摘要
针对粒子群优化(PSO)算法应用于自动导引车(AGV)路径规划时迭代次数较多、收敛速度慢以及生成路径转弯次数多,影响生产效率等问题,提出一种具有遗传因子的粒子群优化算法。引入自适应惯性权重提高算法收敛性,借鉴遗传算法交叉、变异的思想对粒子进行交叉、变异操作增加种群多样性,有效减少算法迭代次数、提高收敛速度,使算法快速产生全局最优解。在算法适应度函数中引入转弯次数因素,减少路径转弯次数,降低路径复杂度。MATLAB仿真实验结果表明:优化后的PSO算法可以有效降低迭代次数,提高收敛速度,简化路径复杂度,得到全局最优路径。
Aiming at the problems of many iterations,slow convergence rate and many times of generating path turning while particle swarm optimization( PSO) algorithm is applied to AGV path planning,which affects production efficiency,an improved PSO algorithm with genetic factor is proposed. In the algorithm,the adaptive inertia weight is introduced to improve the convergence of the algorithm. The idea of crossover and mutation of the genetic algorithm is used to cross and the mutation operation on the particles to increase the diversity of the population,effectively reduce the number of iterations of the algorithm and improve the convergence speed,so that the algorithm can quickly generate the global optimal solution. The turning number factor is introduced in the algorithm fitness function to reduce the number of path turning and reduce the path complexity. MATLAB simulation results show that the optimized PSO algorithm can effectively reduce the number of iterations,improve the convergence speed,simplify the path complexity,and obtain the global optimal path.
作者
丁承君
王鑫
冯玉伯
张家梁
DING Chengjun;WANG Xin;FENG Yubo;ZHANG Jialiang(School of Mechanical Engineering,Hebei University of Technology,Tianjin 300132,China)
出处
《传感器与微系统》
CSCD
2020年第8期123-126,共4页
Transducer and Microsystem Technologies
基金
河北省科技计划资助项目(14214902D)。
关键词
自动导引车
粒子群优化(PSO)算法
路径规划
转弯次数
automated guided vehicle(AGV)
particle swarm optimization(PSO)algorithm
path planning
turn times
