{"title":"Intelligent screening model for uranium alloy corrosion substitute alloys based on machine learning","authors":"Wanying Zhang, Xiaoyuan Wang, Yibo Ai, Weidong Zhang","doi":"10.1016/j.pnsc.2025.03.016","DOIUrl":null,"url":null,"abstract":"<div><div>Uranium is a highly important metal material in the nuclear industry. However, uranium is highly susceptible to corrosion in environmental media such as oxygen, hydrogen, or humid air. The corrosion and corrosion protection of uranium materials have always been a focal point for nuclear material researchers. This study aims to investigate the oxidation kinetics of U-2.5NB alloy in order to explore a new type of surrogate alloy that can replace this uranium alloy in terms of oxidation properties. Firstly, the important features of uranium alloy oxidation reactions are determined, and image clustering and image similarity comparison are used to screen the available surrogate alloy database, resulting in the selection of nine alloys with similar properties. Subsequently, an LSTM neural network with PSO optimization is employed to generate surrogate alloys for U-2.5NB alloy by training the chemical element mass fractions of the surrogate alloys, for the evaluation of their oxidation properties. The final results show an 80 % similarity compared to the reference standard, indicating the feasibility of the method used.</div></div>","PeriodicalId":20742,"journal":{"name":"Progress in Natural Science: Materials International","volume":"35 3","pages":"Pages 622-630"},"PeriodicalIF":4.8000,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Progress in Natural Science: Materials International","FirstCategoryId":"88","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1002007125000462","RegionNum":2,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"MATERIALS SCIENCE, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0
Abstract
Uranium is a highly important metal material in the nuclear industry. However, uranium is highly susceptible to corrosion in environmental media such as oxygen, hydrogen, or humid air. The corrosion and corrosion protection of uranium materials have always been a focal point for nuclear material researchers. This study aims to investigate the oxidation kinetics of U-2.5NB alloy in order to explore a new type of surrogate alloy that can replace this uranium alloy in terms of oxidation properties. Firstly, the important features of uranium alloy oxidation reactions are determined, and image clustering and image similarity comparison are used to screen the available surrogate alloy database, resulting in the selection of nine alloys with similar properties. Subsequently, an LSTM neural network with PSO optimization is employed to generate surrogate alloys for U-2.5NB alloy by training the chemical element mass fractions of the surrogate alloys, for the evaluation of their oxidation properties. The final results show an 80 % similarity compared to the reference standard, indicating the feasibility of the method used.
期刊介绍:
Progress in Natural Science: Materials International provides scientists and engineers throughout the world with a central vehicle for the exchange and dissemination of basic theoretical studies and applied research of advanced materials. The emphasis is placed on original research, both analytical and experimental, which is of permanent interest to engineers and scientists, covering all aspects of new materials and technologies, such as, energy and environmental materials; advanced structural materials; advanced transportation materials, functional and electronic materials; nano-scale and amorphous materials; health and biological materials; materials modeling and simulation; materials characterization; and so on. The latest research achievements and innovative papers in basic theoretical studies and applied research of material science will be carefully selected and promptly reported. Thus, the aim of this Journal is to serve the global materials science and technology community with the latest research findings.
As a service to readers, an international bibliography of recent publications in advanced materials is published bimonthly.