An active learning hybrid reliability method for positioning accuracy of industrial robots
- PDF / 980,651 Bytes
- 10 Pages / 595.22 x 842 pts (A4) Page_size
- 63 Downloads / 160 Views
DOI 10.1007/s12206-020-0729-8
Journal of Mechanical Science and Technology 34 (8) 2020 Original Article DOI 10.1007/s12206-020-0729-8 Keywords: · Industrial robot · Positioning accuracy · Hybrid reliability analysis · Active learning method · Kriging model
Correspondence to: Dequan Zhang [email protected]
Citation: Zhang, D., Liu, S., Wu, J., Wu, Y., Liu, J. (2020). An active learning hybrid reliability method for positioning accuracy of industrial robots. Journal of Mechanical Science and Technology 34 (8) (2020) ?~?. http://doi.org/10.1007/s12206-020-0729-8
Received February 10th, 2020 Revised
May 13th, 2020
Accepted June 7th, 2020 † Recommended by Editor Ja Choon Koo
© The Korean Society of Mechanical Engineers and Springer-Verlag GmbH Germany, part of Springer Nature 2020
An active learning hybrid reliability method for positioning accuracy of industrial robots Dequan Zhang1, Song Liu1, Jinhui Wu1, Yimin Wu1 and Jie Liu2 1
State Key Laboratory of Reliability and Intelligence of Electrical Equipment, School of Mechanical 2 Engineering, Hebei University of Technology, Tianjin 300401, China, State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body, College of Mechanical and Vehicle Engineering, Hunan University, Changsha 410082, China
Abstract Popsitioning accuracy is an important index for evaluating the capacity of industrial robots. As a mechanism with multi-degree of freedom, the uncertainties of industrial robots are diverse and analyzing the positioning accuracy reliability is time consuming. To improve computation efficiency, a new active learning method based on Kriging model is proposed for hybrid reliability analysis of positioning accuracy with random and interval variables. In this study, the updated samples were selected through U learning function in the vicinity of limit-state function. A new stopping criterion based on expected risk function was exploited to judge whether the accuracy of Kriging model is enough. Two numerical examples and one engineering example were provided to verify the efficiency and accuracy of the proposed method. The results indicate that the proposed method is accurate and efficient. 1. Introduction As mechatronic equipment, industrial robots have significant advantages in terms of repeatability, refinement, intelligence and informatization. By now, industrial robots have become the core equipment in automated production, so are required to have high accuracy and reliability to meet production needs. However, as a serial mechanism with multiple degrees of freedom (DoF), uncertain variables such as link dimension, joint rotation angle and link torsion angle, caused by manufacturing error, material deformation and gear backlash etc., would have a serious impact on the positioning accuracy of industrial robots [1]. Therefore, it is significant to consider the influence of uncertain parameters on the positioning accuracy reliability of industrial robots. Based on the principle of maximum entropy and fractional moments, Pandey and Zhang [2] an
Data Loading...
