Proceedings of the 8th conference of the European Society for Fuzzy Logic and Technology (EUSFLAT-13)

Ensembled Self-Adaptive Fuzzy Calibration Models for On-line Cloud Point Prediction

Authors
Carlos Cernuda, Edwin Lughofer, Peter Hintenaus, Wolfgang Märzinger, Thomas Reischer, Marcin Pawlicek, Jürgen Kasberger
Corresponding Author
Carlos Cernuda
Available Online August 2013.
DOI
https://doi.org/10.2991/eusflat.2013.3How to use a DOI?
Keywords
prediction of cloud point self-adaptive fuzzy calibration models ensemble strategy drift prevention
Abstract
In this paper we investigate the usage of non-linear chemometric models, which are calibrated based on near infrared (FTNIR) spectra, in order to increase efficiency and to improve quantification quality in melamine resin production. They rely on fuzzy systems model architecture and are able to {incrementally adapt themselves during the on-line process, resolving dynamic process changes, which may cause severe error drifts of static models. The most informative wavebands in NIR spectra are extracted by a new variant of forward selection, termed as forward selection with bands (FSB) and used as inputs for the fuzzy models. A specific ensemble strategy is developed which is able to properly compensate noise in repeated spectra measurements. Results on high-dimensional data from four independent types of melamine resin show that 1.) our fuzzy modeling methodology can outperform state-of-the-art linear and non-linear chemometric modeling methods in terms of validation error, 2.) the ensemble strategy is able to improve the performance of models without ensembling significantly and 3.) incremental model updates are necessary in order to prevent drifting residuals.
Open Access
This is an open access article distributed under the CC BY-NC license.

Download article (PDF)

Proceedings
8th conference of the European Society for Fuzzy Logic and Technology (EUSFLAT-13)
Part of series
Advances in Intelligent Systems Research
Publication Date
August 2013
ISBN
978-90786-77-78-9
ISSN
1951-6851
DOI
https://doi.org/10.2991/eusflat.2013.3How to use a DOI?
Open Access
This is an open access article distributed under the CC BY-NC license.

Cite this article

TY  - CONF
AU  - Carlos Cernuda
AU  - Edwin Lughofer
AU  - Peter Hintenaus
AU  - Wolfgang Märzinger
AU  - Thomas Reischer
AU  - Marcin Pawlicek
AU  - Jürgen Kasberger
PY  - 2013/08
DA  - 2013/08
TI  - Ensembled Self-Adaptive Fuzzy Calibration Models for On-line Cloud Point Prediction
BT  - 8th conference of the European Society for Fuzzy Logic and Technology (EUSFLAT-13)
PB  - Atlantis Press
SP  - 17
EP  - 24
SN  - 1951-6851
UR  - https://doi.org/10.2991/eusflat.2013.3
DO  - https://doi.org/10.2991/eusflat.2013.3
ID  - Cernuda2013/08
ER  -