Assembly Control Parameter Learning for Complex Robotic Assembly Processes
Pages 2526 - 2530
Abstract
Recently robotic technology has been advanced rapidly. There are many robotic applications in manufacturing environments to replace human workers. However there are many unsolved problems in robotic automation. One issue is how to optimize a robotic manufacturing process. To face this challenge, this paper proposes a robot learning method to optimize process control parameters. The system performance including cycle and First Time Through rate can be optimized. Experimental platforms have been developed and experimental results demonstrate the proposed control parameter learning method is very effective compared to other existing methods. Hence the proposed method will make industrial robots more intelligent to meet the modern manufacturing demands in Industry 4.0.
References
[1]
J. Pfrommer, C. Zimmerlingc, J. Liu, L. Kärgerc, F. Henning, and J. Beyerer, “Optimisation of manufacturing process parameters using deep neural networks as surrogate models,” in 51st CIRP Conference on Manufacturing Systems. ScienceDirect, 2018, pp. 426–431. [Online]. Available: https://doi.org/10.1016/j.procir.2018.03.046.
[2]
L. Sudha, R. Dillibabu, S. Srivatsa Srinivas, and A. Annamalai, “Optimization of process parameters in feed manufacturing using artificial neural network,” Computers and electronics in agriculture, vol. 120, pp. 1–6, 2018. [Online]. Available:.
[3]
B. Zhang, “Robotic force control assembly parameter optimization for adaptive production,” in IEEE International Conference on Robotics and Automation, Shanghai, China, 2011.
[4]
S. Sayler and R. Dillmann, “Experience-based optimization of universal manipulation strategies for industrial assembly tasks,” Robotics and Autonomous Systems, vol. 59, no. 11 pp. 882–898, 2011.
[5]
W.-c. Chen, Y.-y. Hsu, L.-f. Hsieh, and P.-h. Tai, “Expert systems with applications a systematic optimization approach for assembly sequence planning using,” Expert Systems With Applications, vol. 37, no. 1, pp. 716–726, 2010.
[6]
Y. P. Aneja and H. Kamoun, “Scheduling of parts and robot activities in a two machine robotic cell,” Computers & Operations Research, vol. 26, no. 4, pp. 297–312, 1999.
[7]
H. Chen, N. Xi, W. Sheng, and Y. Chen, “General framework of optimal tool trajectory planning for free-form surfaces in surface manufacturing,” Journal of Manufacturing Science and Engineering, vol. 127, no. 2, pp. 49–59, Feburary 2005.
[8]
J. Marvel, W. Newman, D. Gravel, G. Zhang, J. Wang, and T. Fuhlbrigge, “Automated learning for parameter optimization of robotic assembly tasks utilizing genetic algorithms,” in IEEE International Conference on Robotics and Biomimetics(ROBIO), feb. 2009, pp. 179–184.
[9]
J. Marvel and W. Newman, “Accelerating robotic assembly parameter optimization through the generation of internal models,” in IEEE International Conference on Technologies for Practical Robot Applications(TePRA), nov. 2009, pp. 42–47.
[10]
G. Hawe and J. Sykulski, “An enhanced probability of improvement utility function for locating pareto optimal solutions,” in 16th Conference on the Computation of Electromagnetic Fields COMPUMAG, vol. 3. RWTH Aachen University, 2007, pp. 965–966, event Dates: 25 ? 28 June 2007. [Online]. Available: http://eprints.soton.ac.ukl/264368/.
[11]
J. Kleijnen, W. Beers, and I. Nieuwenhuyse, “Expected improvement in efficient global optimization through bootstrapped kriging,” Journal of Global Optimization, vol. 54, no. 1, pp. 59–73, 2012. [Online]. Available: https://doi.org/10.1007/s10898-011-9741-y.
[12]
A. Garivier and E. Moulines, “On upper-confidence bound policies for switching bandit problems,” in Proceedings of the 22nd international conference on Algorithmic learning theory, ser. ALT'11. Berlin, Heidelberg: Springer-Verlag, 2011, pp. 174–188.
Index Terms
- Assembly Control Parameter Learning for Complex Robotic Assembly Processes
Index terms have been assigned to the content through auto-classification.
Recommendations
Flexible robotic assembly in dynamic environments
PerMIS '10: Proceedings of the 10th Performance Metrics for Intelligent Systems WorkshopWhile robotic automation has played a key role in the automotive industry and specifically in stamping, welding, material handling and painting over the last 30 years, currently there are no robotic assembly applications in the final assembly of a ...
Robotic assembly: chamferless peg-hole assembly
The peg-in-hole insertion process is the most common task in the robotic/automatic assembly industry. However, the inaccuracy of the assembly robot in positioning the inserted peg into the hole due to the uncertainty of the assembly environment, ...
Automated learning for parameter optimization of robotic assembly tasks utilizing genetic algorithms
ROBIO '09: Proceedings of the 2008 IEEE International Conference on Robotics and BiomimeticsA challenge for automating mechanical assembly is that cumulative uncertainties typically exceed part clearances, which makes conventional position-based tactics unsuccessful. Force-based assembly strategies offer a potential solution, although such ...
Comments
Information & Contributors
Information
Published In
Dec 2018
5858 pages
Copyright © 2018.
Publisher
IEEE Press
Publication History
Published: 12 December 2018
Qualifiers
- Research-article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 13 Jan 2025