2TPR&2TPS并联机器人结构参数辨识

Structural Parametric Identification of 2TPR&2TPS Parallel Robot

并联机器人末端位姿精度对其工作性能影响较大,建立有效的标定算法是提高机器人位姿精度的重要保证。本文以一种2TPR&2TPS并联机构为研究对象,首先对机器人进行运动学分析,采用全微分法得出机器人的误差模型,根据该模型得出机器人结构参数误差与末端位姿误差的量化关系,以及各误差项误差变动对末端位姿误差的影响规律;接着,建立参数辨识模型和标定效果评价函数,验证了参数辨识模型的有效性,再用该模型辨识机器人的结构参数误差;最后,修正运动学模型完成了机器人的误差标定。实验结果显示,标定后机器人的平均位置精度提升68.62%,距离误差均值由7.710 mm降至2.350 mm,精度提升69.52%,实验结果证明本文的标定算法有效。

The end pose accuracy of parallel robots has a significant impact on their working performance,and establishing effective calibration algorithms is an important guarantee for improving the pose accuracy of robots. A 2TPR&2TPS parallel mechanism was taken as the research object. Firstly,the kinematics of the robot was analyzed,and the error model of the robot was obtained by using the total derivative method. According to the model,the quantitative relationship between the structural parameter error of the robot and the end pose error and the influence law of the error changes of each error item on the end pose error was obtained. Subsequently,a parameter identification model was established based on the improved particle swarm optimization algorithm. The effectiveness of the parameter identification model was verified by setting a set of error values for the identified variables,and comparing the identified values with the set values five times. At the same time,a calibration effect evaluation function was established. Finally,the structural parameter error of the robot was identified with the parameter identification model,and the kinematics model of the robot was modified with the identified error value,and the error calibration of the robot was completed. The calibration effect evaluation function established was used to analyze the calibration effect. The experimental results showed that the average position accuracy of the robot after calibration was improved by 68.62%,and the average distance error was reduced from 7.710mm to 2.350mm,with an accuracy improvement of 69.52%. The experimental results proved that the calibration algorithm was effective.