–
The prospects of implementation of artificial intelligence for modelling of microstructural parameters in metal forming processes
TRETYAKOV Denis, BYLYA Olga, SHITIKOV Andrei, GARTVIG Artur, STEBUNOV Sergey, BIBA Nikolay
download PDFAbstract. The primary trend in modern metal forming can be characterised by the increase in the complexity of the technological processes and higher demand for the quality of the products. This naturally raises the requirements for the quality of modelling prediction of various aspects of metal forming process, such as tool wear, metal flow, fracture and defects formation, microstructure evolution and mechanical properties. However, various independent benchmarking studies [1] have shown that modelling predictions can be wrong even for well-calibrated models, and all the efforts with more detailed and metrologically better experiments didn’t lead to any significant leap in the prediction quality. As an attempt to implement some alternative approach, this paper investigates the applicability of an Artificial Intelligence (AI) approach, in particular Deep Learning models. The example of a recurrent neural network model predicting recrystallisation during hot forging of Inconel 718 is presented. The model considers the entire thermo-mechanical history at every point and is trained and blind-tested using actual experimental data.
Keywords
Metals, Forging, Inconel 718, Microstructure Evolution, Recrystallisation, FEM, Deep Learning, AI Models
Published online 4/24/2024, 10 pages
Copyright © 2024 by the author(s)
Published under license by Materials Research Forum LLC., Millersville PA, USA
Citation: TRETYAKOV Denis, BYLYA Olga, SHITIKOV Andrei, GARTVIG Artur, STEBUNOV Sergey, BIBA Nikolay, The prospects of implementation of artificial intelligence for modelling of microstructural parameters in metal forming processes, Materials Research Proceedings, Vol. 41, pp 2164-2173, 2024
DOI: https://doi.org/10.21741/9781644903131-238
The article was published as article 238 of the book Material Forming
Content from this work may be used under the terms of the Creative Commons Attribution 3.0 license. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.
References
[1] Reshetov, A. and Bylya, O., 2023, April. Benchmarking mean-field models available in commercial FE software in application to two-blow forging of IN718 alloy. Materials Research Forum LLC. https://doi.org/10.21741/9781644902479-74
[2] Bylya, O., Reshetov, A., Stefani, N., Rosochowska, M. and Blackwell, P., 2017. Applicability of JMAK-type model for predicting microstructural evolution in nickel-based superalloys. Procedia engineering, 207, pp.1105-1110. https://doi.org/10.1016/j.proeng.2017.10.1067
[3] Guimaraes, A.A. and Jonas, J.J., 1981. Recrystallization and aging effects associated with the high temperature deformation of Waspaloy and Inconel 718. Metallurgical Transactions A, 12, pp.1655-1666. https://doi.org/10.1007/BF02643571
[4] Sui, F.L., Xu, L.X., Chen, L.Q. and Liu, X.H., 2011. Processing map for hot working of Inconel 718 alloy. Journal of Materials Processing Technology, 211(3), pp.433-440. https://doi.org/10.1016/j.jmatprotec.2010.10.015
[5] Nicolaÿ, A., Fiorucci, G., Franchet, J.M., Cormier, J. and Bozzolo, N., 2019. Influence of strain rate on subsolvus dynamic and post-dynamic recrystallization kinetics of Inconel 718. Acta Materialia, 174, pp.406-417. https://doi.org/10.1016/j.actamat.2019.05.061
[6] Cybenko, G., 1989. Approximation by superpositions of a sigmoidal function. Math. Control. Signals, Syst. 2, 303–314. https://doi.org/10.1007/BF02551274
[7] Reshetov, A., Stefani, N., Bylya, O., Krishnamurthy, B. and Blackwell, P., 2020. Aspects of high strain rate industrial forging of Inconel 718. In Superalloys 2020: Proceedings of the 14th International Symposium on Superalloys (pp. 461-470). Springer International Publishing. https://doi.org/10.1007/978-3-030-51834-9_45
[8] Stefani, N., 2020. Novel experimental methodology for the investigation of recrystallisation during industrial hot forging of Inconel 718, Engineering Doctoral Thesis, pp243
[9] Gers, F., 2001. Long short-term memory in recurrent neural networks, Doctoral dissertation,.
[10] Huang, D., Wu, W.T., Lambert, D. and Semiatin, S.L., 2001. Computer simulation of microstructure evolution during hot forging of Waspaloy and nickel alloy 718. Minerals, Metals and Materials Society/AIME, Microstructure Modeling and Prediction During Thermomechanical Processing(USA), pp.137-146.
[11] Micas Simulation LTD, “QForm UK version 11, The software documentation: Description of Microstructure evolution model”, 2023.
[12] “DEFORMTM V11.0.1 System Documentation (Reed Road Columbus, Ohio: Scientific Forming Technologies Corporation).” pp. 175–180, 2014.
[13] Meriem Zouari, Roland E, Logé, Nathalie Bozzolo In Situ Characterization of Inconel 718 Post-Dynamic Recrystallization within a Scanning Electron Microscope, Metals 2017, 7, 476. https://doi.org/10.3390/met7110476
