ANN Modeling of Nickel Base Super Alloys for Time Dependent Deformation

Abstract

Alloys 617 and 276 are nickel-based super alloys with excellent mechanical properties, oxidation, creepresistance, and phase stability at high temperatures. These alloys are used in complex and stochastic applications. Thus, it is difficult to predict their output characteristics mathematically. Therefore, the non-conventional methods for modeling become more effective. These two alloys have been subjected to time-dependent deformation at high temperatures under sustained loading of different values. The creep results have been used to develop the new models. Artificial neural network (ANN) was applied to predict the creep rate and the anelastic elongation for the two alloys. The neural network contains twenty hidden layer with feed forward back propagation hierarchical. The neural network has been designed with MATLAB Neural Network Toolbox. The results show a high correlation between the predicted and the observed results which indicates the validity of the models. 

Machine learning for design, phase transformation and mechanical properties of alloys

“…Effort has been made to also use ML methods to predict time dependent deformation behaviour. References [108][109][110][111][112][113][114][115][116][117] are some examples of ML based publications covering creep. The main input requirements for the ML model were alloy composition, static mechanical properties [114], heat treatment and prior mechanical working parameters, microstructure details such grain size, mechanical loading stress level applied, prior creep strain and temperature.…”

“…The R value for the prediction between predicted and actual was 0.9330. In [109], ANN was used to predict the time dependent deformation of nickel-based superalloys 276 and 617. The inputs used included the alloying content, the loading stress and the operating temperature.…”

BRANN forecast of superalloy tensile strength versus Larson–Miller parameter relation and its approximation by a sigmoidal function

“…Previously, artificial neural networks were already used to analyze nickel‐based alloys, 26,27 but these works dealt with applications in synthesizing new chemical compositions of heat‐resistant alloys, 26,28–31 in modeling the change in the coefficient of thermal expansion, 32,33 in modeling energy hysteresis, 34 in the prediction of low‐cycle fatigue energy, 35 in modeling the development of fatigue cracks, 36 in predicting the occurrence of material defects, 37 and in modeling the time to failure 38 . Moreover, each study was typically limited to a single grade of alloy.…”

Modeling the influence of the composition of refractory elements on the heat resistance of nickel alloys by a deep learning artificial neural network

“…Previously, the ANNs were used to analyze the nickel alloys; however, the major goal of these works was to synthesize new chemical compositions of the alloys 12–16 . There are, also, the ANN applications to model change in the coefficient of thermal expansion, 17,18 to model energy hysteresis, 19 to predict low‐cycle fatigue energy, 20 to model the development of fatigue cracks, 21 to predict the occurrence of material defects, 22 and to model the time to failure 23 . We also engaged the ANN approach to replenish the missing nickel alloys properties 24…”

“…[12][13][14][15][16] There are, also, the ANN applications to model change in the coefficient of thermal expansion, 17,18 to model energy hysteresis, 19 to predict low-cycle fatigue energy, 20 to model the development of fatigue cracks, 21 to predict the occurrence of material defects, 22 and to model the time to failure. 23 We also engaged the ANN approach to replenish the missing nickel alloys properties. 24 This work aims to establish relationships between the refractory elements content and the rupture strength in the nickel alloys employing a specially developed deep learning artificial neural network.…”