Nickel-based polycrystalline superalloy composition design framework based on non-dominated sorting genetic algorithm II

Nickel-based superalloy composition design problem has always been a fundamental task for growing demands in intended applications. In this paper, we establish a nickel-based polycrystalline superalloy composition design framework to excavate novel alloys with superior properties efficiently and comprehensively. First, we establish a model of creep resistance with respect to composition proportions with little data knowledge and computational effort based on the Gaussian process regression. Then, we solve the constrained multi -objective nickel-based superalloy composition design problem, aiming at maximizing the creep resistance while minimizing the alloy cost, by meta-heuristic non-dominated sorting genetic algorithm II efficiently, which enables fast searching rather than simply ranking in large-scale solution space. Pareto fronts containing optimal candidate alloys where the trade-off between creep resistance and alloy cost is fully considered are obtained. Finally, we filter the unqualified candidate alloys that dissatisfy the phase fraction of superalloy on several Pareto fronts based on some screening indicators computed by JMatPro software, and a set of well-performed alloys with high creep resistance and low alloy cost is obtained.

Automated summary

In this paper, a nickel-based polycrystalline superalloy composition design framework is established to efficiently and comprehensively explore novel alloys with superior properties. A model of creep resistance is established using Gaussian process regression, requiring limited data knowledge and computational effort. The constrained multi-objective nickel-based superalloy composition design problem is solved using meta-heuristic non-dominated sorting genetic algorithm II, effectively providing Pareto fronts that consider the trade-off between creep resistance and alloy cost. Well-performed alloys with high creep resistance and low alloy cost are obtained through filtering unqualified candidate alloys using screening indicators computed by JMatPro software.