某些实际问题的优化目标是求所有的局部最优解，即求解多峰寻优问题，为了求解多峰优化问题，提出了改造的微粒

群优化算法．尽量减少微粒群算法中的全局因素，从而增大其局部因素，同时采用变步长方法增加微粒的多样性．并给出了该算法

的原理和步骤．仿真实验表明该算法概念清楚，计算简单，具有很好的局部寻优特性，可应用求解于多峰寻优问题．另外还给出了几

个运算实例和与其它优化算法的比较-Some of the practical problems of optimization goal is to strive for all local optimal solution, ie solving multimodal optimization problems, and proposed the transformation of the particle swarm optimization algorithm for solving multimodal optimization problems. Minimize particle swarm optimization global factors, thereby increasing its local factors, variable step size at the same time to increase the diversity of the particles. And the principles and steps of the algorithm. Simulation results show that a clear concept of the algorithm, a simple calculation and good local optimization features, can be applied to solving multimodal optimization problems. It also gives the comparison of several computing instances and other optimization algorithms