论文部分内容阅读
针对差分进化(DE)算法在解决优化问题时收敛速度不够快、容易陷入局部最优的缺点,本文通过分析DE算法不同变异操作模式的优缺点及缩放因子和交叉因子对算法寻优性能的影响,提出一种多种群自适应差分进化算法.在进化过程中,不同种群采用不同的变异操作模式,有利于不同模式之间的优势互补,同时使用logistic模型来自适应调节缩放因子和交叉因子,使算法在前期提高全局搜索能力,后期提高局部搜索能力.对典型测试函数的仿真实验表明所提算法计算精度高、收敛速度快.
Aiming at the shortcomings of the differential evolution (DE) algorithm in solving the optimization problem, the convergence speed is not fast enough and easily fall into the local optimum. This paper analyzes the advantages and disadvantages of different mutation operation modes and the influence of the scaling factor and the crossover factor on the optimization performance of the algorithm , A multi-population adaptive differential evolution algorithm is proposed.During the evolutionary process, different populations adopt different mutation operation modes, which is beneficial to the complementarity of different modes, while using the logistic model to adaptively adjust the scaling factor and the crossover factor The algorithm improves the global search ability in the early stage and enhances the local search ability in the later stage.The simulation of the typical test function shows that the proposed algorithm has high computational accuracy and fast convergence.