• Refine Query
  • Source
  • Publication year
  • to
  • Language
  • 1
  • Tagged with
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • About
  • The Global ETD Search service is a free service for researchers to find electronic theses and dissertations. This service is provided by the Networked Digital Library of Theses and Dissertations.
    Our metadata is collected from universities around the world. If you manage a university/consortium/country archive and want to be added, details can be found on the NDLTD website.
1

An?lise de desempenho de abordagens orientadas a fluxo de dados aplicadas ? detec??o de falhas de processos industriais

Germano, Amanda Lucena 31 July 2017 (has links)
Submitted by Automa??o e Estat?stica (sst@bczm.ufrn.br) on 2018-01-15T21:33:32Z No. of bitstreams: 1 AmandaLucenaGermano_DISSERT.pdf: 7217536 bytes, checksum: 25a20d10202bb0af3f3b8e89539d2fbb (MD5) / Approved for entry into archive by Arlan Eloi Leite Silva (eloihistoriador@yahoo.com.br) on 2018-01-17T12:52:40Z (GMT) No. of bitstreams: 1 AmandaLucenaGermano_DISSERT.pdf: 7217536 bytes, checksum: 25a20d10202bb0af3f3b8e89539d2fbb (MD5) / Made available in DSpace on 2018-01-17T12:52:40Z (GMT). No. of bitstreams: 1 AmandaLucenaGermano_DISSERT.pdf: 7217536 bytes, checksum: 25a20d10202bb0af3f3b8e89539d2fbb (MD5) Previous issue date: 2017-07-31 / Com a necessidade do aumento da qualidade dos produtos e do desempenho dos processos, o grau de automa??o cresceu bastante nas ind?strias. Com isso, os sistemas est?o cada vez mais complexos e v?m acompanhados por problemas dif?ceis de resolver devido ? alta dimensionalidade desses sistemas e do grande volume do fluxo de informa??es necess?rias, al?m da aleatoriedade de falhas e defeitos. Uma falha inesperada pode levar a riscos operacionais, por isso a import?ncia de detectar e localizar a falha, principalmente quando a planta industrial ainda est? operando em uma regi?o control?vel e ? poss?vel agir para trazer o processo de volta para o estado normal, seguro e operacional. Assim, ? desej?vel que o sistema de detec??o de falhas forne?a respostas r?pidas e confi?veis com um esfor?o computacional adequado para processamento em tempo real, mesmo necessitando tratar com grandes quantidades de dados. Para trabalhar com grandes quantidades de dados em tempo real, surgiu o modelo de fluxo de dados, que consiste de uma sequ?ncia ordenada de pontos que s? podem ser lidos apenas uma ou algumas poucas vezes. Essa ?rea cresceu bastante nos ?ltimos anos, principalmente devido a grande quantidade de sistemas que precisavam tratar com dados desse tipo, que incluem desde dados do mercado financeiro, registros telef?nicos, transa??es web a dados m?dicos, redes de sensores ou mesmo dados multim?dia. Diante da relev?ncia do tema de detec??o de falhas, nessa tese foram utilizados o TEDA (Typicality and Eccentricity Data Analytics), o RDE (Recursive Density Estimation) e o R-PCA (Recursive Principal Component Analysis) como ferramentas para detec??o de falhas em processos industriais. Para a an?lise do desempenho de cada uma dessas abordagens foi utilizado o cl?ssico benchmark Tennessee Eastman Process. / In order to increase product quality and process performance, the degree of automation has grown significantly in industries. As a result, systems are increasingly complex and are accompanied by problems that are difficult to solve due to the high dimensionality of these systems and the large amount of information flow, as well as the randomness of faults and defects. An unexpected failure can lead to operational risks, so the importance of detecting and locating the fault, especially when the industrial plant is still operating in a controllable region and it is possible to act to bring the process back to normal, safe and operational. Thus, it is desirable for the fault detection system to provide fast and reliable responses with a computational effort appropriate for real-time processing, even though it requires handling large amounts of data. In this context, data stream-oriented algorithms to outlier detection may be promising candidates for fault detection of industrial process, because they work with sequences of temporarily ordered samples. In addition, they handle well with large amount of data because they are recursive and online algorithms that do not need to store past samples. Thus, in this dissertation two algorithms of this class are analyzed, named TEDA (Typicality and Eccentricity Data Analytics) and RDE (Recursive Density Estimation), when applied to fault detection of industrial processes. Their performances are compared to R-PCA (Recursive Principal Component Analysis) algorithm. The classic Tennessee Eastman Process benchmark was used as case study to evaluate these algorithms.

Page generated in 0.02 seconds