In view of such flaws as the premature convergence of the traditional particle swarm optimization algorithm with its liability to fall into the local optimization during the optimization process, a particle swarm algorithm, which is based on dynamic adjustment of inertia weights and learning factors, has thus been proposed. The proposed algorithm improves the inertial weights and learning factor parameters for the optimization of the traditional algorithm. As the algorithm continues to iterate, its inertial weights and learning factors are dynamically optimized with the increase of iteration times, so as to strike a balance between the local optimization ability and the global search ability.The experimental results show that the improved algorithm is superior to the traditional particle swarm optimization algorithm in convergence speed and convergence accuracy, thus helping to improve the premature convergence problem.