机械臂空间轨迹的非支配扰动粒子群算法优化  

Manipulator Joint Space Trajectory Optimization Based on Non-Dominated Disturbed PSO

作　　者：杜柯[1] 刘祎[2] DU Ke;LIU Yi(Guang’an Vocational and Technical College,Sichuan Guang’an 638000,China;Suqian College,Jiangsu Suqian 223800,China)

机构地区：[1]广安职业技术学院,四川广安638000 [2]宿迁学院,江苏宿迁223800

出　　处：《机械设计与制造》2024年第10期315-319,323,共6页Machinery Design & Manufacture

基　　金：2019年度市级指导性科技计划项目(Z2019108)。

摘　　要：为了减少机械臂工作时间同时减小机械臂的运动冲击,提出了基于非支配排序扰动粒子群算法的机械臂轨迹多目标优化方法。以那智MZ04机械臂为研究对象,对机械臂空间轨迹规划问题进行描述,并建立了时间最少、冲击最小的多目标优化模型。在粒子群算法中融入了扰动策略和非支配排序策略,扰动策略使粒子不再向固定的种群最优学习,而是向种群最优邻域学习,有效维持了粒子多样性并提高了算法优化能力;将非支配排序扰动粒子群算法应用于机械臂轨迹规划,其Pareto前沿解优于非支配排序粒子群算法。将非支配扰动粒子群算法和非支配粒子群算法的时间、冲击等权重解进行比较可以看出,非支配扰动粒子群算法规划路径的时间和冲击均优于非支配粒子群算法,且轨迹连续、平滑,运动轨迹参数在约束范围内,证明了非支配扰动粒子群算法在机械臂轨迹规划中的有效性。In order to reduce the working time of the manipulator and the motion impact of the manipulator,a multi-objective trajectory optimization method based on non-dominated sorting perturbation particle swarm optimization algorithm is proposed.Taking the Nazhi MZ04 manipulator as the research object,the space trajectory planning problem of the manipulator is described,and the multi-objective optimization model with the least time and the least impact is established.Disturbance strategy and non-dominated sorting strategy are integrated into particle swarm optimization.Disturbance strategy makes particles learn from the optimal neighborhood instead of the fixed population,which effectively maintains the diversity of particles and improves the optimization ability of the algorithm.The results show that the Pareto frontier solution of the PSO algorithm is better than that of the PSO algorithm.Comparing the time,impact and other weight solutions of non-dominated perturbed particle swarm optimization algorithm and non-dominated particle swarm optimization algorithm,it can be seen that the time and impact of path planning of non-dominated perturbed particle swarm optimization algorithm are better than that of non-dominated particle swarm optimization algorithm,and the trajectory is continuous and smooth,and the trajectory parameters are within the constraint range,It is proved that the non-dominated perturbed particle swarm optimization algorithm is effective in trajectory planning of manipulator.

关 键 词：机械臂轨迹 非支配扰动粒子群算法 最优粒子邻域 多目标优化 

分 类 号：TH16[机械工程—机械制造及自动化] TP241.3[自动化与计算机技术—检测技术与自动化装置]