New contributions to non linear process monitoring through kernel partial least squares

The kernel partial least squares (KPLS) method was originally focused on soft-sensor calibration for predicting online quality attributes. In this work, an analysis of the KPLS-based modeling technique and its application to nonlinear process monitoring are presented. To this effect, the measureme...

Descripción completa

Detalles Bibliográficos
Autores principales: Vega, Jorge Ruben, Godoy, José Luis, Marchetti, Jacinto, Zumoffen, David
Formato: Artículo acceptedVersion
Lenguaje:Inglés
Publicado: 2018
Materias:
nonlinear
process monitoring
Kernel Partial
Acceso en línea:http://hdl.handle.net/20.500.12272/3119
Aporte de:
RIA - Repositorio Institucional Abierto (UTN) de Universidad Tecnológica Nacional
id I68-R174-20.500.12272-3119
record_format dspace
spelling I68-R174-20.500.12272-31192023-07-03T19:03:22Z New contributions to non linear process monitoring through kernel partial least squares Vega, Jorge Ruben Godoy, José Luis Marchetti, Jacinto Zumoffen, David nonlinear process monitoring Kernel Partial The kernel partial least squares (KPLS) method was originally focused on soft-sensor calibration for predicting online quality attributes. In this work, an analysis of the KPLS-based modeling technique and its application to nonlinear process monitoring are presented. To this effect, the measurement decomposition, the development of new specific statistics acting on non-overlapped domains, and the contribution analysis are addressed for purposes of fault detection, diagnosis, and prediction risk assessment. Some practical insights for synthesizing the models are also given, which are related to an appropriate order selection and the adoption of the kernel function parameter. A proper combination of scaled statistics allows the definition of an efficient detection index for monitoring a nonlinear process. The effectiveness of the proposed methods is confirmed by using simulation examples. Keywords: KPLS Modeling, Fault Detection, Fault Diagnosis, Prediction Risk Assessment, Nonlinear Processes. Fil: Vega, Jorge Ruben/ Universidad Tecnològica Nacional. Argentina Peer Reviewed 2018-09-14T22:08:31Z 2018-09-14T22:08:31Z 2013 info:eu-repo/semantics/article info:eu-repo/semantics/acceptedVersion info:ar-repo/semantics/artículo http://hdl.handle.net/20.500.12272/3119 eng Técnicas numéricas de estimación y optimización: aplicaciones en problemas de nanotecnologìa y de energía eléctrica, info:eu-repo/semantics/openAccess http://creativecommons.org/licenses/by-nc-sa/4.0/ Condiciones de Uso libre desde su aprobación / aprobación Atribución-NoComercial-CompartirIgual 4.0 Internacional application/pdf
institution Universidad Tecnológica Nacional
institution_str I-68
repository_str R-174
collection RIA - Repositorio Institucional Abierto (UTN)
language Inglés
topic nonlinear
process monitoring
Kernel Partial
spellingShingle nonlinear
process monitoring
Kernel Partial
Vega, Jorge Ruben
Godoy, José Luis
Marchetti, Jacinto
Zumoffen, David
New contributions to non linear process monitoring through kernel partial least squares
topic_facet nonlinear
process monitoring
Kernel Partial
description The kernel partial least squares (KPLS) method was originally focused on soft-sensor calibration for predicting online quality attributes. In this work, an analysis of the KPLS-based modeling technique and its application to nonlinear process monitoring are presented. To this effect, the measurement decomposition, the development of new specific statistics acting on non-overlapped domains, and the contribution analysis are addressed for purposes of fault detection, diagnosis, and prediction risk assessment. Some practical insights for synthesizing the models are also given, which are related to an appropriate order selection and the adoption of the kernel function parameter. A proper combination of scaled statistics allows the definition of an efficient detection index for monitoring a nonlinear process. The effectiveness of the proposed methods is confirmed by using simulation examples. Keywords: KPLS Modeling, Fault Detection, Fault Diagnosis, Prediction Risk Assessment, Nonlinear Processes.
format Artículo
acceptedVersion
Artículo
author Vega, Jorge Ruben
Godoy, José Luis
Marchetti, Jacinto
Zumoffen, David
author_facet Vega, Jorge Ruben
Godoy, José Luis
Marchetti, Jacinto
Zumoffen, David
author_sort Vega, Jorge Ruben
title New contributions to non linear process monitoring through kernel partial least squares
title_short New contributions to non linear process monitoring through kernel partial least squares
title_full New contributions to non linear process monitoring through kernel partial least squares
title_fullStr New contributions to non linear process monitoring through kernel partial least squares
title_full_unstemmed New contributions to non linear process monitoring through kernel partial least squares
title_sort new contributions to non linear process monitoring through kernel partial least squares
publishDate 2018
url http://hdl.handle.net/20.500.12272/3119
work_keys_str_mv AT vegajorgeruben newcontributionstononlinearprocessmonitoringthroughkernelpartialleastsquares
AT godoyjoseluis newcontributionstononlinearprocessmonitoringthroughkernelpartialleastsquares
AT marchettijacinto newcontributionstononlinearprocessmonitoringthroughkernelpartialleastsquares
AT zumoffendavid newcontributionstononlinearprocessmonitoringthroughkernelpartialleastsquares
_version_ 1770623467224301568

Ejemplares similares