Advances in aircraft and spacecraft science

Techno-Press (테크노프레스)
권호 표지
DOI QR코드

DOI QR Code

Deep learning in nickel-based superalloys solvus temperature simulation

  • Dmitry A., Tarasov (Department of Information Technology and Automation, Ural Federal University) ;
  • Andrey G., Tyagunov (Department of Information Technology and Automation, Ural Federal University) ;
  • Oleg B., Milder (Department of Information Technology and Automation, Ural Federal University)
  • Received : 2021.11.17
  • Accepted : 2022.06.01
  • Published : 2022.09.25
⟨ Previous Next ⟩

Abstract

Modeling the properties of complex alloys such as nickel superalloys is an extremely challenging scientific and engineering task. The model should take into account a large number of uncorrelated factors, for many of which information may be missing or vague. The individual contribution of one or another chemical element out of a dozen possible ligants cannot be determined by traditional methods. Moreover, there are no general analytical models describing the influence of elements on the characteristics of alloys. Artificial neural networks are one of the few statistical modeling tools that can account for many implicit correlations and establish correspondences that cannot be identified by other more familiar mathematical methods. However, such networks require careful tuning to achieve high performance, which is time-consuming. Data preprocessing can make model training much easier and faster. This article focuses on combining physics-based deep network configuration and input data engineering to simulate the solvus temperature of nickel superalloys. The used deep artificial neural network shows good simulation results. Thus, this method of numerical simulation can be easily applied to such problems.

Keywords

References

  1. Bano, N. and Nganbe, M. (2012), "Neural network approach for modeling the hysteresis energy of Ni based superalloys", Proceedings of the International Conference on Mechanical Engineering and Mechatronics, Ottawa.
  2. Bano, N. and Nganbe, M. (2013), "Modeling of thermal expansion coefficients of Ni based superalloys using Artificial Neural Networks", J. Mater. Eng. Perform., 22(4), 952-957. https://doi.org/10.1007/s11665-012-0398-6
  3. Bano, N., Fahim, A. and Nganbe, M. (2008), "Determination of thermal expansion coefficient of IN738LC with duplex size gamma prime using Neural Network", Proceedings of the Conference of Metallurgists, Winnipeg.
  4. Bano, N., Fahim, A. and Nganbe, M. (2010), "Fatigue crack initiation life prediction of IN738LC using Artificial Neural Network", Proceedings of the AES-ATEMA'2010 Fifth International Conference, Montreal, Quebec, Canada.
  5. Bano, N., Fahim, A. and Nganbe, M. (2010), "Neural network model to predict low cycle fatigue failure energy of Rene77", Proceedings of the AES-ATEMA'2010 Fifth International Conference, Montreal, Quebec, Canada.
  6. Biedermann, T.M., Reich, M., Kameier, F., Adam, M. and Paschereit, C.O. (2019), "Assessment of statistical sampling methods and approximation models applied to aeroacoustic and vibroacoustic problems", Adv. Aircraft Spacecraft Sci., 6(6), 529-550. https://doi.org/10.12989/aas.2019.6.6.529.
  7. Caron, P. (2000). "High y'solvus new generation nickel-based superalloys for single crystal turbine blade applications", Superalloys, 2000, 737-746.
  8. Conduit, B.D., Jones, N.G., Stone, H.J. and Conduit, G.J. (2017), "Design of a nickel-base superalloy using a neural network", Mater. Des., 131, 358-365. https://doi.org/10.1016/j.matdes.2017.06.007.
  9. Das, N. (2010), "Advances in nickel-based cast superalloys", Trans. Ind. Inst. Metal., 63(2-3), 265-274. https://doi.org/10.1007/s12666-010-0036-7.
  10. Detrois, M., Rotella, J., Hardy M., et al. (2017), "Tailoring the properties of a Ni-based superalloy via modification of the forging process: An ICME approach to fatigue performance", Integr. Mater. Manuf. Innov., 6(4), 265-278. https://doi.org/10.1007/s40192-017-0103-6.
  11. Donachie, M.J. and Donachie, S.J. (2002), Superalloys: A Technical Guide, 2nd Edition, ASM Int., USA. Feng, S., Zhou, H. and Dong, H. (2019), "Using deep neural network with small dataset to predict material defects", Mater. Des., 162, 300-310. https://doi.org/10.1016/j.matdes.2018.11.060.
  12. Hasan, M.H., Al Hazza, M. and Mubarak W. (2014), "ANN modeling of nickel base super alloys for time dependent deformation", J. Automat. Control Eng., 2(4), 353-356. https://doi.org/10.12720/joace.2.4.353-356
  13. Haykin, S.O. (2009) Neural Networks and Learning Machines, 3rd Edition, McMaster University, Canada.
  14. Jones, J. and MacKay, D.J.C. (1996), "Neural network modeling of the mechanical properties of Nickel base superalloys", Eds. RD et al., Seven Springs, Pennsylvania, USA.
  15. Kuznetsov, V.P., Lesnikov, V.P. and Popov, N.A. (2004), "Structure and properties single-crystal hightemperature nickel alloy", UrFU. 160. (in Russian)
  16. Nurgayanova, O.S. and Ganeev, A.A. (2007), "Neural network approaches to the design of new hightemperature casting nickel alloys", Neurocomput.: Develop., Appl., 10, 70-74. (in Russian)
  17. Nurgayanova, O.S., Ganeev, A.A. and Pavlinich, S.P. (2006), "Computer-aided design system for casting nickel heat-resistant alloys with a single crystal structure", Polzunovsky Almanac, 3, 22-27. (in Russian)
  18. Olympio, K.R., Blender, F., Holz, M., Kommer, A. and Vetter, R. (2018), "Comparison of mass operator methods considering test uncertainties", Adv. Aircraft Spacecraft Sci., 5(2), 277-294. https://doi.org/10.12989/aas.2018.5.2.277.
  19. Pelleg, J. (2013), Mechanical Properties of Materials, Springer.
  20. Pollock, T.M. and Tin, S. (2006), "Nickel-based superalloys for advanced turbine engines: chemistry, microstructure and properties", J. Propuls. Power, 22(2), 361-374. https://doi.org/10.2514/1.18239.
  21. Reed, R.C. (2006), The Superalloys. Fundamentals and Applications, Cambridge University Press.
  22. Tyagunov, A., Milder, O. and Tarasov, D. (2019a), "Application of Artificial Neural Networks for the replenishment of nickel-based superalloys catalogues", Proceedings 2nd European Conference on Electrical Engineering & Computer Science EECS 2018, IEEE Explore.
  23. Tyagunov, A., Milder, O. and Tarasov, D. (2019b), "Application of Artificial Neural Networks for prediction of nickel-based superalloys service properties based on the chemical composition", WSEAS Trans. Env. Devel., 15, 113-119.
  24. Tyagunov, A., Milder, O. and Tarasov, D. (2019c), "Deep learning in simulation of nickel-based superalloys ultimate tensile strength: Accounting the role of alloying elements", WSEAS Trans. Env. Devel., 15, 340-345.
  25. Yoo, Y.S., Kim, I.S., Kim, D.H., Jo, C.Y., Kim, H.M. and Jones, C.N. (2004), "The application of neural network to the development of single crystal superalloys", Superalloy., 2004, 942-950.
  26. Zhou, Y., Zhang, Z., Zhao, Z. and Zhong, Q. (2012), "Morphological evolution of γ' precipitates in a nickel-based superalloy during various solution treatments", Rare Metal., 31(3), 221-226. https://doi.org/10.1007/s12598-012-0495-6.