Hardness serves as a crucial indicator for assessing the success of quenching treatment in the steel and iron industry, impacting the processability and wear properties of materials. In the present study, a dataset comprising 125 hardness values of the QT500-7 sample subjected to various austempering heat treatment parameters was utilised to train a neural network model for predicting the hardness of austempered ductile iron (ADI). The established model based on a genetic algorithm and error backpropagation algorithm demonstrates high accuracy in predicting the hardness of ADI if given heat treatment parameters. The mean square error of the model was about 1.019, indicating the reliability and precision of the model in predicting the hardness of ADI based on the specified heat treatment parameters.
HanJMZouQBarberGC, et al.Study of the effects of austempering temperature and time on scuffing behavior of austempered Ni–Mo–Cu ductile iron. Wear2012; 290–291: 99–105.
2.
DuYWangXZhangD, et al.A superior strength and sliding-wear resistance combination of ductile iron with nanobainitic matrix. J Mater Res Technol2021; 11: 1175–1183.
3.
WhiteA. The materials genome initiative: one year on. MRS Bull2012; 37: 715–716.
4.
SmedskjaerMMMauroJCYueY. Prediction of glass hardness using temperature-dependent constraint theory. Phys Rev Lett2010; 105: 115503.
5.
SorsaALeiviskäKSanta-ahoS,et al.Quantitative prediction of residual stress and hardness in case-hardened steel based on the Barkhausen noise measurement. NDT & E Int2012; 46: 100–106.
6.
ChughTChakrabortiNSindhyaK,et al.A data-driven surrogate-assisted evolutionary algorithm applied to a many-objective blast furnace optimization problem. Mater Manuf Process2017; 32: 1172–1178.
7.
RoySSainiBSChakrabartiD,et al.Mechanical properties of micro-alloyed steels studied using a evolutionary deep neural network. Mater Manuf Processes2020; 35: 611–624.
8.
BishopCM. Neural networks and their applications. Rev Sci Instrum1994; 65: 1803–1832.
PaliwalMKumarUA. Neural networks and statistical techniques: a review of applications. Expert Syst Appl2009; 36: 2–17.
11.
SadeghiB. A BP-neural network predictor model for plastic injection molding process. J Mater Process Technol2000; 103: 411–416.
12.
WuZLiuZLiL,et al.Experimental and neural networks analysis on elevated-temperature mechanical properties of structural steels. Mater Today Commun2022; 32: 104092.
13.
YanYBaoJLeiY.Tribological properties prediction of brake lining for automobiles based on BP neural network. In: Chinese control & decision conference, Xuzhou, 2010, pp.2678–2682.
14.
LiQYuJ-YMuB-C,et al.BP Neural network prediction of the mechanical properties of porous NiTi shape memory alloy prepared by thermal explosion reaction. Mater Sci Eng A2006; 419: 214–217.
15.
YescasMABhadeshiaHMackayDJ. Estimation of the amount of retained austenite in austempered ductile irons using neural networks. Mater Sci Eng A2001; 311: 162–173.
16.
YescasMA. Prediction of the vickers hardness in austempered ductile irons using neural networks. Int J Cast Met Res2016; 15: 513–521.
17.
AwrynowiczZDymskiSTrepczyńska-entM,et al.A 20/3 neural network analysis of tensile strength of austempered ductile iron. Arch Foundry Eng2007; 7: 99–104.
18.
PourAsiabiHPourAsiabiHAmirZadehZ,et al.Development a multi-layer perceptron artificial neural network model to estimate the Vickers hardness of Mn–Ni–Cu–Mo austempered ductile iron. Mater Des2012; 35: 782–789.
19.
LanQWangXSunJ, et al.Artificial neural network approach for mechanical properties prediction of as-cast A380 aluminum alloy. Mater Today Commun2022; 31: 103301.
20.
OjhaVKAbrahamASnášelV. Metaheuristic design of feedforward neural networks: a review of two decades of research. Eng Appl Artif Intell2017; 60: 97–116.
21.
DingSSuCYuJ. An optimizing BP neural network algorithm based on genetic algorithm. Artif Intell Rev2011; 36: 153–162.
22.
IgweKPillayN.Automatic programming using genetic programming. In: 2013 third world congress on information and communication technologies (WICT 2013), Hanoi, Vietnam, 2013, pp.337–342. IEEE.
SmithMGBullLJGP. Genetic programming with a genetic algorithm for feature construction and selection. Genet Program Evolvable Mach2005; 6: 265–281.
25.
CookDFRagsdaleCTMajorR. Combining a neural network with a genetic algorithm for process parameter optimization. Eng Appl Artif Intell2000; 13: 391–396.
YanGXuYJiangB. The production of high-density hollow cast-iron bars by vertically continuous casting. J Mater Process Technol2012; 212: 15–18.
28.
GenelK. Application of artificial neural network for predicting strain-life fatigue properties of steels on the basis of tensile tests. Int J Fatigue2004; 26: 1027–1035.
29.
GhaisariJJannesariHVataniM. Artificial neural network predictors for mechanical properties of cold rolling products. Adv Eng Softw2012; 45: 91–99.
30.
DattJBatraU. Influence of composition and austempering temperature on machinability of austempered ductile iron. Mater Sci Eng, A2013; 7: 132–137.
31.
UyarASahinONalcaciB,et al.Effect of austempering times on the microstructures and mechanical properties of dual-matrix structure austempered ductile iron (DMS-ADI), int. J Met2021; 16: 407–418.
32.
CakirMCBayramAIsikY,et al.The effects of austempering temperature and time onto the machinability of austempered ductile iron. Mater Sci Eng, A2005; 407: 147–153.
33.
OhdarRPashaS. Prediction of the process parameters of metal powder preform forging using artificial neural network (ANN). J Mater Process Technol2003; 132: 227–234.
34.
GuoX. Correlation between austempering parameters and hardness of austempered ductile iron based on artificial neural network. Comp Model Tech2014; 18: 72–76.
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
