论文部分内容阅读
针对粒子群算法容易陷入局部最优点,收敛较慢等问题,在不增加算法复杂度的前提下,提出了线性变化参数的粒子群优化(LCPPSO)算法.LCPPSO算法通过对粒子的速度更新方式进行调整,采用惯性权重和加速因子c1的值线性递减,c_2线性递增的策略加强算法的收敛能力.通过经典测试函数进行仿真实验,与标准PSO及其他改进的PSO算法进行对比,实验结果表明LCPPSO算法实现更加简单,需要调整的参数更少,不仅提高了收敛速度,也具有更好的跳出局部最优能力.
Particle swarm optimization (LCPPSO) algorithm with linear variation parameters is proposed for particle swarm optimization, which is easy to fall into the local optimal point and slow to converge. Without changing the complexity of the algorithm, LPSPSO algorithm is proposed to update the particle swarm optimization Adjust and adopt the strategy of linear decreasing of inertia weight and accelerating factor c1 and c 2 linear increasing strategy to strengthen the convergence ability of the algorithm.Compared with the standard PSO and other improved PSO algorithms through the classical test function simulation experiment, the experimental results show that the LCPPSO algorithm Achieve more simple, fewer parameters need to be adjusted, not only improves the convergence rate, but also has a better out of the local optimal ability.