WSEAS Transactions on Environment and Development
Print ISSN: 1790-5079, E-ISSN: 2224-3496
Volume 15, 2019
Nickel-based Superalloys Heat Resistance BRANN Simulation and Analytical Approximation
Authors: , ,
Abstract: Nickel-based superalloys containing many different chemical elements are systems with complex doping. These materials are widely used for the gas turbine engines parts and other heat-resistant devices manufacturing, which makes them extremely important for the industry. One of the main service property of the superalloys is the heat resistance that is expressed by the value of the ultimate tensile strength (UTS) or creep to rupture (σ). The level of damage required to cause failure is measured after the metal is heated and maintained to a certain temperature for a specific time interval. The heat resistance of alloys with different chemical compositions is often estimated using the complex Larson-Miller parameter (PLM), which combines the temperature and the exposure time. The development of new alloys takes considerable time and is quite expensive. A model describing the dependence of UTS on the alloys composition would be an essential help for the developers. In our work, we have applied a statistical method for modelling the properties of alloys according to their composition. The approach is based on the use of artificial neural networks with preliminary processing of the input data. This allowed us to obtain a series of dependences σ = f(PLM) for a large number of superalloys compositions. The simulation results are in good agreement with the experimental data. Plots of heat resistance vs PLM have a characteristic exponential form for all alloys, however, each composition has its own characteristics reflected in the graph’s slope coefficient, which indicates the thermal stability of an alloy.
Search Articles
Keywords: nickel-based superalloys, artificial neural network, ultimate tensile strength, heat resistance, Larson-Miller
Pages: 288-296
WSEAS Transactions on Environment and Development, ISSN / E-ISSN: 1790-5079 / 2224-3496, Volume 15, 2019, Art. #32