Compositional prediction of creep rupture life of single crystal Ni base superalloy by Bayesian neural network

The creep rupture lives of single crystal Ni base superalloys are predicted as a function of alloy composition, creep stress, and creep temperature. A database has been constructed from previous publications and the Rolls-Royce materials database. The Bayesian neural network technique was used for the modelling of creep rupture life. To obtain the posterior distribution and prediction which is of a high dimensional integral form, the Markov chain Monte Carlo method was applied. With a complex 13-31-1 architecture, the neural network shows a precise prediction of creep rupture life of superalloys. Automatic relevance determination reveals that the influences of Re and Cr on creep rupture life of single crystal superalloys are the greatest amongst the alloying elements.