Application of Gaussian Process regression models for capturing the evolution of microstructure statistics in aging of Nickel-based superalloys

摘要: Abstract Nickel-based superalloys, used extensively in advanced gas turbine engines, exhibit complex microstructures that evolve during exposure to high temperatures (i.e., aging treatments). In this work, we examine critically if the principal component (PC) representation of rotationally invariant 2-point spatial correlations can adequately capture salient features microstructure evolution thermal superalloys. For purpose, an experimental study involving characterization 27 differently aged different combinations temperature and time exposure) samples was designed conducted. Of these, 23 were employed for training a Gaussian Process Regression (GPR) model took as inputs, predicted statistics output. The viability approach described above evaluated by comparing predictions four not GPR model. Furthermore, new strategy developed implemented generate digital corresponding statistics. found be good agreement with experimentally measured one, validating novel framework presented work.