关键词: 混沌思想, 分组并行粒子群算法, 动态模糊神经网络, 记忆功放模型

Abstract: In order to improve the accuracy of radio frequency power amplifier with memory effect, and the early fast convergence rate of the traditional particle swarm optimization algorithm, but in the later period easy to fall into premature and local optimum characteristics, a group of parallel chaotic particle swarm optimization algorithm is proposed and the dynamic fuzzy neural network parameters are optimized by using the algorithm to optimize the dynamic fuzzy neural network parameters. The grouping parallel chaotic particle swarm optimization algorithm is used to combine the grouping method and chaotic particle swarm optimization algorithm. The population can be divided into several groups. Each group computes independently to improve the convergence rate, while the chaos theory is applied to each particle to avoid premature and local optimum, shortening the time of iteration. By the simulation, the training error of the model is reduced to 0.1, and the convergence rate is improved by 32.5%, which verifies the validity and reliability of the method.

Key words: chaos theory, grouping parallel particle swarm optimization, dynamic fuzzy neural network, memory power amplifier model