Welding parameters optimization for economic design using neural approximation and genetic algorithm

Welding is a basic manufacturing process for making components or assemblies. Recent welding economics research has focused on developing the reliable machinery database to ensure optimum production. It is an important issue, especially for the expensive equipment and the high quality preference in welding. An integrated approach is proposed to address the welding economic design problem. The integrated approach applies general regression neural network to approximate the relationship between welding parameters ( welding current, electrode force, welding time, and sheet thickness) and the failure load. Analytical formula can be generated from the trained general regression neural network, and the mathematical model for the economic welding design can be constructed. An optimization method based on genetic algorithms is then applied to resolve the mathematical model and to select the optimum welding parameters. These parameters are used to obtain the preferred welding quality at the least possible cost.