• 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

Redes neurais artificiais e redes complexas: aplicaÃÃes em processos quÃmicos. / Artificial neural networks and complex networks: an application in chemical plants.

Daniel Muniz Bezerra 29 June 2005 (has links)
nÃo hà / Na primeira parte deste trabalho, empregamos uma rede neural artificial (RNA) treinada com algoritmo back-propagation para inferir a volatilidade dos gases liquefeitos de petrÃleo (GLP) produzidos em uma torre de fracionamento de lÃquido de gÃs natural (LGN). Os resultados obtidos indicam que a RNA fornece melhores respostas do que um simulador desenvolvido com base fenomenolÃgica que se encontra em fase de implementaÃÃo na planta em estudo. Na segunda parte da dissertaÃÃo, o nosso objetivo primordial à demonstrar que os fluxogramas de processos de refinarias de petrÃleo podem estar intrinsecamente associados à topologias de redes complexas, que sÃo scale-free, exibem efeitos de mundo pequeno e possuem organizaÃÃo hierÃrquica. A emergÃncia dessas propriedades em redes artificiais à explicada como uma consequÃncia dos princÃpios usados no design de projeto dos processos, os quais incluem regras heurÃsticas e tÃcnicas algorÃtmicas. Esperamos que esses resultados sejam tambÃm vÃlidos para plantas quÃmicas de diferentes tipos e capacidades. / In the first part of this work we apply an artificial neural network (ANN) trained with a back-propagation algorithm to predict the volatility of liquefied petroleum gases (LPG) produced from a fractionation tower of natural gas liquid (NGL). Our analysis indicate that the ANN scheme provides better results than a simulator developed based phenomenological which is currently being implemented in the plant under study. In the second part, our primary objective is to demonstrate that flowsheets of oil refineries can be intrinsically associated to complex network topologies, which are scale-free, display small-word effect and have hierarchical organization. The emergence of these properties artificial networks is explained as a consequence of the design principles used in the processâ design, which include heuristics rules and algorithmic techniques. We expect these results to be also valid for chemical plants of different types and capacities.

Page generated in 0.0546 seconds