Detalhes bibliográficos
Ano de defesa: |
2000 |
Autor(a) principal: |
Terra, Ana Rita Tiradentes |
Orientador(a): |
Pereira, Neocles Alves
 |
Banca de defesa: |
Não Informado pela instituição |
Tipo de documento: |
Dissertação
|
Tipo de acesso: |
Acesso aberto |
Idioma: |
por |
Instituição de defesa: |
Universidade Federal de São Carlos
|
Programa de Pós-Graduação: |
Programa de Pós-Graduação em Engenharia de Produção - PPGEP
|
Departamento: |
Não Informado pela instituição
|
País: |
BR
|
Palavras-chave em Português: |
|
Palavras-chave em Inglês: |
|
Área do conhecimento CNPq: |
|
Link de acesso: |
https://repositorio.ufscar.br/handle/20.500.14289/3543
|
Resumo: |
Production scheduling finds in the most detailed and complex level of production planning and control systems. Due to its nature combinatorial, several methods have been proposed to solve it. Among them there are the techniques of simulation systems and artificial intelligence approaches. This work presents a procedure of solution of production scheduling, through a hybrid model of simulation systems and artificial neural networks. In this procedure, the purpose of the artificial neural network is to learn the relationships between the priority rules designated to the machines of a production system, and the values of performance measures used to evaluate the scheduling. The objective is to analyze the differentiation among a group of combinations of priority rules through the evaluation of four performance measures. Results are presented and commented, highlighting the capacity of generalization of the hybrid model in prescribing priority rules to the machines, based on values of performance measures established by the user. |