Aiming at the shortages of basic flower pollination algorithm,in order to improve the convergence rate and optimization accuracy of the algorithm,this paper proposed an adaptive flower pollination algorithm fusing simulated annealing mechanism and dynamically adjusting the global step length and local reproduction probability according to the iterative evolution.Firstly,the scaling factor of the deformed exponential function is used to control step length in the global pollination of the basic algorithm,so that the individual of flower can be adaptively updated with the number of iterations.Then,through combining Rayleigh distribution function and the number of iterations,the factors of multiplication probability are improved,thus avoiding the precocious convergence and making the solution close to the optimal solution in the later stage.Finally,a simulated annealing cooling operation is incorporated into the improved flower pollination algorithm,which not only increases the diversity of population,but also improves the overall performance of algorithm.The simulation results show that the algorithm has faster convergence speed and higher convergence precision,and the optimization performance of the proposed algorithm is improved.