- -

Determination of the total acid number (TAN) of used mineral oils in aviation engines by FTIR using regression models

RiuNet: Institutional repository of the Polithecnic University of Valencia

Share/Send to

Cited by

Statistics

Determination of the total acid number (TAN) of used mineral oils in aviation engines by FTIR using regression models

Show simple item record

Files in this item

dc.contributor.author Leal De-Rivas, Beatríz Cecilia es_ES
dc.contributor.author Vivancos, José-Luis es_ES
dc.contributor.author Ordieres Meré, Joaquín es_ES
dc.contributor.author Capuz-Rizo, Salvador F. es_ES
dc.date.accessioned 2018-01-11T09:48:14Z
dc.date.available 2018-01-11T09:48:14Z
dc.date.issued 2017 es_ES
dc.identifier.issn 0169-7439 es_ES
dc.identifier.uri http://hdl.handle.net/10251/94468
dc.description.abstract [EN] Total acid number (TAN) has been considered an important indicator of the oil quality of used oils. TAN is determined by potentiometric titration, which is time-consuming and requires solvent. A more convenient approach to determine TAN is based on infrared (IR) spectral data and multivariate regression models. Predictive models for the determination of TAN using the IR data measured from ashless dispersant oils developed for aviation piston engines (SAE 50) have been developed. Different techniques, including Projection Pursuit Regression (PPR), Partial Least Square, Support Vector Machines, Linear Models and Random Forest (RF), have been used. The used methodology involved a five folder cross validation to derive the best model. Then a full error measure over the whole dataset was taken. A backward variable selection was used and 25 highly relevant variables were extracted. RF provided an acceptable modelling technology with grouped dataset predictions that allowed transformations to be performed that fitted the measured values. A hybrid method considering group of bands as features was used for modelling. An innovative mechanism for wider features selection based on genetic algorithm has been implemented. This method showed better performance than the results obtained using the other methodologies. RMSE and MAE values obtained in the validation were 0.759 and 0.359 for PPR model respectively. es_ES
dc.description.sponsorship The authors would like to thank Roland Tones of the Universidad Metropolitana for his collaboration in oil sample processing. BLDR acknowledges financial support from the Venoco Company. The authors also thank the Universidad Politecnica de Madrid for granting access to the CESVIMA (http://www.cesvima.upm.es/) HPC infrastructure. We would also like to thank the author Beatriz Leal de Rivas (in memoriam), for her efforts to conform this team of researchers from different areas of expertise, and we want to dedicate this work to her loving memory. en_EN
dc.language Inglés es_ES
dc.publisher Elsevier es_ES
dc.relation.ispartof Chemometrics and Intelligent Laboratory Systems es_ES
dc.rights Reconocimiento - No comercial - Sin obra derivada (by-nc-nd) es_ES
dc.subject Aircraft turbine es_ES
dc.subject Engine oil es_ES
dc.subject Total acid number (TAN) es_ES
dc.subject FTIR es_ES
dc.subject Regression models es_ES
dc.subject.classification PROYECTOS DE INGENIERIA es_ES
dc.title Determination of the total acid number (TAN) of used mineral oils in aviation engines by FTIR using regression models es_ES
dc.type Artículo es_ES
dc.identifier.doi 10.1016/j.chemolab.2016.10.015 es_ES
dc.rights.accessRights Abierto es_ES
dc.date.embargoEndDate 2019-06-16 es_ES
dc.contributor.affiliation Universitat Politècnica de València. Departamento de Proyectos de Ingeniería - Departament de Projectes d'Enginyeria es_ES
dc.description.bibliographicCitation Leal De-Rivas, BC.; Vivancos, J.; Ordieres Meré, J.; Capuz-Rizo, SF. (2017). Determination of the total acid number (TAN) of used mineral oils in aviation engines by FTIR using regression models. Chemometrics and Intelligent Laboratory Systems. 160:32-39. doi:10.1016/j.chemolab.2016.10.015 es_ES
dc.description.accrualMethod S es_ES
dc.relation.publisherversion http://doi.org/10.1016/j.chemolab.2016.10.015 es_ES
dc.description.upvformatpinicio 32 es_ES
dc.description.upvformatpfin 39 es_ES
dc.type.version info:eu-repo/semantics/publishedVersion es_ES
dc.description.volume 160 es_ES
dc.relation.pasarela S\323689 es_ES
dc.contributor.funder Venoco, Inc.


This item appears in the following Collection(s)

Show simple item record