Adaptive fault detection and diagnosis using parsimonious Gaussian mixture models trained with distributed computing techniques

Página do item simplificado
dc.creatorThiago A. Nakamura
dc.creatorReinaldo M. Palhares
dc.creatorWalmir M. Caminhas
dc.creatorBenjamin R. Menezes
dc.creatorMário Cesar M. M. de Campos
dc.creatorUbirajara Fumega
dc.creatorCarlos H. de M. Bomfim
dc.creatorAndré Paim Lemos
dc.date.accessioned2025-03-25T14:13:55Z
dc.date.accessioned2025-09-09T00:18:39Z
dc.date.available2025-03-25T14:13:55Z
dc.date.issued2016
dc.identifier.doihttps://doi.org/10.1016/j.jfranklin.2016.11.024
dc.identifier.issn0016-0032
dc.identifier.urihttps://hdl.handle.net/1843/80887
dc.languageeng
dc.publisherUniversidade Federal de Minas Gerais
dc.rightsAcesso Restrito
dc.subjectRepresentação do conhecimento (Teoria da informação)
dc.subjectAprendizado do computador
dc.subject.otherGaussian mixture models
dc.subject.otherfault detection and diagnosis
dc.subject.otherstatistical models
dc.subject.otherusing the Parsimonious Gaussian Mixture Models (PGMM) as the base of the system brings greater flexibility to the model, allowing for better representation of nonlinear and dynamic behaviours
dc.titleAdaptive fault detection and diagnosis using parsimonious Gaussian mixture models trained with distributed computing techniques
dc.typeArtigo de periódico
local.citation.epage2572
local.citation.spage2543
local.citation.volume354
local.description.resumoAfter a great advance by the industry on processes automation, an important challenge still remains: the automation under abnormal situations. The first step towards solving this challenge is the Fault Detection and Diagnosis (FDD). This work proposes a batch-incremental adaptive methodology for fault detection and diagnosis based on mixture models trained on a distributed computing environment. The models used are from a family of Parsimonious Gaussian Mixture Models (PGMM), in which the reduced number of parameters of the model brings important advantages when there are few data available, an expected scenario of faulty conditions. On the other hand, a large number of different models rises another challenge, the best model selection for a given behaviour. For that, it is proposed to train a large number of models, using distributed computing techniques, for only then select the best model. This work proposes the usage of the Spark framework, ideal for iterative computations. The proposed methodology was validated in a simulated process, the Tennessee Eastman Process (TEP), showing good results for both the detection and the diagnosis of faults. Furthermore, numeric experiments show the viability of training a large number of models for the best model selection a posteriori.
local.publisher.countryBrasil
local.publisher.departmentENG - DEPARTAMENTO DE ENGENHARIA ELETRÔNICA
local.publisher.initialsUFMG
local.url.externahttps://www.sciencedirect.com/science/article/pii/S0016003216304434

Arquivos

Licença do pacote

Agora exibindo 1 - 1 de 1
Imagem de Miniatura
Nome:
License.txt
Tamanho:
1.99 KB
Formato:
Plain Text
Descrição:
Baixar

Coleções

Artigo de Periódico

Logo UFMG