Other (Scientific journals)
Comparison of supervised learning techniques for atmospheric pollutant monitoring in a Kraft pulp mill
Sainlez, Matthieu; Heyen, Georges
2012In Journal of Computational and Applied Mathematics
Peer Reviewed verified by ORBi
 

Files


Full Text
JCAM-review-SAINLEZ.pdf
Author preprint (2.2 MB)
Preprint submitted to JCAM (status: in revision)
Request a copy

All documents in ORBi are protected by a user license.

Send to



Details



Abstract :
[en] In this paper, supervised learning techniques are compared to predict nitro- gen oxide (NOx) pollutant emission from the recovery boiler of a Kraft pulp mill. Starting from a large database of raw process data related to a Kraft recovery boiler, we consider a regression problem in which we are trying to predict the value of a continuous variable. Generalization is done on the worst case configuration possible to make sure the model is adequate: the training period concerns stationary operations while test periods mainly fo- cus on NOx emissions during transient operations. This comparison involves neural network techniques (i.e., multilayer perceptron and NARX network), tree-based methods and multiple linear regression. We illustrate the potential of a dynamic neural approach compared to the others in this task.
Disciplines :
Engineering, computing & technology: Multidisciplinary, general & others
Author, co-author :
Sainlez, Matthieu ;  Université de Liège - ULiège > Form.doct. sc. ingé. (chim. appl. - Bologne)
Heyen, Georges ;  Université de Liège - ULiège > Département de chimie appliquée > LASSC (Labo d'analyse et synthèse des systèmes chimiques)
Language :
English
Title :
Comparison of supervised learning techniques for atmospheric pollutant monitoring in a Kraft pulp mill
Publication date :
2012
Journal title :
Journal of Computational and Applied Mathematics
ISSN :
0377-0427
eISSN :
1879-1778
Publisher :
Elsevier Science, Amsterdam, Netherlands
Peer reviewed :
Peer Reviewed verified by ORBi
Commentary :
Preprint submitted (status: in revision)
Available on ORBi :
since 01 June 2012

Statistics


Number of views
76 (11 by ULiège)
Number of downloads
7 (7 by ULiège)

Scopus citations®
 
13
Scopus citations®
without self-citations
12
OpenCitations
 
9
OpenAlex citations
 
18

Bibliography


Similar publications



Contact ORBi