集成监督式机器学习用于化学循环制氢和储氢系统的预测评估

IF 5 3区 材料科学 Q2 CHEMISTRY, PHYSICAL
Renge Li, Jimin Zeng, Ying Wei and Zichen Shen
{"title":"集成监督式机器学习用于化学循环制氢和储氢系统的预测评估","authors":"Renge Li, Jimin Zeng, Ying Wei and Zichen Shen","doi":"10.1039/D4SE01255K","DOIUrl":null,"url":null,"abstract":"<p >Chemical looping technology is an emerging method for hydrogen production and storage, characterized by its environmentally friendly and safe inherent gas separation processes. However, the development of this technology requires consideration of oxygen carrier selection, reactor design, and process optimization, trial-and-error experimental methods are labor-intensive and costly. Herein, we propose the integration of machine learning into the chemical looping hydrogen production system to achieve accurate prediction and evaluation during the development process. Based on a dataset of 315 data sets, the ANN and Extra Tree models demonstrated the highest generalization ability among six models, with prediction accuracies for hydrogen yield and purity reaching <em>R</em><small><sup>2</sup></small> = 0.96 and <em>R</em><small><sup>2</sup></small> = 0.94, respectively. The interpretability algorithm analyzed the impact of different input parameters on hydrogen yield and purity, revealing that reaction temperature and fuel gas had the most significant influence. We predicted the hydrogen production performance of four new-input natural oxygen carriers using the trained ANN and Extra Tree models. The results indicated that the predictions were generally consistent with experimental results, with the best oxygen carrier maintaining a hydrogen yield of ∼3.12 mmol g<small><sup>−1</sup></small> and a hydrogen purity of 99.65% after 10 cycles. In summary, machine learning can serve as an alternative to traditional trial-and-error methods, accelerating the development process of chemical looping hydrogen production technology.</p>","PeriodicalId":104,"journal":{"name":"Sustainable Energy & Fuels","volume":" 2","pages":" 640-650"},"PeriodicalIF":5.0000,"publicationDate":"2024-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Integration of supervised machine learning for predictive evaluation of chemical looping hydrogen production and storage system\",\"authors\":\"Renge Li, Jimin Zeng, Ying Wei and Zichen Shen\",\"doi\":\"10.1039/D4SE01255K\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p >Chemical looping technology is an emerging method for hydrogen production and storage, characterized by its environmentally friendly and safe inherent gas separation processes. However, the development of this technology requires consideration of oxygen carrier selection, reactor design, and process optimization, trial-and-error experimental methods are labor-intensive and costly. Herein, we propose the integration of machine learning into the chemical looping hydrogen production system to achieve accurate prediction and evaluation during the development process. Based on a dataset of 315 data sets, the ANN and Extra Tree models demonstrated the highest generalization ability among six models, with prediction accuracies for hydrogen yield and purity reaching <em>R</em><small><sup>2</sup></small> = 0.96 and <em>R</em><small><sup>2</sup></small> = 0.94, respectively. The interpretability algorithm analyzed the impact of different input parameters on hydrogen yield and purity, revealing that reaction temperature and fuel gas had the most significant influence. We predicted the hydrogen production performance of four new-input natural oxygen carriers using the trained ANN and Extra Tree models. The results indicated that the predictions were generally consistent with experimental results, with the best oxygen carrier maintaining a hydrogen yield of ∼3.12 mmol g<small><sup>−1</sup></small> and a hydrogen purity of 99.65% after 10 cycles. In summary, machine learning can serve as an alternative to traditional trial-and-error methods, accelerating the development process of chemical looping hydrogen production technology.</p>\",\"PeriodicalId\":104,\"journal\":{\"name\":\"Sustainable Energy & Fuels\",\"volume\":\" 2\",\"pages\":\" 640-650\"},\"PeriodicalIF\":5.0000,\"publicationDate\":\"2024-12-17\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Sustainable Energy & Fuels\",\"FirstCategoryId\":\"88\",\"ListUrlMain\":\"https://pubs.rsc.org/en/content/articlelanding/2025/se/d4se01255k\",\"RegionNum\":3,\"RegionCategory\":\"材料科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"CHEMISTRY, PHYSICAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Sustainable Energy & Fuels","FirstCategoryId":"88","ListUrlMain":"https://pubs.rsc.org/en/content/articlelanding/2025/se/d4se01255k","RegionNum":3,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"CHEMISTRY, PHYSICAL","Score":null,"Total":0}
引用次数: 0

摘要

化学环技术是一种新兴的制氢和储氢方法,其特点是其固有的气体分离过程环境友好、安全。然而,该技术的发展需要考虑氧载体的选择、反应器的设计和工艺的优化,试验和错误的实验方法是劳动密集型和昂贵的。在此,我们建议将机器学习集成到化学环制氢系统中,以便在开发过程中实现准确的预测和评估。基于315个数据集的数据集,ANN和Extra Tree模型在6个模型中表现出最高的泛化能力,对氢气产率和纯度的预测精度分别达到R2 = 0.96和R2 = 0.94。可解释性算法分析了不同输入参数对氢气产率和纯度的影响,发现反应温度和燃料气体的影响最为显著。我们使用训练好的人工神经网络和Extra Tree模型预测了四种新输入的天然氧载体的产氢性能。结果表明,预测结果与实验结果基本一致,经过10次循环后,最佳氧载体的产氢率保持在~ 3.12 mmol g−1,氢纯度为99.65%。总之,机器学习可以作为传统试错法的替代方法,加速化学环制氢技术的发展进程。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

Integration of supervised machine learning for predictive evaluation of chemical looping hydrogen production and storage system

Integration of supervised machine learning for predictive evaluation of chemical looping hydrogen production and storage system

Chemical looping technology is an emerging method for hydrogen production and storage, characterized by its environmentally friendly and safe inherent gas separation processes. However, the development of this technology requires consideration of oxygen carrier selection, reactor design, and process optimization, trial-and-error experimental methods are labor-intensive and costly. Herein, we propose the integration of machine learning into the chemical looping hydrogen production system to achieve accurate prediction and evaluation during the development process. Based on a dataset of 315 data sets, the ANN and Extra Tree models demonstrated the highest generalization ability among six models, with prediction accuracies for hydrogen yield and purity reaching R2 = 0.96 and R2 = 0.94, respectively. The interpretability algorithm analyzed the impact of different input parameters on hydrogen yield and purity, revealing that reaction temperature and fuel gas had the most significant influence. We predicted the hydrogen production performance of four new-input natural oxygen carriers using the trained ANN and Extra Tree models. The results indicated that the predictions were generally consistent with experimental results, with the best oxygen carrier maintaining a hydrogen yield of ∼3.12 mmol g−1 and a hydrogen purity of 99.65% after 10 cycles. In summary, machine learning can serve as an alternative to traditional trial-and-error methods, accelerating the development process of chemical looping hydrogen production technology.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Sustainable Energy & Fuels
Sustainable Energy & Fuels Energy-Energy Engineering and Power Technology
CiteScore
10.00
自引率
3.60%
发文量
394
期刊介绍: Sustainable Energy & Fuels will publish research that contributes to the development of sustainable energy technologies with a particular emphasis on new and next-generation technologies.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信