Application of intellectual calculation in parameters optimization

It is an important and a hard work to find out the best welding parameters before working at first. On the study of nonlinear mapping function of BP Neural Network (BP NN) and global optimizing ability of Genetic Algorithm (GA), a method combined quadratic regressive orthogonal design with artificial Neural Network and Genetic Algorithm is introduced here, the method can find out the best welding parameters within the whole range of possibilities. The different influence caused by various population size and different crossover fraction is also studied here. Results testify that this method can not only reduce the testing number but also has the virtue of accuracy, efficiency and extensive adaptability.