摘要
针对标准鲸鱼优化算法(WOA)在解决无人机航迹规划问题时存在着全局搜索能力不足、收敛速度慢、易陷入局部最优值的问题,提出了一种融合粒子群优化算法的改进鲸鱼算法(PSO-ImWOA)。首先,利用混沌映射对种群进行初始化,使得鲸鱼搜索域的分布更加均匀,引入非线性收敛因子解决收敛速度的问题;接着,将寻优能力强的PSO算法引入到WOA的探索开发阶段,通过动态惯性权重因子来平衡算法全局探索和局部开发能力;最后,变异扰动产生新解,再借助模拟退火算法接受次优解的方式,成功规避了陷入局部最优的困境。仿真结果表明,PSO-ImWOA在航迹规划中具有优越性和有效性。
Aiming at the problems of insufficient global search ability,slow convergence speed and a tendency to fall into local optima in the standard whale optimization algorithm(WOA)in solving the UAV trajectory planning problem,an improved WOA algorithm fusing particle swarm optimization algorithm(PSO-ImWOA)is proposed.Firstly,chaotic mapping is used to initialize the population,which makes the distribution of the whale search domain more uniform,and nonlinear convergence factor is introduced to solve the problem of convergence speed.Then,PSO algorithm,which has a strong optimization capability,is introduced into the exploration and development stages of the WOA,and the dynamic inertia weight factor is used to balance global exploration and local development capabilities of the algorithm.Finally,the mutation perturbation generates a new solution,and then accepts the suboptimal solution with the help of simulated annealing algorithm,which successfully circumvents the dilemma of falling into local optima.The simulation results show the superiority and effectiveness of the improved algorithm in trajectory planning.
作者
刘二林
王梦桥
LIU Erlin;WANG Mengqiao(School of Mechanical Engineering,Lanzhou Jiaotong University,Lanzhou 730070,China)
出处
《传感器与微系统》
北大核心
2026年第4期162-166,共5页
Transducer and Microsystem Technologies
基金
甘肃省科技计划项目(23JRRA868)
兰州市人才创新创业项目(2019-RC-103)。
