Surface Modification of AH36 Steel Using ENi-P-nano TiO₂ Composite Coatings Through ANN-Based Modelling and Prediction

Abstract

This study aims to analyse and forecast the significance of input process parameters to obtain a better ENi-P-TiO₂ coated surface using artificial neural networks (ANN). By varying the four process parameters with the Taguchi L9 design, forty-five numbers of AH36 steel specimens are coated with ENi-P-TiO₂ composites, and their microhardness values are determined. The ANN model was formulated using the input and output data obtained from the 45 specimens. The optimal design was developed based on mean squared error (MSE) and R ² values. The experimentally measured values were compared with their predicted values to determine the ANN model’s predictability. The efficiency of the ANN model is evaluated with an R ² value of 0.959 and an MSE value of 34.563 4. The authors have concluded that the developed model is suitable for designing and predicting ENi-P-TiO₂ composite coatings to avoid extensive experimentation with economic production. Scanning Electron Microscope (SEM) and X-ray diffraction analysis (XRD) are also utilised to compare the base metal and optimal coated surface.

Keywords

AH36 steel / ENi-P-nanoTiO₂ composite coatings / Artificial neural networks / Taguchi DOE / Microhardness / Mean squared error

References

[1] Agarwala RC, Agarwala V. Electroless alloy/composite coatings: A review. Sadhana-Academy Proceedings in Engineering Sciences, 2003, 28: 475-493

[2] Anthoni Sagaya Selvan R, Thakur DG, Seeman M, Muraliraja R, Ansari MI. Modelling and optimisation of ENi-P-TiO₂ coatings synthesised with Zwitterionic surfactant on naval grade AH36 Steel. Sådhanå, 2022, 47(3): 1-13

[3] Beygi H, Vafaeenezhad H, Sajjadi SA. Modeling the electroless nickel deposition on aluminum nanoparticles. Applied Surface Science, 2012, 258: 7744-7750

[4] Bückle H. Progress in micro-indentation hardness testing. Metallurgical Reviews, 1959, 4: 49-100

[5] Duncan RN. The metallurgical structure of electroless nickel deposits: Effect on coating properties. Plating and Surface Finishing, 1996, 83: 65-69

[6] Duren CF (1990) Prediction of the hardness in the HAZ of HSLA steels by means of the carbon equivalent. Hardenability of Steels-Select Conference, Derby, UK, 51–62

[7] Fotovvati B, Namdari N, Dehghanghadikolaei A. On coating techniques for surface protection: A review. Journal of Manufacturing and Materials Processing, 2019, 3(1): 28

[8] Gadhari P, Sahoo P. Electroless nickel-phosphorus composite coatings: A review. International Journal of Manufacturing, Materials, and Mechanical Engineering, 2016, 6: 14-50

[9] Gadhari P, Sahoo P. Improvement in tribological performance of Ni-P-TiO₂ composite coatings using taguchi technique with grey relational analysis. Indian Journal of Materials Science, 2015, 2015: 1-10

[10] Ger MD, Hwang BJ. Effect of surfactants on codeposition of PTFE particles with electroless Ni-P coating. Materials Chemistry and Physics, 2002, 76: 38-45

[11] Gerberich WW, Tymiak NI, Grunlan JC, Horstemeyer MF, Baskes MI. Interpretations of indentation size effects. Journal of Applied Mechanics, Transactions ASME, 2002, 69: 433-442

[12] Golnaraghi S, Zangenehmadar Z, Moselhi O, Alkass S, Vosoughi AR. Application of artificial neural network(s) in predicting formwork labour productivity. Advances in Civil Engineering, 2019, 2019: 5972620

[13] Igi S, Inohara Y, Hirai T. High performance steel plates for shipbuilding-Life cycle cost reduction technology of JFE Steel. JFE Technical Report, 2005, 5: 16-23

[14] Jha A, Chandrasekaran A, Kim C, Ramprasad R. Impact of dataset uncertainties on machine learning model predictions: The example of polymer glass transition temperatures. Modelling and Simulation in Materials Science and Engineering, 2019, 27: 024002

[15] Juneja R, Yumnam G, Satsangi S, Singh AK. Coupling the high-throughput property map to machine learning for predicting lattice thermal conductivity. Chemistry of Materials, 2019, 31: 5145-5151

[16] Lavesson N, Davidsson P. Quantifying the impact of learning algorithm parameter tuning. Proceedings of the National Conference on Artificial Intelligence, 2006, 1: 395-400

[17] Liu Y, Zhao T, Ju W, Shi S. Materials discovery and design using machine learning. Journal of Materiomics, 2017, 3: 159-177

[18] Mallory GO (1990) The electroless nickel plating bath: effect of variables on the process. Electroless Plating: Fundamentals and Applications 57–101.

[19] Mantovani RG, Rossi ALD, Vanschoren J, Bischl B, Carvalho AC-PLF (2015) To tune or not to tune: Recommending when to adjust SVM hyper-parameters via meta-learning. Proceedings of the International Joint Conference on Neural Networks, Killarney, Ireland, 1–8. https://doi.org/10.1109/IJCNN.2015.7280644

[20] Muraliraja R, Elansezhian R. Effect of zwitterionic surfactant on tribological behaviour of electroless plating. Surface Engineering, 2014, 30: 752-757

[21] Muraliraja R, Elansezhian R, Patterson K. Optimization of reducing agent and key parameters effect on the efficiency of electroless Ni-P plating by Taguchi method. Procedia Materials Science, 2014, 5: 2478-2486

[22] Muraliraja R, Elansezhian R, Sudagar J, Raviprakash AV. Influence of a zwitterionic surfactant on the surface properties of electroless Ni-P coating on mild steel. Journal of Surfactants and Detergents, 2016, 19: 1081-1088

[23] Pancrecious JK, Ulaeto SB, Ramya R, Rajan TPD, Pai BC, Pancrecious JK, Ulaeto SB, Ramya R, Rajan TPD. Metallic composite coatings by electroless technique-a critical review. International Materials Reviews, 2018, 63(10): 1-25

[24] Probst P, Boulesteix AL, Bischl B. Tunability: Importance of hyperparameters of machine learning algorithms. Journal of Machine Learning Research, 2019, 20: 1-32

[25] Sahoo P, Das SK. Tribology of electroless nickel coatings — A review. Materials and Design, 2011, 32: 1760-1775

[26] Shozib IA, Ahmad A, Rahaman MSA, Abdul-Rani AM, Alam MA, Beheshti M, Taufiqurrahman I. Modelling and optimization of microhardness of electroless Ni-P-TiO₂ composite coating based on machine learning approaches and RSM. Journal of Materials Research and Technology, 2021, 12: 1010-1025

[27] Srinivasa Pai P, Mathew MT, Stack MM, Rocha LA. Some thoughts on neural network modelling of microabrasion-corrosion processes. Tribology International, 2008, 41: 672-681

[28] Swetlana S, Khatavkar N, Singh AK. Development of Vickers hardness prediction models via microstructural analysis and machine learning. Journal of Materials Science, 2020, 55: 15845-15856

[29] Taheri R. Electroless depostion of nickel. Modern Electroplating, 2003, 1: 262

[30] Vaghefi SYM, Vaghefi SMM. Prediction of phosphorus content of electroless nickel-phosphorous coatings using artificial neural network modeling. Neural Computing and Applications, 2011, 20: 1055-1060

[31] Van Rijn JN, Hutter F (2018) Hyperparameter importance across datasets. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, London, 2367–2376. https://doi.org/10.1145/3219819.3220058

[32] Vander Voort GF, Fowler R. Low-load vickers microindentation hardness testing. Advanced Materials and Processes, 2012, 170: 28-33

[33] Wen C, Zhang Y, Wang C, Xue D, Bai Y, Antonov S, Dai L, Lookman T, Su Y. Machine learning assisted design of high entropy alloys with desired property. Acta Materialia, 2019, 170: 109-117

[34] Wen G, Guo ZX, Davies CKL. Electroless plating for the enhancement of material performance. Materials Technology, 1999, 14: 210-217

[35] Reidel W. Electroless nickel plating, 1991, Metals Park, Ohio: ASM International, 50-55

[36] Yating W, Bin S, Lei L, Wenbin H. Artificial neural network modelling of plating rate and phosphorus content in the coatings of electroless nickel plating. Journal of Materials Processing Technology, 2008, 205: 207-213

[37] Zhang P, Li SX, Zhang ZF. General relationship between strength and hardness. Materials Science and Engineering A, 2011, 529: 62-73

[38] Zhang R, Somasundaran P. Advances in adsorption of surfactants and their mixtures at solid/solution interfaces. Advances in Colloid and Interface Science, 2006, 123–126: 213-229

[39] Zou XF, Hu YJ, Long XB, Huang LY. Prediction and optimization of phosphorus content in electroless plating of Cr12MoV die steel based on PSO-BP model. Surfaces and Interfaces, 2020, 18: 100443