Inspired from social behavior of organisms such as bird flocking, particle swarm optimization(PSO) has rapid convergence speed and has been successfully applied in many optimization problems. in this paper, we present a dynamic particle swarm optimization algorithm to enhance the performance of standard PSO. We design a novel function to compute the initial dynamic inertia weight, and then calculate inertia weight through a nonlinear function. Afterwards, searching process is repeated until the max iteration number is reached or the minimum error condition is satisfied. to testify the effectiveness of the proposed algorithm, we conduct two experiments. Experimental results show that our algorithm performs better than FPSO and standard PSO in best fitness and convergence speed.