Please use this identifier to cite or link to this item:
http://hdl.handle.net/1843/42874
Type: | Artigo de Periódico |
Title: | A new fault classification approach applied to Tennessee Eastman benchmark process |
Authors: | Marcos Flávio Silveira Vasconcelos D"Angelo Reinaldo Martinez Palhares Murilo César Osório Camargos Renato Dourado Maia João Batista Mendes Petr Iakovlevitch Ekel |
Abstract: | This study presents a data-based methodology for fault detection and isolation in dynamic systems based on fuzzy/Bayesian approach for change point detection associated with a hybrid immune/neural formulation for pattern classification applied to the Tennessee Eastman benchmark process. The fault is detected when a change occurs in the signals from the sensors and classified into one of the classes by the immune/neural formulation. The change point detection system is based on fuzzy set theory associated with the Metropolis–Hastings algorithm and the classification system, the main contribution of this paper is based on a representation which combines the ClonALG algorithm with the Kohonen neural network. |
Subject: | Engenharia elétrica Algoritmos Redes neurais (Computação) Benchmarking (Administração) |
language: | eng |
metadata.dc.publisher.country: | Brasil |
Publisher: | Universidade Federal de Minas Gerais |
Publisher Initials: | UFMG |
metadata.dc.publisher.department: | ICA - INSTITUTO DE CIÊNCIAS AGRÁRIAS |
Rights: | Acesso Aberto |
metadata.dc.identifier.doi: | https://doi.org/10.1016/j.asoc.2016.08.040 |
URI: | http://hdl.handle.net/1843/42874 |
Issue Date: | Dec-2016 |
metadata.dc.url.externa: | https://www.sciencedirect.com/science/article/pii/S1568494616304343#! |
metadata.dc.relation.ispartof: | Applied Soft Computing |
Appears in Collections: | Artigo de Periódico |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
A new fault classification approach applied to Tennessee Eastman benchmark process.pdf | 2.66 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.