loading page

Modeling the Influence of the Composition of Refractory Elements on the Heat Resistance of Nickel Alloys by a Deep Learning Artificial Neural Network
  • Dmitry TARASOV,
  • Oleg Milder,
  • Andrei Tiagunov
Dmitry TARASOV
Ural Federal University named after the first President of Russia B N Yeltsin

Corresponding Author:datarasov@yandex.ru

Author Profile
Oleg Milder
Ural Federal University named after the first President of Russia B N Yeltsin
Author Profile
Andrei Tiagunov
Ural Federal University named after the first President of Russia B N Yeltsin
Author Profile

Abstract

Nickel alloys are widely used in the production of gas turbine parts. The alloys show resistance to mechanical and chemical degradation under severe long-term stress and high temperatures. One of the major mechanical properties of the alloys is the high-temperature rupture strength, which is measured after a specimen is heated to a certain temperature and held for a certain time considering deformation. Determining the influence of certain elements on the properties of an alloy is a complex scientific and engineering problem that affects the time and cost of developing new materials. Simulation is a great chance to cut costs. In this paper, we predict a high-temperature strength based on the composition of refractory elements in alloys using a deep learning artificial neural network. We build the model based on prior knowledge of the composition of the alloys, information on the role of alloying elements, type of crystallization, test temperature and time, and the tensile strength. Successful simulation results show the applicability of this method in practice.
23 Dec 2020Submitted to Mathematical Methods in the Applied Sciences
24 Dec 2020Submission Checks Completed
24 Dec 2020Assigned to Editor
27 Dec 2020Reviewer(s) Assigned
14 Apr 2021Review(s) Completed, Editorial Evaluation Pending
14 Apr 2021Editorial Decision: Revise Major
26 Apr 20211st Revision Received
26 Apr 2021Submission Checks Completed
26 Apr 2021Assigned to Editor
26 Apr 2021Reviewer(s) Assigned
27 Apr 2021Review(s) Completed, Editorial Evaluation Pending
29 Apr 2021Editorial Decision: Accept
Oct 2022Published in Mathematical Methods in the Applied Sciences volume 45 issue 15 on pages 8809-8818. 10.1002/mma.7524