论文部分内容阅读
针对基本PSO算法在全局优化中易陷入局部极值和收敛精度低的不足,分析了基本PSO算法早熟收敛的原因,提出具有自适应邻域探测机制的改进型粒子群优化(ANE-PSO)算法.该算法在进化过程中以概率总体递减的方式,选择部分粒子对最佳位置按半径总体递减的规则进行邻域探测,并引入速度变异算子,提高种群的多样性,增强了算法的全局搜索能力.并证明它依概率1收敛到全局最优解.通过与其它三个改进算法比较,结果表明ANE-PSO具有较好的全局搜索能力,收敛速度较快,稳定性较好,且没有增加时间复杂度,较有效的避免了早熟收敛问题.
Aiming at the shortcomings of the basic PSO algorithm such as easy falling into the local optimum and low convergence accuracy in the global optimization, the reason of the premature convergence of the basic PSO algorithm is analyzed. An improved particle swarm optimization (ANE-PSO) algorithm with adaptive neighborhood detection is proposed In the process of evolution, the algorithm selects part of the particles to detect the neighborhood by the rule that the best position declines by the radius, and introduces the velocity mutation operator to improve the diversity of the population and enhance the overall situation of the algorithm Search ability and proves that it converges to the global optimal solution according to probability 1. Compared with the other three improved algorithms, the results show that ANE-PSO has better global search ability, faster convergence, better stability, and no Increase the time complexity, and avoid the premature convergence problem more effectively.