Multi-objective optimization of structural parameters of SCR system under Eley-Rideal reaction mechanism based on machine learning coupled with response surface methodology

IF 7.2 2区工程技术 Q1 CHEMISTRY, APPLIED

Fuel Processing Technology Pub Date : 2024-10-14 DOI:10.1016/j.fuproc.2024.108141

{"title":"Multi-objective optimization of structural parameters of SCR system under Eley-Rideal reaction mechanism based on machine learning coupled with response surface methodology","authors":"","doi":"10.1016/j.fuproc.2024.108141","DOIUrl":null,"url":null,"abstract":"<div><div>Selective catalytic reduction (SCR) is an important method to control nitrogen oxides (NO<sub>x</sub>) emissions from diesel engines. Excellent SCR structural parameters are the key to effectively reduce NO<sub>x</sub> and back pressure. The dynamic reaction processes of NO<sub>x</sub> standard reaction, fast reaction and NO<sub>2</sub>-SCR reaction are deeply explored by establishing the Eley-Rideal model. The results show that the wall thickness and washcoat thickness of the SCR are the main determinants of the catalyst performance, while the CPSI has a great influence on the pressure drop. In addition, regression prediction analysis of experimental data by random forest (RF), particle swarm optimized backpropagation artificial neural network (PSOBP-ANN) and response surface methodology (RSM) was performed to explore the coupling relation functions of structural parameters, and optimal test results were solved and verified. The denitrification efficiency of the structure-optimized SCR system increased by 22 % and the pressure drop decreased by 23 %.</div></div>","PeriodicalId":326,"journal":{"name":"Fuel Processing Technology","volume":null,"pages":null},"PeriodicalIF":7.2000,"publicationDate":"2024-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Fuel Processing Technology","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0378382024001115","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"CHEMISTRY, APPLIED","Score":null,"Total":0}

引用次数: 0

Abstract

Selective catalytic reduction (SCR) is an important method to control nitrogen oxides (NO_x) emissions from diesel engines. Excellent SCR structural parameters are the key to effectively reduce NO_x and back pressure. The dynamic reaction processes of NO_x standard reaction, fast reaction and NO₂-SCR reaction are deeply explored by establishing the Eley-Rideal model. The results show that the wall thickness and washcoat thickness of the SCR are the main determinants of the catalyst performance, while the CPSI has a great influence on the pressure drop. In addition, regression prediction analysis of experimental data by random forest (RF), particle swarm optimized backpropagation artificial neural network (PSOBP-ANN) and response surface methodology (RSM) was performed to explore the coupling relation functions of structural parameters, and optimal test results were solved and verified. The denitrification efficiency of the structure-optimized SCR system increased by 22 % and the pressure drop decreased by 23 %.

查看原文本刊更多论文

基于机器学习和响应面方法的 Eley-Rideal 反应机理下 SCR 系统结构参数的多目标优化

选择性催化还原（SCR）是控制柴油发动机氮氧化物（NOx）排放的重要方法。优异的 SCR 结构参数是有效降低氮氧化物和背压的关键。通过建立 Eley-Rideal 模型，深入探讨了氮氧化物标准反应、快速反应和 NO2-SCR 反应的动态反应过程。结果表明，SCR 的壁厚和水洗层厚度是决定催化剂性能的主要因素，而 CPSI 则对压降有很大影响。此外，通过随机森林（RF）、粒子群优化反向传播人工神经网络（PSOBP-ANN）和响应面方法（RSM）对实验数据进行回归预测分析，探索结构参数的耦合关系函数，求解并验证了最优试验结果。结构优化后的 SCR 系统脱硝效率提高了 22%，压降降低了 23%。

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

Fuel Processing Technology 工程技术-工程：化工

CiteScore

13.20

自引率

9.30%

发文量

398

审稿时长

26 days

期刊介绍： Fuel Processing Technology (FPT) deals with the scientific and technological aspects of converting fossil and renewable resources to clean fuels, value-added chemicals, fuel-related advanced carbon materials and by-products. In addition to the traditional non-nuclear fossil fuels, biomass and wastes, papers on the integration of renewables such as solar and wind energy and energy storage into the fuel processing processes, as well as papers on the production and conversion of non-carbon-containing fuels such as hydrogen and ammonia, are also welcome. While chemical conversion is emphasized, papers on advanced physical conversion processes are also considered for publication in FPT. Papers on the fundamental aspects of fuel structure and properties will also be considered.