摘要
针对基本蚁群算法在求解过程中容易出现收敛时间过长和陷入局部最优的不足,提出了一种动态自适应的蚁群算法(DSACO),在算法DSACO中改进了算法的重要参数,当算法疑似陷入局部最优时,通过自适应调整参数来提高全局最优解的求解质量和信息量强度;最后在煤炭运输问题上进行实验仿真,结果表明,DSACO算法与基本蚁群算法相比较,加快了收敛速度,提高了全局寻优能力。
Aiming at these disadvantages which are the algorithm is easily got into long convergence time and trapped in a local optimum in the basic ant colony algorithm, this essay presents a dynamic self-adaptive ant colony optimization algorithm （DSACO）. The DSACO algorithm sets-up and affects the algorithm performance parameters （α, β and p） and pheromone values （r）. When the algorithm traps into a local optimum. This algorithm improves the global optimum solution of quality and the strength of pheromone by the adaptive adjustment of parameters when the algorithm traps into a local optimum. Simulation experiment about the question of coal transportation shows that the algorithm, compared with basic ant colony algorithm, enhanced the convergence speed and global optimization asoects.
出处
《煤矿机械》
北大核心
2012年第7期208-209,共2页
Coal Mine Machinery
基金
华北科技学院科技基金项目(2011B032)
关键词
蚁群算法
信息素
自适应
煤炭运输
ant colony algorithm
pheromones
self-adaptive
coal transportation
