Diesel oil quality parameter determinations using support vector regression and near infrared spectroscopy for hydrotreating feedstock monitoring

dc.creatorAlves, JCL
dc.creatorPoppi, RJ
dc.date2012
dc.date2014-07-30T14:42:25Z
dc.date2015-11-26T18:06:12Z
dc.date2014-07-30T14:42:25Z
dc.date2015-11-26T18:06:12Z
dc.date.accessioned2018-03-29T00:48:24Z
dc.date.available2018-03-29T00:48:24Z
dc.identifierJournal Of Near Infrared Spectroscopy. N I R Publications, v. 20, n. 4, n. 419, n. 425, 2012.
dc.identifier0967-0335
dc.identifierWOS:000308680400002
dc.identifier10.1255/jnirs.1012
dc.identifierhttp://www.repositorio.unicamp.br/jspui/handle/REPOSIP/61727
dc.identifierhttp://repositorio.unicamp.br/jspui/handle/REPOSIP/61727
dc.identifier.urihttp://repositorioslatinoamericanos.uchile.cl/handle/2250/1293302
dc.descriptionProduction monitoring and final quality control of diesel can be performed in refineries using near infrared (NIR) spectroscopy combined with regression algorithms. Partial least squares (PLS) is the multivariate regression approach commonly used for such purposes, but it is deficient for modelling complex data sets, such as found in diesel production at refineries. On the other hand, support vector regression (SVR) has demonstrated greater efficiency with high generalisation performance. The aim of this work was to develop regression models using SVR to improve the effectiveness of determining feedstock quality parameters monitored for hydrotreating process control refinery diesel production. SVR and PLS models were developed for the parameters aniline point, cetane index, density and temperature of distillation (initial boiling point and 50%, 85% and 90% recovered). The results indicate the superior modelling capability of SVR. SVR models predicted test set samples with root mean squares errors which were 21% to 54% lower than those predicted using PLS. The NIR determinations presented root mean square error lower than the reproducibility values specified by the established reference methods.
dc.description20
dc.description4
dc.description419
dc.description425
dc.languageen
dc.publisherN I R Publications
dc.publisherChichester
dc.publisherInglaterra
dc.relationJournal Of Near Infrared Spectroscopy
dc.relationJ. Near Infrared Spectrosc.
dc.rightsfechado
dc.sourceWeb of Science
dc.subjectsupport vector regression
dc.subjectpartial least squares
dc.subjectdiesel
dc.subjectnear infrared (NIR) spectroscopy
dc.subjectProcess Analytical-chemistry
dc.subjectNeural-networks
dc.subjectPrediction
dc.subjectModels
dc.subjectPls
dc.subjectCalibration
dc.subjectTutorial
dc.subjectNir
dc.titleDiesel oil quality parameter determinations using support vector regression and near infrared spectroscopy for hydrotreating feedstock monitoring
dc.typeArtículos de revistas


Este ítem pertenece a la siguiente institución