一种基于AEKF的铆接件视觉伺服精确装配方法  

A Visual Servo Precision Assembly Method for Riveting Parts Based on Adaptive Extended Kalman Filtering

作　　者：李宗刚[1,2] 李彦博 焦建军[1,2] 杜亚江[1,2] Li Zonggang;Li Yanbo;Jiao Jianjun;Du Yajiang(School of Mechatronic Engineering,Lanzhou Jiaotong University,Lanzhou 730070,China;Robot Research Institute,Lanzhou Jiaotong University,Lanzhou 730070,China)

机构地区：[1]兰州交通大学机电工程学院,甘肃兰州730070 [2]兰州交通大学机器人研究所,甘肃兰州730070

出　　处：《系统仿真学报》2025年第1期107-118,共12页Journal of System Simulation

基　　金：国家自然科学基金(61663020);甘肃省高等学校产业支撑计划(2022CYZC-33);工业装备结构分析国家重点实验室开放课题(ZG22119)。

摘　　要：针对工业生产中存在多轴孔铆接件因铆钉数量多、铆钉与铆孔间隙小、铆钉分布不规则等特点,致使装配过程约束复杂,装配精度要求高,难以实现铆接工艺智能化以提升装配效率问题,提出一种基于自适应扩展卡尔曼滤波的铆接件视觉伺服精确装配方法。为实现铆接件装配时的高精度定位,在传统扩展卡尔曼滤波的基础上,引入自适应噪声估计器,消除未知环境下的系统噪声对图像雅可比矩阵估计精度的影响,保证视觉伺服过程中图像雅可比矩阵的高精度估计;为保证铆接件装配时视觉伺服运动轨迹平滑稳定,设计滑模控制器,对铆接件进行轨迹跟踪,同时引入最小二乘法对铆接件图像特征深度信息进行实时在线估计,实现铆接件的高精度装配;以6自由度机器人建立仿真模型,结果表明在分布不规则的铆钉中选取4个铆钉的圆心点特征作为控制输入,通过设计的视觉伺服控制器能够完成铆接件的高精度多轴孔装配,提高了铆接工艺中关键工序的智能化水平。Aiming at the problems of multiple peg-in-hole riveting parts in industrial production due to the large number of rivets,small gap between rivets and rivet holes,and irregular rivet distribution,resulting in complex assembly process constraints,high assembly accuracy requirements,and difficulty in realizing intelligent riveting process to improve assembly efficiency,a visual servo accurate assembly method of riveting parts based on adaptive extended Kalman filter is proposed.In order to realize the high-precision positioning of riveted parts assembly,on the basis of the traditional extended Kalman filtering,an adaptive noise estimator is introduced to eliminate the influence of system noise in unknown environment on the estimation accuracy of the image Jacobian matrix,and ensure the high-precision estimation of the image Jacobian matrix in the process of visual servo.In order to ensure the smooth and stable visual servo motion trajectory during rivet assembly,a sliding mode controller is designed to track the trajectory of the riveted parts,and the least squares method is introduced to estimate the image feature depth information of the riveting parts in real time online,so as to realize the high-precision assembly of the rivets.A simulation model is established with a 6-degree-of-freedom robot,and the results show that the center point feature of four rivets is selected as the control input in the irregularly distributed rivets,and the high-precision multiple peg-in-hole assembly of the rivets can be completed through the designed visual servo controller,which improves the intelligence level of the key processes in the riveting process.

关 键 词：铆接 多轴孔装配 自适应扩展卡尔曼滤波 深度在线估计 滑模控制 

分 类 号：TP242.2[自动化与计算机技术—检测技术与自动化装置]