一种提高粒子群算法优化性能的方法

针对粒子群优化算法在解决控制领域优化问题时存在的不足,文章在现有粒子群算法的几种改进方法分析的基础上,提出通过控制算法位置和速度的初始化策略,来提高算法的收敛速度、精度和成功率,该方法适用于各种粒子群改进算法。最后,通过两种改进后的粒子群算法,采用初始化策略对典型单峰函数和多峰函数进行实验测试,结果表明,该方法可以有效提高两种改进粒子群算法的搜索成功率、收敛速度和准确性。

A Method of Improving Particle Swarm Optimization Algorithm Performance

The optimization problem in electrical control field has complex and multimodal target function. In order to improve the convergence velocity, accuracy and success rate, the paper provides a new method to control place and velocity initialization of the Particle Swarm Optimization algorithm（PSO）. The method is applied to each improved PSO. The contrast of different PSO with initialization strategy proposed in the paper by representative test functions is conducted. The results show that the improved method has better performance in global search ability, convergence rate and accuracy.