Please wait a minute...
浙江大学学报(工学版)
浙江大学学报(工学版)  2021, Vol. 55 Issue (6): 1142-1149    DOI: 10.3785/j.issn.1008-973X.2021.06.015
能源工程、机械工程     
机器人加工系统累积误差逐级闭环优化策略
郝晏(),丁雅斌*(),付津昇
天津大学 机构理论与装备设计教育部重点实验室，天津 300354
Hierarchical closed-loop optimization strategy for cumulative error of robot machining system
Yan HAO(),Ya-bin DING*(),Jin-sheng FU
Key Laboratory of Mechanism Theory and Equipment Design of Ministry of Education, Tianjin University, Tianjin 300354, China
 全文: PDF(1553 KB)   HTML
摘要：

针对机器人加工系统的误差累积问题，提出逐级闭环优化策略. 构建以激光跟踪仪、机器人基坐标系和末端工具坐标系组成的核心闭环，以激光跟踪仪、末端工具坐标系、视觉测量坐标系和工件组成的辅助闭环，以激光跟踪仪、视觉测量坐标系和末端工具坐标系组成的相关性闭环. 基于3个闭环独立优化，构建神经网络模型，以数据驱动的方式融合闭环优化结果，提高系统闭环优化的稳定性. 仿真实验结果表明，利用该方法有效地减小系统累积误差，提高机器人末端工具的定位精度，有助于指导后续的样机实验和加工应用.
关键词： 机器人加工;  定位精度;  累积误差;  闭环优化;  神经网络;  视觉测量    
Abstract:

A hierarchical closed-loop optimization strategy was proposed to solve the problem of cumulative error in robot machining system. A core closed-loop composed of the laser tracker frame, robot base frame and the end tool frame was constructed. An auxiliary closed-loop composed of the laser tracker frame, end tool frame, visual measurement frame and the workpiece was constructed. A correlational closed-loop composed of the laser tracker frame, visual measurement frame and the end tool frame was constructed. Then a neural network model was constructed based on the independent optimization of three closed-loops, and the results of the closed-loops optimization were fused by using a data-driven approach in order to improve the closed-loop optimization stability of the system. Simulation experimental results show that the method can effectively reduce the cumulative error of robot machining system and improve the positioning accuracy of the robot end tool, which is conducive to guide the subsequent prototype experiment and machining application.
Key words: robot machining    positioning accuracy    cumulative error    closed-loop optimization    neural network    visual measurement
收稿日期: 2020-07-03 出版日期: 2021-07-30
CLC:  TH 161  
基金资助: 国家自然科学基金资助项目（51775376）
通讯作者: 丁雅斌     E-mail: hyhaoyan@tju.edu.cn;ybding@tju.edu.cn
作者简介: 郝晏（1996—），女，硕士生，从事机器人加工系统定位误差的研究. orcid.org/0000-0002-5966-2696. E-mail： hyhaoyan@tju.edu.cn
服务　　
把本文推荐给朋友
加入引用管理器
E-mail Alert
作者相关文章　　
郝晏
丁雅斌
付津昇

引用本文:

郝晏,丁雅斌,付津昇. 机器人加工系统累积误差逐级闭环优化策略[J]. 浙江大学学报(工学版), 2021, 55(6): 1142-1149.

Yan HAO,Ya-bin DING,Jin-sheng FU. Hierarchical closed-loop optimization strategy for cumulative error of robot machining system. Journal of ZheJiang University (Engineering Science), 2021, 55(6): 1142-1149.

链接本文:

https://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2021.06.015    或    https://www.zjujournals.com/eng/CN/Y2021/V55/I6/1142

图 1  机器人加工系统
图 2  融合闭环优化结果的全连接神经网络模型
位姿数 平均位置误差 平均角度误差
${\varDelta _{\rm{1}}}$ /mm ${\varDelta _{\rm{2}}}$ /mm Φ /% ${\omega _{\rm{1}}}$ /(°) ${\omega _{\rm{2}}}$ /(°) Φ /%
30 0.076 0.064 15.39 0.116 0.083 28.45
50 0.073 0.053 27.40 0.119 0.089 25.21
70 0.068 0.056 17.65 0.128 0.094 26.56
位姿数 最大位置误差 最大角度误差
${\varDelta _{\rm{3}}}$ /mm ${\varDelta _{\rm{4}}}$ /mm Φ /% ${\omega _{\rm{3}}}$ /(°) ${\omega _{\rm{4}}}$ /(°) Φ /%
30 0.123 0.109 11.38 0.198 0.169 14.65
50 0.105 0.088 16.19 0.190 0.161 15.26
70 0.104 0.098 5.77 0.234 0.185 20.94
表 1  核心闭环优化检验结果
图 3  
图 3  不同机器人位姿的核心闭环优化效果
图 4  样本点分别经过闭环优化和神经网络融合后的误差
图 5  神经网络融合辅助和相关性闭环优化的效果
图 6  样本点优化前、经过闭环优化和神经网络融合后的误差
图 7  神经网络融合后点的误差比优化前减小的百分比
图 8  工件局部及工件上预定的目标点
图 9  机器人末端工具的位置
图 10  机器人末端工具的位置误差
1 CHOI D G, KWAK C H, LEE S Y, et al Structural design and analyses of a fabric-covered wind turbine blade[J]. Advanced Composite Materials, 2019, 28 (6): 607- 623
doi: 10.1080/09243046.2019.1626187
2 DHARMAWARDHANA M, OANCEA G, RATNAWEERA A. A review of STEP-NC compliant CNC systems and possibilities of closed loop manufacturing[C]//　3rd China-Romania Science and Technology Seminar. Brasov: IOP, 2018: 012014.
3 TAO B, ZHAO X W, DING H Mobile-robotic machining for large complex components: a review study[J]. Science China Technological Sciences, 2019, 62 (8): 1388- 1400
doi: 10.1007/s11431-019-9510-1
4 HUANG T, DONG C L, LIU H T, et al. Five-degree-of-freedom hybrid robot with rotational supports: US 9, 943, 967 B2 [P]. 2018-04-17.
5 ZHANG Z Y, DING Y B, HUANG T, et al. A mobile robotic system for large scale manufacturing[C]//　18th International Conference in Manufacturing Research. Belfast: IOS, 2019: 67-74.
6 DETESAN O A, CRISAN A V A theoretical approach on determining the geometrical errors in case of articulated robot structures[J]. Applied Mathematics, Mechanics, and Engineering, 2019, 62 (1): 63- 70
7 HUANG C J, FAROOQ U, LIU H Y, et al A PSO-tuned fuzzy logic system for position tracking of mobile robot[J]. International Journal of Robotics and Automation, 2019, 34 (1): 84- 94
8 QIN Y, PENG C S, KUN Y X, et al A novel loop closure detection approach using simplified structure for low-cost LiDAR[J]. Sensors, 2020, 20 (8): 2299
doi: 10.3390/s20082299
9 LIANG Y Y, WU Z Z, HU J Road side unit location optimization for optimum link flow determination[J]. Compute-Aided Civil and Infrastructure Engineering, 2020, 35 (1): 61- 79
doi: 10.1111/mice.12490
10 JIANG P Y, JIA F, WANG Y Real-time quality monitoring and predicting model based on error propagation networks for multistage machining processes[J]. Journal of Intelligent Manufacturing, 2014, 25 (3): 521- 538
doi: 10.1007/s10845-012-0703-0
11 VASIN V V Modified steepest descent method for nonlinear irregular operator equations[J]. Doklady Mathematics, 2015, 91 (3): 300- 303
doi: 10.1134/S1064562415030187
12 GONCALVES M L N, MENEZES T C Gauss-Newton methods with approximate projections for solving constrained nonlinear least squares problems[J]. Journal of Complexity, 2020, 58: 101459
doi: 10.1016/j.jco.2020.101459
13 XIA K, GAO H, DING L, et al Trajectory tracking control of wheeled mobile manipulator based on fuzzy neural network and extended Kalman filtering[J]. Neural Computing and Applications, 2018, 30 (2): 447- 462
14 CHANG L, NIU X J, LIU T Y, et al GNSS/INS/LiDAR-SLAM integrated navigation system based on graph optimization[J]. Remote Sensing, 2019, 11 (9): 1009
doi: 10.3390/rs11091009
15 SCHMIDHUBER J Deep learning in neural networks: an overview[J]. Neural Networks, 2015, 61: 85- 117
doi: 10.1016/j.neunet.2014.09.003
16 JOUBAIR A, NUBIOLA A, BONEV I Calibration efficiency analysis based on five observability indices and two calibration models for a six-axis industrial robot[J]. SAE International Journal of Aerospace, 2013, 6 (1): 161- 168
doi: 10.4271/2013-01-2117
17 NGUYEN H N, LE P N, KANG H J A new calibration method for enhancing robot position accuracy by combining a robot model-based identification approach and an artificial neural network-based error compensation technique[J]. Advances in Mechanical Engineering, 2019, 11 (1): 1687814018822935
18 NORMAN A R, SCHÖNBERG A, GORLACH I A, et al Validation of iGPS as an external measurement system for cooperative robot positioning[J]. International Journal of Advanced Manufacturing Technology, 2013, 64 (1-4): 427- 446
doi: 10.1007/s00170-012-4004-8
19 RAO G, WANG G L, YANG X D, et al Normal direction measurement and optimization with a dense 3D point cloud in robotic drilling[J]. IEEE/ASME Transactions on Mechatronics, 2017, 23 (3): 986- 996
20 CAO C T, DO V P, LEE B R A novel indirect calibration approach for robot positioning error compensation based on neural network and hand-eye vision[J]. Applied Sciences-Basel, 2019, 9 (9): 1940
doi: 10.3390/app9091940
21 GALETTO M, MASTROGIACOMO L, MAISANO D, et al Cooperative fusion of distributed multi-sensor LVM (large volume metrology) systems[J]. CIRP Annals-Manufacturing Technology, 2015, 64 (1): 483- 486
doi: 10.1016/j.cirp.2015.04.003
22 李瑛, 成芳, 赵志林 采用结构光的大跨度销孔加工精度在线测量[J]. 浙江大学学报: 工学版, 2020, 54 (3): ‏557- 565
LI Ying, CHENG Fang, ZHAO Zhi-lin Machining precision online measurement of large span pin hole using structured light[J]. Journal of Zhejiang University: Engineering Science, 2020, 54 (3): ‏557- 565
23 毕运波, 徐超, 樊新田, 等 基于视觉测量的沉头孔垂直度检测方法[J]. 浙江大学学报: 工学版, 2017, 51 (2): 312- 318
BI Yun-bo, XU Chao, FAN Xin-tian, et al Method of countersink perpendicularity detection using vision measurement[J]. Journal of Zhejiang University: Engineering Science, 2017, 51 (2): 312- 318
[1] 何立,庞善民. 结合年龄监督和人脸先验的语音-人脸图像重建[J]. 浙江大学学报(工学版), 2022, 56(5): 1006-1016.
[2] 王云灏,孙铭会,辛毅,张博宣. 基于压电薄膜传感器的机器人触觉识别系统[J]. 浙江大学学报(工学版), 2022, 56(4): 702-710.
[3] 吴泽康,赵姗,李宏伟,姜懿芮. 遥感图像语义分割空间全局上下文信息网络[J]. 浙江大学学报(工学版), 2022, 56(4): 795-802.
[4] 陈扬钊,袁伟娜. 深度学习辅助上行免调度NOMA多用户检测方法[J]. 浙江大学学报(工学版), 2022, 56(4): 816-822.
[5] 张科文,潘柏松. 考虑非线性模型不确定性的航天器自主交会控制[J]. 浙江大学学报(工学版), 2022, 56(4): 833-842.
[6] 程若然,赵晓丽,周浩军,叶翰辰. 基于深度学习的中文字体风格转换研究综述[J]. 浙江大学学报(工学版), 2022, 56(3): 510-519, 530.
[7] 王婷,朱小飞,唐顾. 基于知识增强的图卷积神经网络的文本分类[J]. 浙江大学学报(工学版), 2022, 56(2): 322-328.
[8] 温佩芝,陈君谋,肖雁南,温雅媛,黄文明. 基于生成式对抗网络和多级小波包卷积网络的水下图像增强算法[J]. 浙江大学学报(工学版), 2022, 56(2): 213-224.
[9] 李广龙,申德荣,聂铁铮,寇月. 数据库外基于多模型的学习式查询优化方法[J]. 浙江大学学报(工学版), 2022, 56(2): 288-296.
[10] 任松,朱倩雯,涂歆玥,邓超,王小书. 基于深度学习的公路隧道衬砌病害识别方法[J]. 浙江大学学报(工学版), 2022, 56(1): 92-99.
[11] 黄发明,潘李含,姚池,周创兵,姜清辉,常志璐. 基于半监督机器学习的滑坡易发性预测建模[J]. 浙江大学学报(工学版), 2021, 55(9): 1705-1713.
[12] 张楠,董红召,佘翊妮. 公交专用道条件下公交车辆轨迹的Seq2Seq预测[J]. 浙江大学学报(工学版), 2021, 55(8): 1482-1489.
[13] 王飞,徐维祥. 基于LSTM神经网络改进的路阻函数模型[J]. 浙江大学学报(工学版), 2021, 55(6): 1065-1071.
[14] 许佳辉,王敬昌,陈岭,吴勇. 基于图神经网络的地表水水质预测模型[J]. 浙江大学学报(工学版), 2021, 55(4): 601-607.
[15] 程鸿,胡佳杰,刘勇,叶远青. 强度传输方程和神经网络融合的三维重构算法[J]. 浙江大学学报(工学版), 2021, 55(4): 658-664.