论文部分内容阅读
针对粒子群优化(PSO)算法在解决高维非线性优化类问题时存在易陷入局部最小难以寻求最优解的问题,提出了一种具有局部搜索的参数自适应调整的粒子群算法.其核心思想是利用种群分布信息动态调整算法参数;加入混沌变异机制,增加种群多样性;在算法中加入局部搜索机制加强算法局部搜索能力.对6个基准函数的优化结果表明,改进算法具有较好的优化性能.将其用于优化实际的给水管网案例-汉诺塔管网和纽约管网,并与其它算法的结果进行了对比.实验结果表明该算法具有较好的搜索精度和更快的收敛速度.
Particle Swarm Optimization (PSO) is a particle swarm optimization algorithm with local search parameters adaptively adjusted to solve the problem of high-dimensional non-linear optimization problem easily falling into the local minimum and difficult to find the optimal solution. The core idea is Using the distribution information of the population to dynamically adjust the parameters of the algorithm, adding the chaotic mutation mechanism to increase the population diversity, and adding local search mechanism to the algorithm to enhance the local search ability of the algorithm.The optimization results of the six benchmark functions show that the improved algorithm has better performance It is used to optimize the actual water supply network case - the Hornot tube network and the New York pipe network, and compared with the results of other algorithms.The experimental results show that the algorithm has better search accuracy and faster convergence rate .