Detalhes bibliográficos
| Resumo: | This paper suggests a methodology based on a neuroevolutionary approach to optimize the use of material in blow molding applications. This approach aims at determining the optimal thickness distribution for a certain blow molded product as a function of its geometry. Multiobjective search is performed by neuroevolution to reflect the conflicting nature of the design problem and to capture some possible trade-offs. During the search, each design alternative is evaluated through a finite element analysis. The coordinates of mesh elements are the inputs to an artificial neural network that is evolved and whose output determines the thickness for the corresponding location. The proposed approach is applied to the design of an industrial bottle. The results reveal validity and usefulness of the proposed technique, which were able to distribute the material along mostcritical regions to adequate mechanical properties. The approach is general and can be applied to products with different geometries. |
|---|
| Autores principais: | Denysiuk, Roman |
|---|
| Outros Autores: | Gonçalves, Nuno; Pinto, Renê Souza; Silva, Hugo Miguel Andrade Lopes Figueiredo; Duarte, F. M.; Nunes, J. P.; Gaspar-Cunha, A. |
|---|
| Assunto: | Blow Molding Process optimization Evolutionary algorithms Thickness optimization Engenharia e Tecnologia::Engenharia dos Materiais Engenharia e Tecnologia::Outras Engenharias e Tecnologias Indústria, inovação e infraestruturas Produção e consumo sustentáveis |
|---|
| Ano: | 2019 |
|---|
| País: | Portugal |
|---|
| Tipo de documento: | artigo |
|---|
| Tipo de acesso: | acesso aberto |
|---|
| Instituição associada: | Universidade do Minho |
|---|
| Idioma: | inglês |
|---|
| Origem: | RepositóriUM - Universidade do Minho |
|---|