Optimization of welding robot based on genetic algorithm and BP neural network

Abstract

Today, with the development of industrial automation, reasonable robot welding parameters are of great significance to obtain the ideal weld quality. It not only enables a stricter guarantee of the weld quality, but also greatly improves the production efficiency. Firstly, after consulting literature and experimental practice on the welding process, the whole robot welding process and the key influencing factors on the welding seam quality are analyzed in detail. Secondly, the genetic algorithm is used in section 4 to optimize the BP neural network to optimize the parameters of the identified welding seam quality reference index-welding time, which realizes the effective measurement of welding time with less experimental data, and enhances the local search ability of the algorithm. Finally, the optimized results are obtained. The optimal welding time is 218.0899s under the data of five layers of currents of 341A, 348A, 345A, 345A, and 345A, due to the welding time of the conventional equal area model. It can be concluded that the BP neural network algorithm optimized by the genetic algorithm is used to optimize the parameters of the welding robot.