Method for predicting creep life of nickel-based single crystal superalloy containing Re and Ru

Abstract

The invention provides a prediction method for creep life of a nickel-based single-crystal superalloy containing Re and Ru, and relates to the field of nickel-based single-crystal superalloys. According to the method, on the basis of a small data set of nickel-based single crystal superalloy components-creep conditions-creep life, machine learning is utilized, and the creep life of the nickel-based single crystal superalloy is predicted through linkage of two models. According to the method, the prediction precision of machine learning on a small data set is improved by coupling a low-precision model and a high-precision model, and the method has reference significance for some complex machine learning problems with less data volume in the field of material science. Besides, the creep life prediction method can be used for rapidly predicting the creep life of the Re and Ru-containing nickel-based single crystal superalloy within the range of components and creep conditions covered by a data set, and has stronger engineering application significance and better prospects in component design and optimization of the nickel-based single crystal superalloy.

Description

technical field [0001] The invention belongs to the field of nickel-based single-crystal high-temperature alloys, and in particular relates to a method for predicting the creep life of nickel-based single-crystal high-temperature alloys containing Re and Ru. Background technique [0002] Nickel-based single crystal superalloys have excellent high-temperature comprehensive properties and are mainly used in the manufacture of aero-engines and gas turbine hot-end turbine blades. In order to improve the performance, efficiency and reliability of engines, the development of single crystal superalloys is very important. Establishing the quantitative relationship between alloy composition and high-temperature mechanical properties has important guiding significance for the alloy composition design and optimization of nickel-based single crystal superalloys. Creep life is an important index to evaluate the high-temperature mechanical properties of nickel-based single crystal supera...

AI Technical Summary

Problems solved by technology

Machine learning methods have also made some progress in predicting the creep properties of nickel-based superalloys, but generally speaking, research institutes that have long been engaged in the design of nickel-based single crystal superalloys, such as NIMS or large aero-engine company GE, etc. It is realized on the basis of historical data, and nickel-based single crystal superalloy is a material of strategic significance, usually the amount of data that researchers can publicly obtain is limited, so in the face of the problem of less data and complex mechanism, how to Improving the predictive power of machine learning is key

Images