ANN for design and fabrication of ENi-P-nano TiO 2 coatings on AH36 steel
Source abstract
Abstract
Designing optimal ENi-P-nano TiO 2 with higher surface hardness is time-consuming and expensive. Thus, this study is aims to develop the optimal optimiser-based ANN model to forcast Vickers hardness for newer process parametric combinations and find the ideal combination before manufacture. Consequently, three ANN model were devised using ADAM, AdaMax, and RMSprop optimisers with identical data set for training and testing. mean Squared Error (MSE) and R 2 values were used to compare and assess their performance. Rectified Linear Unit (ReLU) is used to provide nonlinearity to the neural network's output since the activation function affects ANN model performance. The study also highlights hyperparameter setting's impact on optimiser performance. The ADAM-based ANN model was determined as optimal design through comparing the predicted and experimental Vickers hardness for the unknown combinations using Taguchi DOE. In addition, FESEM and XRD micrographs confirmed the optimal coating's morphology and phases. This study results shown the compatibility of utilising ANN-based prediction models for ENi-P-nanoTiO 2 coating design and prediction, however future research much incoporates more process parameters and their level ranges.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Metal and Thin Film Mechanics · Machine Learning in Materials Science · Corrosion Behavior and Inhibition
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Mechanical Engineering, DIAT (DU), Pune, India
Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology, Chennai, India
References (29)
Show source-provided references
1. 10.1016/j.surfcoat.2015.01.07110.1016/j.surfcoat.2015.01.071 ↗
2. 10.1016/S0043-1648(02)00118-710.1016/S0043-1648(02)00118-7 ↗
3. 10.1016/j.jmrt.2021.03.06310.1016/j.jmrt.2021.03.063 ↗
4. Anthoni Sagaya Selvan R, Thakur DG, Seeman M Modelling and optimisation of ENi-P-TiO2 coatings synthesised with zwitterionic surfactant on naval grade AH36 steel. Sadhana - Acad Proc Eng Sci. 2022;47:116.
5. 10.1155/2015/10418710.1155/2015/104187 ↗
6. 10.1007/s10853-020-05153-w10.1007/s10853-020-05153-w ↗
7. 10.1016/j.surfcoat.2016.12.08910.1016/j.surfcoat.2016.12.089 ↗
8. 10.1007/s11743-016-1858-z10.1007/s11743-016-1858-z ↗
9. 10.1016/j.msea.2011.08.06110.1016/j.msea.2011.08.061 ↗
10. 10.1115/1.146900410.1115/1.1469004 ↗
11. 10.1038/s41524-018-0081-z10.1038/s41524-018-0081-z ↗
12. 10.1038/s41524-017-0056-510.1038/s41524-017-0056-5 ↗
13. 10.1007/s11804-022-00288-510.1007/s11804-022-00288-5 ↗
14. 10.1186/s42787-019-0043-810.1186/s42787-019-0043-8 ↗
15. 10.1080/02533839.2019.170880410.1080/02533839.2019.1708804 ↗
16. Lavesson N, Davidsson P. Quantifying the impact of learning algorithm parameter tuning. Proc Natl Conf Artif Intell. 2006;1:395–400.
17. Weerts HJP Mueller AC Vanschoren J. Importance of tuning hyperparameters of machine learning algorithms [Internet]. 2020. Available from: http://arxiv.org/abs/2007.07588.
18. Ba JL Kingma DP. Adam: a method for stochastic optimisation. 3rd Int Conf Learn Represent ICLR 2015 - Conf Track Proc. 2015;1–15.
19. Tolstikhin I Bousquet O Schölkopf B An overview of gradient descent optimisation algorithms. Lect Notes Comput Sci (including Subser Lect Notes Artif Intell Lect Notes Bioinformatics) [Internet]. 2018;11046 LNCS:1–9. Available from: https://ruder.io/optimizing-gradient-descent/.
20. Chollet F. Deep learning with Python. 1st ed. USA: Manning Publications Co.; 2017.
21. Gadhari P, Sahoo P. Electroless nickel-phosphorus composite coatings: a review. Int J Manuf Mater Mech Eng. 2016;6:14–50.
22. 10.1016/j.compstruct.2010.04.00810.1016/j.compstruct.2010.04.008 ↗
23. Maleki E, Kashyzadeh KR. Effects of the hardened nickel coating on the fatigue behavior of CK45 steel: experimental, finite element method, and artificial neural network modeling. Iran J Mater Sci Eng. 2017;14:81–99.
24. Ruder S. An overview of gradient descent optimisation algorithms. 2016;1–14. Available from: http://arxiv.org/abs/1609.04747.
25. 10.1007/s11804-016-1385-310.1007/s11804-016-1385-3 ↗
26. 10.1007/s11743-016-1858-z10.1007/s11743-016-1858-z ↗
27. Duncan RN. The metallurgical structure of electroless nickel deposits: effect on coating properties. Plat Surf Finish. 1996;83:65–69.
28. 10.1016/j.mseb.2010.08.00310.1016/j.mseb.2010.08.003 ↗
29. 10.1533/978085709096610.1533/9780857090966 ↗