CAJ | 학술논문

针对粒子群算法在解决给水管网优化问题时存在容易陷入局部最优的缺点,通过分析粒子的运动轨迹和相似程度,提出一种参数自适应粒子群算法. 该算法利用种群粒子与期望粒子之间相似度的大小,动态调整算法参数,平衡算法全局和局部搜索能力,利用分期变异策略增加种群多样性,保证算法收敛于全局最优值. 将改进算法用于优化汉诺塔管网和纽约管网2个经典的管网案例,证明算法可以有效应用于给水管网这类组合优化问题. 将该算法优化实际的管网改扩建案例,结果表明,所提出的算法具有更好的寻优性能和收敛性能.
침대입자군산법재해결급수관망우화문제시존재용역함입국부최우적결점,통과분석입자적운동궤적화상사정도,제출일충삼수자괄응입자군산법. 해산법이용충군입자여기망입자지간상사도적대소,동태조정산법삼수,평형산법전국화국부수색능력,이용분기변이책략증가충군다양성,보증산법수렴우전국최우치. 장개진산법용우우화한낙탑관망화뉴약관망2개경전적관망안례,증명산법가이유효응용우급수관망저류조합우화문제. 장해산법우화실제적관망개확건안례,결과표명,소제출적산법구유경호적심우성능화수렴성능.
Particle swarm optimization easily falls into a local optimum when solving water supply optimization prob-lems. In order to solve this weakness, by analyzing particle trajectories and the similarity of particles, this paper proposes a parameter adaptive particle swarm optimization ( PAPSO) . By estimating the degree of similarity between particles and expected particles, the algorithm dynamically adjusts parameters and balances the global and local search ability. The algorithm uses the variation strategy of staging to increase the population diversity and ensure that it converges to the global optimum. The tower of Hanoi network and New York network have been optimized by the improved algorithm, and the result shows that the PAPSO algorithm can be effectively applied to the combinato-rial optimization of water supply pipeline networks. The proposed algorithm has been applied to optimize an actual pipe network reconstruction case and the result shows that the algorithm has better optimization and convergence performance.