论文部分内容阅读
针对标准人工鱼群优化算法在迭代过程中易陷入局部最优和后期收敛速度慢的问题,提出一种基于R★ssler混沌改进的自适应人工鱼群算法。该算法利用混沌序列获得均匀初始化的种群,并在人工鱼群陷入局部极值时对其进行混沌变异操作,增加鱼群的多样性,同时根据食物浓度自适应调节人工鱼步长,提高收敛速度。仿真实验表明,该算法能够有效避免早熟问题,并且具有较快的收敛速度。
Aiming at the problem that the standard artificial fish swarm optimization algorithm is easy to fall into the local optimum during the iterative process and has a slow convergence rate at the later stage, an adaptive artificial fish swarm algorithm based on improved R ★ ssler chaos is proposed. The algorithm uses a chaotic sequence to obtain a uniformly initialized population. When the artificial fish swarm reaches a local extreme, the algorithm performs chaotic mutation operation to increase the diversity of the fish. At the same time, the artificial fish step size is adaptively adjusted according to the food concentration to improve the convergence rate . Simulation results show that this algorithm can effectively avoid premature problems and has a faster convergence rate.