Seleção de materiais e design: um método com base nas redes neurais artificiais

• Ano de defesa: 2015
• Autor(a) principal: Nunes, Tercia Valfridia Lima [UNESP]
• Tipo de documento: Tese
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Estadual Paulista (Unesp)
• Palavras-chave em Português: Desenho industrial; Materiais - Seleção; Processo decisorio; Redes neurais (Computação); Industrial design
• Link de acesso: http://hdl.handle.net/11449/126366; http://www.athena.biblioteca.unesp.br/exlibris/bd/cathedra/18-08-2015/000838880.pdf

This study is part of a globalized environment in which companies invest in innovations in search of differention in order to stand out from competittors. This differentiation is an important component material selection, because to create a product to compete with the existing ones is necessary to innovate in materials, design and manufacturing processes. However, the development of a product designers require extensive knowledge of the materials and manufacturing processes. It is worth mentioning the design, as an important considerations in the design process and that this has had a growing involvement in the design of multidisciplinary teams. In addition, it should be noted that Ashby & Johnson (2011) confirm that there is plenty of support for teaching materials in design; an Kindlein et al. (2006) define it as just a basic contact, the relationship that designers have with science and tecnology materials at graduation. In this context, the objective of this work is to propose a method based on the technique of Artificial Neural Networks to design and evaluate a model for predicting the materials and industrial processes to assist the designer in material selection in product design. The aim is to materialize the result of aplying the method proposed in a Microsoft Excel 2010 spreadsheet able to replicate the trained and validated neural network model. In this tool, based on predetermined attributes, manufactuing processes and materials compatible with the required use and based on predetermined attributes options will be provided. It is expected to obtain as output variables, options to address the type of material and the associated manufacturing process, considering predetermined attributes as input variables. Search up with that on the one hand offer the student and/or professional design options appropriate to the type of product to be designed and on the other to optimize the search of materials for product design