An adaptive global harmony search(AGHS) algorithm is proposed for the problem of premature convergence in novel global harmony search(NGHS) algorithm. A novel position updating strategy is employed in the AGHS algorithm and the mutation operation is excluded with the diversity of harmony memory which is characterized by the norm of differential vector. With the guidance of the diversity of harmony memory, the optimal performance of the algorithm is improved, which avoids the algorithm trapped in local optimal. In addition, the AGHS algorithm is simpler and less parameter needed. The simulation is carried out by using the optimization algorithm of AGHS, PSO, GA and other HS variants that have been proposed. The simulation results show that the AGHS algorithm has higher convergence precision and convergence rate.