CASIA OpenIR  > 学术期刊  > 自动化学报
基于潜在特征选择性集成建模的二噁英排放浓度软测量
汤健; 乔俊飞; 郭子豪
Source Publication自动化学报
ISSN0254-4156
2022
Volume48Issue:1Pages:223-238
Abstract二噁英(Dioxin,DXN)是导致城市固废焚烧(Municipal solid waste incineration, MSWI)建厂存在“邻避现象”的主要原因之一.工业现场多采用离线化验手段检测DXN浓度,难以满足污染物减排控制的需求.针对上述问题,本文提出了基于潜在特征选择性集成(Selective ensemble, SEN)建模的DXN排放浓度软测量方法.首先,采用主元分析(Principal component analysis, PCA)分别提取依据工艺阶段子系统及全流程系统过程变量的潜在特征,并依据预设贡献率阈值进行特征初选;接着,采用互信息(Mutual information, MI)度量初选特征与DXN间的相关性,并自适应确定再选的上下限及阈值;最后,采用具有超参数自适应选择机制的最小二乘-支持向量机(Least squares—support vector machine,LS-SVM)算法建立多源特征的候选子模型,基于分支定界(Branch and bound, BB)优化和预测误差信息熵加权算法进行集成子模型的优化选择和加权组合,进而得到软测量模型.基于某MSWI焚烧厂DXN检测数据仿真验证了所提方法的有效性.
Keyword城市固废焚烧 二噁英 多源潜在特征 最小二乘-支持向量机 选择性集成建模
DOI10.16383/j.aas.c190254
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/56442
Collection学术期刊_自动化学报
Recommended Citation
GB/T 7714
汤健,乔俊飞,郭子豪. 基于潜在特征选择性集成建模的二噁英排放浓度软测量[J]. 自动化学报,2022,48(1):223-238.
APA 汤健,乔俊飞,&郭子豪.(2022).基于潜在特征选择性集成建模的二噁英排放浓度软测量.自动化学报,48(1),223-238.
MLA 汤健,et al."基于潜在特征选择性集成建模的二噁英排放浓度软测量".自动化学报 48.1(2022):223-238.
Files in This Item: Download All
File Name/Size DocType Version Access License
AAS-CN-2019-0254.pdf(2184KB)期刊论文出版稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[汤健]'s Articles
[乔俊飞]'s Articles
[郭子豪]'s Articles
Baidu academic
Similar articles in Baidu academic
[汤健]'s Articles
[乔俊飞]'s Articles
[郭子豪]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[汤健]'s Articles
[乔俊飞]'s Articles
[郭子豪]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: AAS-CN-2019-0254.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.