Online Modeling and Parameter Optimization Method for Robotic Complex Assembly Process of Gear

doi:10.3901/JME.2021.13.124

Abstract

Abstract: Taking the gear assembly station of the retarder assembly line as a research background, an online modeling learning and parameter optimization method for complex robot assembly process is proposed to solve the problems of low assembly success rate and low efficiency using current offline methods. For the complex and changeable robotic assembly process of gear, the dynamic model of contact states and robot motion is established based on Gaussian process regression (GPR). A new particle swarm optimization algorithm based on generative adversarial algorithm (GAPSO) is proposed for online learning to generate optimization strategy of assembly key parameters. Support vector data description (SVDD) is utilized to detect the new assembly data. The method finally realizes the online modeling and parameter optimization of the assembly process. Experiment results of the gear and spline shaft show that the GAPSO-GPR method is superior to the manual and offline methods in assembly success rate and efficiency, and can be used for online assembly of gears with different batches and specifications, which can meet the actual production demand of the retarder assembly line. Key words:industrial robots; gear assembly; online learning; improved particle swarm optimization; Gaussian process regression

Key words: industrial robots, gear assembly, online learning, improved particle swarm optimization, Gaussian process regression

CLC Number:

TP242

LIU Dong, YUAN Liheng, CONG Ming. Online Modeling and Parameter Optimization Method for Robotic Complex Assembly Process of Gear[J]. Journal of Mechanical Engineering, 2021, 57(13): 124-131.

References

[1] ZHANG B, GRAVEL D, ZHANG G, et al. Robotic force control assembly parameter optimization for adaptive production[C]//IEEE International Conference on Robotics and Automation, May, 9-13, 2011, Shanghai, China. New York:IEEE, 2011:464-469.
[2] LI B, CHEN H, JIN T. Industrial robotic assembly process modeling using support vector regression[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems, September, 14-18, 2014, Chicago, USA. New York:IEEE, 2014:4334-4339.
[3] MARVEL J A, NEWMAN W S, GRAVEL D P, et al. Automated learning for parameter optimization of robotic assembly tasks utilizing genetic algorithms[C]//IEEE International Conference on Robotics and Biomimetics, December, 18-22, 2009, Guilin, China. New York:IEEE, 2009:179-184.
[4] IBRAHIM J, PLAPPER P. Contact-state modeling of robotic assembly tasks using Gaussian mixture models[J]. Procedia Cirp, 2014, 23:229-234.
[5] 董悫, 张立建, 易旺民, 等. 基于动力学前馈的空间机器人多销孔装配力柔顺控制[J]. 机械工程学报, 2019, 55(4):207-217. DONG Que, ZHANG Lijian, YI Wangmin, et al. Force compliance control of multi-peg-in-hole assembling by space robot based on dynamic feedforward[J]. Journal of Mechanical Engineering, 2019, 55(4):207-217.
[6] GRUENDLING T, GUILHAUS M, CHRISTOPHER B K. Design of experiment (DoE) as a tool for the optimization of source conditions in SEC-ESI-MS of functional synthetic polymers synthesized via ATRP[J]. Macromolecular Rapid Communications, 2009, 30(8):589-597.
[7] DIETRICH F, BUCHHOLZ D, WOBBE F, et al. On contact models for assembly tasks:Experimental investigation beyond the peg-in-hole problem on the example of force-torque maps[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems, October, 18-22, 2010, Taipei, Taiwan, China. New York:IEEE, 2010:2313-2318.
[8] CHEN H, XU J, ZHANG B, et al. Improved parameter optimization method for complex assembly process in robotic manufacturing[J]. Industrial Robot An International Journal, 2017, 44(1):21-27.
[9] 张思思, 李凤鸣, 杨旭亭, 等. 基于接触状态感知发育的机器人柔性装配方法[J/OL]. 控制与决策, [2021-02-22].https://doi.org/10.13195/j.kzyjc.2019.1079. ZHANG Sisi, LI Fengming, YANG Xuting, et al. Flexible assembly method based on contact state perception development[J/OL]. Control and Decision, [2021-02-22]. https://doi.org/10.13195/j.kzyjc.2019.1079.
[10] SCHERZINGER S, RÖNNAU A, DILLMANN R. Contact skill imitation learning for robot-independent assembly programming[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems, November, 4-8, 2019, Macau, China. New York:IEEE, 2019:4309-4316.
[11] LI F, JIANG Q, ZHANG S, et al. Robot skill acquisition in assembly process using deep reinforcement learning[J]. Neurocomputing, 2019, 345:92-102.
[12] 孟少华, 胡瑞钦, 张立建, 等. 一种基于机器人的航天器大型部件自主装配方法[J]. 机器人, 2018, 40(1):81-88. MENG Shaohua, HU Ruiqin, ZHANG Lijian, et al. A method of autonomous assembly of large spacecraft components using robot[J]. Robot, 2018, 40(1):81-88.
[13] 季旭全, 王君臣, 赵江地, 等. 基于机器人与视觉引导的星载设备智能装配方法[J]. 机械工程学报, 2018, 54(23):63-72. JI Xuquan, WANG Junchen, ZHAO Jiangdi, et al. Intelligent robotic assembly method of spaceborne equipment based on visual guidance[J]. Journal of Mechanical Engineering, 2018, 54(23):63-72.
[14] RASMUSSEN C E. Gaussian processes in machine learning[C]//Summer School on Machine Learning, February, 2-14, 2003. Canberra, Australia. Berlin:Springer, 2003:63-71.
[15] GOODFELLOW I, POUGET-ABADIE J, MIRZA M, et al. Generative adversarial nets[C]//Proceeding of the Conference and Workshop on Neural Information Processing System, December, 8-13, 2014, Montreal, Canada. New York:IEEE, 2014:2672-2680.
[16] CHENG R, JIN Y. A competitive swarm optimizer for large scale optimization[J]. IEEE Transactions on Cybernetics, 2015, 45(2):191-204.
[17] PRICE K, STORN R M, LAMPINEN J A. Differential evolution:a practical approach to global optimization[M]. Berlin:Springer Science and Business Media, 2006.
[18] WANG H, LI H, LIU Y, et al. Opposition-based particle swarm algorithm with Cauchy mutation[C]//IEEE Congress on Evolutionary Computation, September, 25-28, 2007, Singapore. New York:IEEE, 2007:4750-4756.
[19] ZHOU J, FANG W, WU X, et al. An opposition-based learning competitive particle swarm optimizer[C]//IEEE Congress on Evolutionary Computation, July, 24-29, 2016, Vancouver, Canada. New York:IEEE, 2016:515-521.
[20] 夏学文, 刘经南, 高柯夫, 等. 具备反向学习和局部学习能力的粒子群算法[J]. 计算机学报, 2015, 38(7):1397-1407. XIA Xuewen, LIU Jingnan, GAO Kefu, et al. Particle swarm optimization algorithm with reverse-learning and local-learning behavior[J]. Journal of Computer Science and Technology, 2015, 38(7):1397-1407.
[21] TAX D M J, DUIN R P W, Support vector domain description[J]. Pattern Recognition, 1999, 20(6):1191-1199.