Aiming at the shortcomings of slow convergence speed， easy to fall into local optimum and low convergence accuracy of basic harmony search （HS） algorithm， an improved HS（IHS） algorithm is proposed by combining sine cosine optimization operator， Levy flight mechanism and parameter dynamic adjustment strategy. In the improvisation stage， the algorithm first introduces a combination of sine cosine optimization operator and fine-tuning bandwidth to fine-tune the harmony vectors， makes full use of the position information of the optimal individual and the current individual， and improves the calculation accuracy and convergence speed of the algorithm.The Levy flight mechanism is then used to update the fine-tuned bandwidth to avoid the algorithm falling into local optimization and improve the global search capability. During the algorithm iteration process， adaptive dynamic adjustments are made to the storage probability， base tone fine-tuning probability and search domain of the harmony memory to further improve the convergence performance of the algorithm. The results of the performance test comparison experiment on ten reference functions show that the proposed algorithm has the stronger global search ability， the faster convergence speed and the better calculation accuracy.