High-dimensional ultrasonic evaluation method for grain size of nickel-based alloy

Abstract

The invention discloses a high-dimensional ultrasonic evaluation method for the grain size of a nickel-based alloy. The method comprises the following steps of: extracting the grain size and ultrasonic parameters of an alloy test block, carrying out normalization processing on the acquired data, combining high-dimensional multi-characteristic parameters with an HDMR high-dimensional model expression technology, converting a high-dimensional problem caused by a plurality of ultrasonic parameters into a series of low-dimensional problems for summation, establishing an evaluation model of the grain size and the ultrasonic characteristic parameters, adopting Cut-HDMR for solving an HDMR model, solving response functions, determining model parameters by using a support vector machine technology, adding first-order and second-order model response functions linearly, and establishing a high-dimensional ultrasonic evaluation model for the grain size of the nickel-based superalloy. According to the high-dimensional ultrasonic evaluation model constructed by adopting the high-dimensional ultrasonic evaluation method, the ultrasonic characteristic parameter information is comprehensively considered, and the evaluation precision is effectively improved.

Description

technical field [0001] The invention relates to the technical field of alloy grain size measurement, in particular to a high-dimensional ultrasonic evaluation method for nickel-based alloy grain size. Background technique [0002] Due to its low production cost, strong oxidation resistance and corrosion resistance, superalloys are widely used as raw materials for aero-engine casings and industrial gas turbines. During the production process of superalloys, the microstructure is easily affected by high temperature. Grain size is an important parameter to characterize the microstructure of an alloy. To ensure the reliability of the alloy, it is extremely important to detect the grain size at different temperatures and deformations. In the detection process, the grain size detection method often adopts the ultrasonic detection method in the non-destructive testing, which can detect the microstructure of the material. This method has strong penetrating ability and does not need...

AI Technical Summary

Problems solved by technology

In order to further improve the detection accuracy, the current multi-parameter evaluation method calculates the correlation between ultrasonic parameters, realizes the fusion of multiple parameters through the measurement principle, and then constructs the fitting model structure to effectively improve the accuracy. The parameter input ultrasonic detection method has a better application prospect, but this kind of method still faces the problem of a large number of material tissue structure ultrasonic parameter input, the evaluation model dimension increases exponentially, and the model construction is difficult, and the multi-parameter evaluation method will appear multidimensional (dimension disaster) problem

That is to say, it is difficult to build a model to evaluate the grain size of superalloys by using multi-characteristic parameter information.

Images