• Refine Query
  • Source
  • Publication year
  • to
  • Language
  • 1
  • Tagged with
  • 1
  • 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

Aplica??o de sistemas multi-classificadores no diagn?stico de falhas em motores de indu??o trif?sicos

Santos, Sergio Pinheiro dos 11 April 2009 (has links)
Made available in DSpace on 2014-12-17T14:55:37Z (GMT). No. of bitstreams: 1 SergioPS.pdf: 2376478 bytes, checksum: 7999af148ddd33a9739b28a9fdf05cf3 (MD5) Previous issue date: 2009-04-11 / Coordena??o de Aperfei?oamento de Pessoal de N?vel Superior / Equipment maintenance is the major cost factor in industrial plants, it is very important the development of fault predict techniques. Three-phase induction motors are key electrical equipments used in industrial applications mainly because presents low cost and large robustness, however, it isn t protected from other fault types such as shorted winding and broken bars. Several acquisition ways, processing and signal analysis are applied to improve its diagnosis. More efficient techniques use current sensors and its signature analysis. In this dissertation, starting of these sensors, it is to make signal analysis through Park s vector that provides a good visualization capability. Faults data acquisition is an arduous task; in this way, it is developed a methodology for data base construction. Park s transformer is applied into stationary reference for machine modeling of the machine s differential equations solution. Faults detection needs a detailed analysis of variables and its influences that becomes the diagnosis more complex. The tasks of pattern recognition allow that systems are automatically generated, based in patterns and data concepts, in the majority cases undetectable for specialists, helping decision tasks. Classifiers algorithms with diverse learning paradigms: k-Neighborhood, Neural Networks, Decision Trees and Na?ves Bayes are used to patterns recognition of machines faults. Multi-classifier systems are used to improve classification errors. It inspected the algorithms homogeneous: Bagging and Boosting and heterogeneous: Vote, Stacking and Stacking C. Results present the effectiveness of constructed model to faults modeling, such as the possibility of using multi-classifiers algorithm on faults classification / A manuten??o de equipamentos ? um dos principais fatores de custo no ambiente industrial, sendo de fundamental import?ncia o desenvolvimento de t?cnicas de preven??o de falhas. Os motores de indu??o trif?sicos s?o os equipamentos el?tricos mais utilizados na industria, pois apresentam um baixo custo e boa robustez, entretanto, n?o est?o imunes a diversos tipos de falhas como curto-circuitos nos enrolamentos e quebra de barras rot?ricas. Diversas formas de aquisi??o, processamento e an?lise dos sinais s?o aplicadas para melhorar seu diagn?stico. As t?cnicas mais eficazes utilizam sensores de corrente e a an?lise de sua assinatura. Neste trabalho, s?o apresentadas an?lises a partir destes sensores, sendo esta informa??o processada atrav?s do vetor de Park, que fornece uma boa capacidade de visualiza??o dos padr?es. Visando a obten??o destes padr?es fora do ambiente de opera??o, foi desenvolvida uma metodologia para a constru??o das bases de dados. Para a modelagem da m?quina tamb?m ? aplicada a transforma??o de Park no referencial estacion?rio para solucionar as equa??es diferenciais da m?quina. Detec??o de falhas requer uma an?lise profunda das vari?veis envolvidas e suas influ?ncias, tornando o diagn?stico complexo. Reconhecimento de padr?es permite que sistemas sejam gerados automaticamente, por encontrar padr?es e conceitos nos dados, muitas vezes n?o detectados por especialistas, auxiliando na tomada de decis?es. Algoritmos de classifica??o com diferentes paradigmas de aprendizado como k-vizinhos mais pr?ximos, Redes Neurais, ?rvores de Decis?o e Na?ve-Bayes s?o utilizados para reconhecer os padr?es dos motores. M?todos de multiclassifica??o s?o empregados para melhorar o desempenho na taxa de erro de classifica??o, s?o examinados os seguintes algoritmos homog?neos: Bagging e Boosting e heterog?neos: Vote, Stacking e Stacking C. Nos resultados ? poss?vel notar a efic?cia do modelo constru?do para simular as falhas assim como dos algoritmos multiclassificadores para a classifica??o de falhas

Page generated in 0.0919 seconds