LAUSR

To make the welding robot more reasonable and furthermore improve the productivity and reduce costs, two intelligent algorithms for welding path optimization, genetic algorithm (GA) and discrete particle swarm optimization, are proposed to optimize the welding robot path. Through the improved selection of the operator, the GA achieves the fastest iterative efficiency. By introducing the “swap operator” and “swap sequence” in the particle swarm optimization algorithm, the PSO algorithm is improved for the solution of the discrete problem (welding robot path planning) which is superior to the continuous optimization problem. Besides, for the better iterative efficiency of PSO, the parameters of traditional inertia weight are determined by a linear inertia weigh, which can improve the convergence performance of the algorithm. The modeling and solutions of the two algorithms are discussed in detail to illustrate the applications in the welding robot path optimization. In order to compare the pros and cons of the two algorithms, the same welding tasks are presented, and Matlab simulation is carried out. The simulation results show that both genetic algorithm and particle swarm optimization algorithm can obtain the optimal or near-optimal welding path by iterative calculations.