摘要
CO_(2)的捕集与封存(CCS)是一种潜力巨大的减排措施。多孔生物炭含有丰富的多尺度孔隙结构,具有优异的CO_(2)吸附性能。针对传统基于试验数据建立的CO_(2)吸附预测模型存在的精度低、计算复杂等不足,采用梯度提升决策树(GBDT)、极端梯度增强算法(XGB)、轻型梯度增压机算法(LGBM)等机器学习方法对生物炭吸附CO_(2)进行模型预测,并对预测结果进行对比分析。结果表明:影响CO_(2)吸附量的前3个因素依次为生物炭的比表面积、C含量、O含量。3种算法均能有效预测生物炭对CO_(2)的吸附性能。相比之下,LGBM的预测精度最高,达到94%;GBDT在异常样本数据处理方面有显著优势;而XGB对不同测试集变化的预测结果更加稳定。在设计生物炭吸附性能时,不应盲目追求过高的表面积。建议生物炭C含量优先选择83%~88%之间,O含量优先选择15%~18%之间。
CO_(2)capture and sequestration(CCS)is an emission reduction measure with great potential.Porous biochar contains rich multi-scale pore structure,which makes it have excellent CO_(2)adsorption performance.To address the shortcomings of traditional CO_(2)adsorption prediction models built with experimental data,such as low accuracy and complicated calculation,this paper adopts machine learning methods such as gradient boosting decision tree(GBDT),extreme gradient enhancement algorithm(XGB)and light gradient booster algorithm(LGBM)to make model predictions of CO_(2)adsorption by biochar,and conducts comparative analysis of the prediction results.The results showed that the three most important factors affecting CO_(2)adsorption were the specific surface area,C content,and O content of biochar in order.All three algorithms could effectively predict the CO_(2)adsorption performance of biochar.In comparison,LGBM has the highest prediction accuracy of 94%;GBDT has a significant advantage in processing anomalous sample data;and XGB has more stable prediction results for different test set variations.When designing the adsorption performance of biochar,excessive surface area should not be blindly pursued.It is recommended that the selection of biochar C content should preferably be between 83%and 88%,and O content should preferably be between 15%and 18%.
作者
陈一飞
张晓晴
谭康豪
汪俊松
覃英宏
CHEN Yifei;ZHANG Xiaoqing;TAN Kanghao;WANG Junsong;QIN Yinghong(School of Civil Engineering and Architecture,Key Laboratory of Disaster Prevention and Engineering Safety of Guangxi,Guangxi University,Nanning 530004,P.R.China;State Key Laboratory of Subtropical Building Science,South China University of Technology,Guangzhou 510640,P.R.China)
出处
《土木与环境工程学报(中英文)》
北大核心
2025年第3期242-250,共9页
Journal of Civil and Environmental Engineering
基金
广东省省级科技计划项目国际合作专项(2021A0505030008)。
关键词
生物炭
机器学习
二氧化碳吸附
特征重要性
部分依赖图
biochar
machine learning
CO_(2)adsorption
feature importance
partial dependency map
作者简介
陈一飞(1997-),男,主要从事低碳建筑材料研究,E-mail:1993795408@qq.com;通信作者:谭康豪,男,博士,E-mail:haokangtan@163.com。
