基于NSGA-Ⅱ的串联机器人几何参数公差的多目标优化分配

Multi-objective Optimization Allocation of Geometric Parameter Tolerances for Serial Robots Based on NSGA-Ⅱ

为了提高机器人末端执行器的几何定位精度,在机器人精度的初始设计阶段合理分配几何参数公差,提出了一种带精英策略的快速非支配排序遗传算法(NSGA-Ⅱ)的以成本与精度为目标的多目标公差优化分配方法.以ROKAE XB7型6自由度串联机器人为研究对象,分别基于遗传算法(GA)的最小成本单目标公差优化分配方法和NSGA-Ⅱ的多目标公差优化分配方法对DH(Denavit-Hartenberg)参数的公差优化分配.在精度设计目标和遗传算法参数设置相同的情况下,与基于遗传算法的最小成本的几何参数公差优化分配相比,基于NSGA-Ⅱ的多目标公差优化分配能够给出不同制造成本和不同精度设计要求的一系列最优解,在得到同等制造成本和机器人精度的情况下,公差的容错松弛率相对较高,参数公差优化分配的结果更优.

In order to improve the geometric positioning accuracy of robot end‑effectors and allocate geometric parameter tolerances reasonably in the initial design stage of robot precision,a multi‑objective tolerance optimization allocation method based on fast non‑dominated sorting genetic algorithm(NSGA-Ⅱ)with elite strategy was proposed.ROKAE XB76-DOF serial robot was studied,and the minimum cost single‑objective tolerance optimal allocation based on genetic algorithm(GA)and NSGA-Ⅱ multi‑objective tolerance optimal allocation method were used to optimize the tolerance allocation of DH(Denavit‑Hartenberg)parameters.In the case of the same precision design objectives and genetic algorithm parameter settings,compared with the minimum cost geometric parameter tolerance optimization allocation based on the genetic algorithm,the multi‑objective optimal allocation based on NSGA-Ⅱ could provide a series of optimal solutions with different manufacturing costs and different precision design requirements.The relaxation rate of tolerance is relatively high,and the result of parameter tolerance optimization is better.