Prediction of electrochemical properties of La–Y–Ni-based hydrogen storage alloys based on machine learning

IF 8.1 2区工程技术 Q1 CHEMISTRY, PHYSICAL

International Journal of Hydrogen Energy Pub Date : 2024-11-16 DOI:10.1016/j.ijhydene.2024.11.113

Yang Zhang , Yuanyuan Bai , Jin Xu , Rufei Wei

{"title":"Prediction of electrochemical properties of La–Y–Ni-based hydrogen storage alloys based on machine learning","authors":"Yang Zhang , Yuanyuan Bai , Jin Xu , Rufei Wei","doi":"10.1016/j.ijhydene.2024.11.113","DOIUrl":null,"url":null,"abstract":"<div><div>La–Y–Ni-based hydrogen storage alloys, renowned for their high hydrogen capacity and chemical stability, show significant developmental potential. However, their development is heavily reliant on extensive and costly experimental work. This study established regression models to predict three key properties—electrochemical capacity (0.2C), cyclic stability (80%Age), and high-rate discharge performance (1C)—using Random Forest (RF), Extreme Gradient Boosting (XGB), and Ridge regression (Ridge) algorithms. The RF algorithm outperformed the others, with test set R<sup>2</sup> values exceeding 0.8 for all properties. Using SHapley Additive exPlanations (SHAP) for model interpretation, this study quantitatively analyzed the optimal models. Under the constraint of the total mass ratio of elements on the A side and B side being fixed at 100, this study analyzed the optimal Mn + Al intervals for replacing Ni on the B side and the optimal Y and Y + Ce intervals for replacing La on the A side.</div></div>","PeriodicalId":337,"journal":{"name":"International Journal of Hydrogen Energy","volume":"94 ","pages":"Pages 687-696"},"PeriodicalIF":8.1000,"publicationDate":"2024-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Hydrogen Energy","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0360319924047888","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"CHEMISTRY, PHYSICAL","Score":null,"Total":0}

引用次数: 0

Abstract

La–Y–Ni-based hydrogen storage alloys, renowned for their high hydrogen capacity and chemical stability, show significant developmental potential. However, their development is heavily reliant on extensive and costly experimental work. This study established regression models to predict three key properties—electrochemical capacity (0.2C), cyclic stability (80%Age), and high-rate discharge performance (1C)—using Random Forest (RF), Extreme Gradient Boosting (XGB), and Ridge regression (Ridge) algorithms. The RF algorithm outperformed the others, with test set R² values exceeding 0.8 for all properties. Using SHapley Additive exPlanations (SHAP) for model interpretation, this study quantitatively analyzed the optimal models. Under the constraint of the total mass ratio of elements on the A side and B side being fixed at 100, this study analyzed the optimal Mn + Al intervals for replacing Ni on the B side and the optimal Y and Y + Ce intervals for replacing La on the A side.

Abstract Image

查看原文本刊更多论文

基于机器学习的 La-Y-Ni 基储氢合金电化学特性预测

La-Y-Ni 基储氢合金以其高容量氢和化学稳定性而闻名，显示出巨大的发展潜力。然而，它们的开发在很大程度上依赖于大量昂贵的实验工作。本研究利用随机森林（RF）、极端梯度提升（XGB）和岭回归（Ridge）算法建立了回归模型，以预测三种关键性能--电化学容量（0.2C）、循环稳定性（80%Age）和高速放电性能（1C）。RF 算法的性能优于其他算法，所有属性的测试集 R2 值均超过 0.8。本研究使用 SHapley Additive exPlanations（SHAP）进行模型解释，对最优模型进行了定量分析。在 A 侧和 B 侧元素总质量比固定为 100 的约束条件下，本研究分析了在 B 侧替代 Ni 的最佳 Mn + Al 间隔，以及在 A 侧替代 La 的最佳 Y 和 Y + Ce 间隔。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

International Journal of Hydrogen Energy 工程技术-环境科学

CiteScore

13.50

自引率

25.00%

发文量

3502

审稿时长

60 days

期刊介绍： The objective of the International Journal of Hydrogen Energy is to facilitate the exchange of new ideas, technological advancements, and research findings in the field of Hydrogen Energy among scientists and engineers worldwide. This journal showcases original research, both analytical and experimental, covering various aspects of Hydrogen Energy. These include production, storage, transmission, utilization, enabling technologies, environmental impact, economic considerations, and global perspectives on hydrogen and its carriers such as NH3, CH4, alcohols, etc. The utilization aspect encompasses various methods such as thermochemical (combustion), photochemical, electrochemical (fuel cells), and nuclear conversion of hydrogen, hydrogen isotopes, and hydrogen carriers into thermal, mechanical, and electrical energies. The applications of these energies can be found in transportation (including aerospace), industrial, commercial, and residential sectors.