Study explores the potential of a deep learning-based approach for predicting the current efficiency of aluminium sacrificial anodes in marine environments. The model takes into account various input variables, including the chemical composition of the sacrificial anode, pH, dissolved oxygen (DO), temperature, pressure, cathode electrode, current density, and the ratio of the surface area of the cathode to anode, with the anode current efficiency serving as the output variable. Utilising artificial neural networks in this study shows a mean absolute percentage error of 6.4% and 7.8% for the training and validation for predicting the current efficiency. The proposed model shows promising potential to predict the current efficiency of aluminium sacrificial anodes and improve the design of cathodic protection systems based on aluminium sacrificial anodes.
MuazuA, YaroSA.J Miner Mater Charact Eng. 2011;10:185–198.
2.
XiaZ, ZhangW, YangX, . Influence of Sn, Cd, and Si addition on the electrochemical performance of Al–Zn–In sacrificial anodes. Mater Corros. 2020;71:585–592. doi:10.1002/maco.201911336
VijayaraniK, DevanMV, NatarajanR.Effects of addition of alkaline earth metal-beryllium on the dissolution behaviour of aluminium-zinc alloy. Port Electrochimica Acta. 2017;35:91–102. doi:10.4152/pea.201702091
5.
HaoQG, WenJB, HeJG, . Effects of gallium addition on the microstructure and electrochemical properties of Al-Zn-Bi series alloy anode. Mater Sci Forum (Trans Tech Publ). 2011;686:107–112.
6.
XiY, JiaM, ZhangJ, . Evaluating the performance of aluminum sacrificial anodes with different concentration of gallium in artificial sea water. Coatings. 2022;12:53. doi:10.3390/coatings12010053
7.
HeJ-G, WenJ-B, LiX-D, . Influence of Ga and Bi on electrochemical performance of Al-Zn-Sn sacrificial anodes. Trans Nonferrous Met Soc China. 2011;21:1580–1586. doi:10.1016/S1003-6326(11)60900-X
8.
MaJ, WenJ.The effects of lanthanum on microstructure and electrochemical properties of Al–Zn–In based sacrificial anode alloys. Corros Sci. 2009;51:2115–2119. doi:10.1016/j.corsci.2009.05.039
9.
KennyED, ParedesRSC, de LacerdaLA, . Artificial neural network corrosion modeling for metals in an equatorial climate. Corros Sci. 2009;51:2266–2278. doi:10.1016/j.corsci.2009.06.004
10.
DudziakT, GajewskiP, ŚnieżyńskiB, . Neural network modelling studies of steam oxidised kinetic behaviour of advanced steels and Ni-based alloys at 800 °C for 3000 h. Corros Sci. 2018;133:94–111. doi:10.1016/j.corsci.2018.01.013
11.
KimH-S, ParkS-J, SeoS-M, . Regression analysis of high-temperature oxidation of Ni-based superalloys using artificial neural network. Corros Sci. 2021;180:109207. doi:10.1016/j.corsci.2020.109207
12.
KamrunnaharM, Urquidi-MacdonaldM.Prediction of corrosion behaviour of alloy 22 using neural network as a data mining tool. Corros Sci. 2011;53:961–967. doi:10.1016/j.corsci.2010.11.028
13.
HuQ, LiuY, ZhangT, . Modeling the corrosion behavior of Ni-Cr-Mo-V high strength steel in the simulated deep sea environments using design of experiment and artificial neural network. J Mater Sci Technol. 2019;35:168–175. doi:10.1016/j.jmst.2018.06.017
14.
OluwoleO, IdusuyiN. (2012).
15.
MurthyYI.Neural Network Models for the Half-Cell Potential of Reinforced Slabs with Magnesium Sacrificial Anodes Subjected to Chloride Ingress. J Soft Comput Civ Eng. 2023;8(1):85–106.
16.
BhattacharyaSK, SaharaR, NarushimaT.Predicting the parabolic rate constants of high-temperature oxidation of Ti alloys using machine learning. Oxid Met. 2020;94:205–218. doi:10.1007/s11085-020-09986-3
17.
ShibliSMA, GireeshVS.Activation of aluminium alloy sacrificial anodes by selenium. Corros Sci. 2005;47:2091–2097. doi:10.1016/j.corsci.2004.09.010
18.
SunH, LiuL, LiY, . The performance of Al–Zn–In–Mg–Ti sacrificial anode in simulated deep water environment. Corros Sci. 2013;77:77–87. doi:10.1016/j.corsci.2013.07.029
19.
LiW, YanY, ChenG, . The effect of temperature and dissolved oxygen concentration on the electrochemical behavior of Al-Zn-inbased anodes. Procedia Eng. 2011;12:27–34. doi:10.1016/j.proeng.2011.05.006
20.
FerdianD, YudhaRD, ArioWM, . Efficiency and characterization study of low voltage current sacrificial anode on Al-Zn-Cu and Al-Zn-Si alloy. IOP Conf. Ser. Mater. Sci. Eng.IOP Publishing; 2019. p. 012047.
21.
FarooqA, HamzaM, AhmedQ, . Evaluating the performance of zinc and aluminum sacrificial anodes in artificial seawater. Electrochim Acta. 2019;314:135–141. doi:10.1016/j.electacta.2019.05.067
22.
KaraminezhaadM, JafariAH, SarrafiA, . Influence of bismuth on electrochemical behavior of sacrificial aluminum anode. Anti-Corros Methods Mater. 2006;53(2):102–109.
23.
MaJ, WenJ, LiX, . Influence of Mg and Ti on the microstructure and electrochemical performance of aluminum alloy sacrificial anodes. Rare Met. 2009;28:187–192. doi:10.1007/s12598-009-0037-z
24.
WangSS, LiangCH, HuangNB.Influence of Si content on the characteristics of Al-Zn-In-Mg-Ti sacrificial anode. Adv Mater Res (Trans Tech Publ). 2014;936:1963–1968.
25.
WenJ, HeJ, LuX.Influence of silicon on the corrosion behaviour of Al–Zn–In–Mg–Ti sacrificial anode. Corros Sci. 2011;53:3861–3865. doi:10.1016/j.corsci.2011.07.039
26.
WorasaenK, MungsantisukP.Influence of Ti on the electrochemical behavior of Al-Zn-In-Si sacrificial anodes. Key Eng Mater (Trans Tech Publ). 2017;728:15–19. doi:10.4028/www.scientific.net/KEM.728.15
27.
SaeriMR, KeyvaniA.Optimization of manganese and magnesium contents in As-cast aluminum-zinc-indium alloy as sacrificial anode. J Mater Sci Technol. 2011;27:785–792. doi:10.1016/S1005-0302(11)60143-6
28.
MuazuA, AliyuYS, AbdulwahabM, . Sacrificial anode stability and polarization potential variation in a ternary Al-xZn-xMg alloy in a seawater-marine environment. J Mar Sci Appl. 2016;15:208–213. doi:10.1007/s11804-016-1356-8
29.
JinglingMA, JiubaW, GengxinLI, . The corrosion behaviour of Al–Zn–In–Mg–Ti alloy in NaCl solution. Corros Sci. 2010;52:534–539. doi:10.1016/j.corsci.2009.10.010
30.
ZhangX, DuC, LiuZ, . The influence of temperature and dissolved oxygen on the electrochemical nature of Al–Zn–In–Ga galvanic anode. Surf Topogr Metrol Prop. 2021;9:035054. doi:10.1088/2051-672X/ac28a6
31.
GuB, SungY.Enhanced reinforcement learning method combining one-hot encoding-based vectors for CNN-based alternative high-level decisions. Appl Sci. 2021;11:1291. doi:10.3390/app11031291
32.
MukherjeeS, ChakrabortyM.A decentralized algorithm for large scale Min-Max problems. 2020 59th IEEE Conf. Decis. Control CDC (2020). p. 2967–2972.
OtchereDA, Arbi GanatTO, GholamiR, . Application of supervised machine learning paradigms in the prediction of petroleum reservoir properties: comparative analysis of ANN and SVM models. J Pet Sci Eng. 2021;200:108182. doi:10.1016/j.petrol.2020.108182
35.
BisginH, BeraT, DingH, . Comparing SVM and ANN based machine learning methods for species identification of food contaminating beetles. Sci Rep. 2018;8:6532. doi:10.1038/s41598-018-24926-7
36.
JhaNK, GhodsiZ, GargS, . Deepreduce: ReLU reduction for fast private inference. Proc. 38th Int. Conf. Mach. Learn. (PMLR, 2021); 2023 Jul 21. p. 4839–4849. https://proceedings.mlr.press/v139/jha21a.html
WangH, DuM, LiangH, . Study on Al-Zn-In alloy as sacrificial anodes in seawater environment. J Ocean Univ China. 2019;18:889–895. doi:10.1007/s11802-019-3788-7
