Algoritmos genéticos de otimização aplicados em processos de soldagem GMAW

• Ano de defesa: 2020
• Autor(a) principal: Moura, Marcus Vinicius Ferreira
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Federal de Lavras; Programa de Pós-Graduação em Engenharia de Sistemas e Automação; UFLA; brasil; Departamento de Administração e Economia
• Palavras-chave em Português: Algoritmo genético multiobjetivo; Elementos finitos; Soldagem - Otimização; Multiobjective genetic algorithm; Welding - Optimization; Finite elements; Soldagem
• Link de acesso: http://repositorio.ufla.br/jspui/handle/1/46112

The welding process plays an important role in the manufacture of various products in the most varied industrial sectors. Despite its wide applicability, this process is subject to some inconsistency in quality due to controllable and uncontrollable variables. In this work, using the Finite Element Method (FEM), we tried to simulate the movement of the heat flow in the base metal, submitted to the Gas Metal Arc Welding (GMAW) welding process. For that, control limits were established, such as voltage and electric current (in the form of the heat source) and welding speed in order to obtain optimized values of deformations and stresses, arising from the welding process used. As stresses and strains are inversely proportional quantities, we worked with a multiobjective function to find an optimized solution. For the modeling of the process, empirical data from weld beads applied on both sides of ASTM A36 steel plates were used in the "T"configuration (type joint "T"). As a support for the simulations, the multiobjective Genetic Algorithm Non-dominated Sorting Genetic Algorithm II (NSGA II) in conjunction with the Finite Element Method (FEM), via ANSYS 14.5 software. The results obtained were consistent with literature data within the pre-established limits, that is, deformation and stress less than 2 mm and 600 MPa, respectively. This demonstrates the potential of using the FEM in conjunction with the NSGA II genetic algorithm to predict input variables in the welding process, which can be considered an important contribution to the technological advancement of the GMAW welding process.