A fault detection and diagnosis technique for multivariate processes using a PLS-decomposition of the measurement space

A newstatisticalmonitoring technique based on partial least squares (PLS) is proposed for fault detection and di- 24 agnosis inmultivariate processes that exhibit collinearmeasurements. A typical PLS regression (PLSR)modeling 25 strategy is first extended by adding the projections of the model out...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Vega, Jorge Ruben, Godoy, José Luis, Marchetti, Jacinto
Formato: Artículo acceptedVersion
Lenguaje:Inglés
Publicado: 2018
Materias:
multivariate processes
PLS-decomposition
Acceso en línea:http://hdl.handle.net/20.500.12272/3121
Aporte de:
RIA - Repositorio Institucional Abierto (UTN) de Universidad Tecnológica Nacional
id I68-R174-20.500.12272-3121
record_format dspace
spelling I68-R174-20.500.12272-31212023-07-03T21:53:37Z A fault detection and diagnosis technique for multivariate processes using a PLS-decomposition of the measurement space Vega, Jorge Ruben Godoy, José Luis Marchetti, Jacinto multivariate processes PLS-decomposition A newstatisticalmonitoring technique based on partial least squares (PLS) is proposed for fault detection and di- 24 agnosis inmultivariate processes that exhibit collinearmeasurements. A typical PLS regression (PLSR)modeling 25 strategy is first extended by adding the projections of the model outputs to the latent space. Then, a PLS- 26 decomposition of the measurements into four terms that belongs to four different subspaces is derived. In 27 Q2 order to online monitor the PLS-projections in each subspace, new specific statistics with non-overlapped do- 28 mains are combined into a single index able to detect process anomalies. To reach a complete diagnosis, a further 29 decomposition of each statistic was defined as a sum of variable contributions. By adequately processing all this 30 information, the technique is able to: i) detect an anomaly through a single combined index, ii) diagnose the 31 anomaly class from the observed pattern of the four component statistics with respect to their respective confi- 32 dence intervals, and iii) identify the disturbed variables based on the analysis of themain variable contributions 33 to each of the four subspaces. The effectiveness observed in the simulated examples suggests the potential appli- 34 cation of this technique to real production systems. Fil: Vega, Jorge Ruben. Universidad Tecnológica Nacional. Argentina Fil: Godoy, Jose Luis. Universidad Tecnológica Nacional. Argentina Fil: Marchetti, Jacinto. Universidad Tecnológica Nacional. Argentina Peer Reviewed 2018-09-14T22:23:22Z 2018-09-14T22:23:22Z 2013 info:eu-repo/semantics/article info:eu-repo/semantics/acceptedVersion info:ar-repo/semantics/artículo http://hdl.handle.net/20.500.12272/3121 eng info:eu-repo/semantics/openAccess http://creativecommons.org/licenses/by-nc-sa/4.0/ Condiciones de Uso libre desde su 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 multivariate processes
PLS-decomposition
spellingShingle multivariate processes
PLS-decomposition
Vega, Jorge Ruben
Godoy, José Luis
Marchetti, Jacinto
A fault detection and diagnosis technique for multivariate processes using a PLS-decomposition of the measurement space
topic_facet multivariate processes
PLS-decomposition
description A newstatisticalmonitoring technique based on partial least squares (PLS) is proposed for fault detection and di- 24 agnosis inmultivariate processes that exhibit collinearmeasurements. A typical PLS regression (PLSR)modeling 25 strategy is first extended by adding the projections of the model outputs to the latent space. Then, a PLS- 26 decomposition of the measurements into four terms that belongs to four different subspaces is derived. In 27 Q2 order to online monitor the PLS-projections in each subspace, new specific statistics with non-overlapped do- 28 mains are combined into a single index able to detect process anomalies. To reach a complete diagnosis, a further 29 decomposition of each statistic was defined as a sum of variable contributions. By adequately processing all this 30 information, the technique is able to: i) detect an anomaly through a single combined index, ii) diagnose the 31 anomaly class from the observed pattern of the four component statistics with respect to their respective confi- 32 dence intervals, and iii) identify the disturbed variables based on the analysis of themain variable contributions 33 to each of the four subspaces. The effectiveness observed in the simulated examples suggests the potential appli- 34 cation of this technique to real production systems.
format Artículo
acceptedVersion
Artículo
author Vega, Jorge Ruben
Godoy, José Luis
Marchetti, Jacinto
author_facet Vega, Jorge Ruben
Godoy, José Luis
Marchetti, Jacinto
author_sort Vega, Jorge Ruben
title A fault detection and diagnosis technique for multivariate processes using a PLS-decomposition of the measurement space
title_short A fault detection and diagnosis technique for multivariate processes using a PLS-decomposition of the measurement space
title_full A fault detection and diagnosis technique for multivariate processes using a PLS-decomposition of the measurement space
title_fullStr A fault detection and diagnosis technique for multivariate processes using a PLS-decomposition of the measurement space
title_full_unstemmed A fault detection and diagnosis technique for multivariate processes using a PLS-decomposition of the measurement space
title_sort fault detection and diagnosis technique for multivariate processes using a pls-decomposition of the measurement space
publishDate 2018
url http://hdl.handle.net/20.500.12272/3121
work_keys_str_mv AT vegajorgeruben afaultdetectionanddiagnosistechniqueformultivariateprocessesusingaplsdecompositionofthemeasurementspace
AT godoyjoseluis afaultdetectionanddiagnosistechniqueformultivariateprocessesusingaplsdecompositionofthemeasurementspace
AT marchettijacinto afaultdetectionanddiagnosistechniqueformultivariateprocessesusingaplsdecompositionofthemeasurementspace
AT vegajorgeruben faultdetectionanddiagnosistechniqueformultivariateprocessesusingaplsdecompositionofthemeasurementspace
AT godoyjoseluis faultdetectionanddiagnosistechniqueformultivariateprocessesusingaplsdecompositionofthemeasurementspace
AT marchettijacinto faultdetectionanddiagnosistechniqueformultivariateprocessesusingaplsdecompositionofthemeasurementspace
_version_ 1770623467679383552

Ejemplares similares