]. J. Mater. Sci. Technol., 2020, 47(0): 10 -19 .
[3] Wenjing Long, Haining Li, Bing Yang, Nan Huang, Lusheng Liu, Zhigang Gai, Xin Jiang. Research Article Superhydrophobic diamond-coated Si nanowires for application of anti-biofouling’[J]. J. Mater. Sci. Technol., 2020, 48(0): 1 -8 .
[4] Long Chen, Chengtao Yang, Chaoyi Yan. High-performance UV detectors based on 2D CVD bismuth oxybromide single-crystal nanosheets[J]. J. Mater. Sci. Technol., 2020, 48(0): 100 -104 .
[5] Nattakan Kanjana, Wasan Maiaugree, Phitsanu Poolcharuansin, Paveena Laokul. Size controllable synthesis and photocatalytic performance of mesoporous TiO2 hollow spheres[J]. J. Mater. Sci. Technol., 2020, 48(0): 105 -113 .
[6] Bo Yang, Xianghe Peng, Yinbo Zhao, Deqiang Yin, Tao Fu, Cheng Huang. Superior mechanical and thermal properties than diamond: Diamond/lonsdaleite biphasic structure[J]. J. Mater. Sci. Technol., 2020, 48(0): 114 -122 .
[7] Y.Z. Chen, X.Y. Ma, W.X. Zhang, H. Dong, G.B. Shan, Y.B. Cong, C. Li, C.L. Yang, F. Liu. Effects of dealloying and heat treatment parameters on microstructures of nanoporous Pd[J]. J. Mater. Sci. Technol., 2020, 48(0): 123 -129 .
[8] Hui Liu, Rui Liu, Ihsan Ullah, Shuyuan Zhang, Ziqing Sun, Ling Ren, Ke Yang. Rough surface of copper-bearing titanium alloy with multifunctions of osteogenic ability and antibacterial activity[J]. J. Mater. Sci. Technol., 2020, 48(0): 130 -139 .
[9] Jinxiong Hou, Wenwen Song, Liwei Lan, Junwei Qiao. Surface modification of plasma nitriding on AlxCoCrFeNi high-entropy alloys[J]. J. Mater. Sci. Technol., 2020, 48(0): 140 -145 .
[10] H.F. Zhang, H.L. Yan, H. Yu, Z.W. Ji, Q.M. Hu, N. Jia. The effect of Co and Cr substitutions for Ni on mechanical properties and plastic deformation mechanism of FeMnCoCrNi high entropy alloys[J]. J. Mater. Sci. Technol., 2020, 48(0): 146 -155 .
ISSN: 1005-0302
CN: 21-1315/TG
Home
About JMST
Privacy Statement
Terms & Conditions
Editorial Office: Journal of Materials Science & Technology , 72 Wenhua Rd.,
Shenyang 110016, China
Tel: +86-24-83978208
E-mail:JMST@imr.ac.cn

Copyright © 2016 JMST, All Rights Reserved.