BP network model-based nuclear zirconium-4 alloy corrosion resistance prediction method, electronic equipment and storage medium

Abstract

The invention provides a BP network model-based nuclear zirconium-4 alloy corrosion resistance prediction method. The method comprises the steps of obtaining an original data sample, extracting feature information, constructing a BP network model and verifying the BP network model. The invention relates to electronic equipment and a storage medium, which are used for executing the method. Aiming at the prediction problem of the influence of different alloy components on the corrosion performance of the nuclear zirconium-4 alloy, the BP network model is taken as the center, dimension reductionand denoising processing is carried out on input variables in combination with a principal component analysis technology, feature information is extracted, the prediction precision and generalizationability of a traditional BP network model are effectively improved, a nonlinear mapping relation model of zirconium-4 alloy component content and corrosion performance is constructed, the problems oflong research and development period, low efficiency and cost waste caused by corrosion performance research through a large number of experimental methods at present are solved, and a new technical means is provided for research and development of a novel zirconium alloy.

Description

technical field [0001] The invention relates to the technical field of nuclear-grade zirconium materials, in particular to a method for predicting the corrosion resistance of a nuclear-use zirconium-4 alloy based on a BP network model, electronic equipment, and a storage medium. Background technique [0002] Zirconium-4 alloys have been used as structural materials in pressurized water reactors (PWRS) and boiling water reactors (BWRS) due to their excellent nuclear properties, such as cladding tubes, end plug rods and spacer grids. Corrosion resistance is the most critical of many nuclear properties of zirconium-4 alloy. In actual production, due to the long process chain, there are many factors affecting corrosion performance, such as alloy composition, thermal processing technology, cumulative annealing parameter ΣA value, surface state and corrosion environment, etc. Compared with other factors, the alloy composition as the source (including the type of element and the a...

AI Technical Summary

Problems solved by technology

However, for a long time, due to the high production cost and technical difficulty of nuclear-grade zirconium materials, domestic research work is still in its infancy

Therefore, there is an urgent need for a method of applying BP neural network technology to the prediction of corrosion performance of nuclear-grade zirconium materials to solve the problem of using single-factor control variable method in existing research work, which has a large amount of experiments and high research and development costs, and it is difficult to establish a simple mathematical model. Problems expressing the intrinsic relationship of different alloy compositions

Images