Proceedings of the 2016 3rd International Conference on Mechatronics and Information Technology

Research On Springback Control Based On GRNN-ES

Authors
Zhaohu Deng
Corresponding Author
Zhaohu Deng
Available Online April 2016.
DOI
10.2991/icmit-16.2016.80How to use a DOI?
Keywords
springback control; ANN; ES; optimization
Abstract

Springback is a kind of formation defect in punch machining. It can be decreased by adjusting the processing parameters. In this paper it put forward to optimize the parameters with response surface method. Firstly it built an artificial neural network for mapping the relation between the parameters and springback. Then it optimized the neural network model with evolution strategy. At last it would get the optimum of parameters after optimization. In order to get more precise parameters it modified the ANN and ES in this paper. Then it took a trial to certify the method. The results showed that the method proposed in this paper can decrease the springback effectively.

Copyright
© 2016, the Authors. Published by Atlantis Press.
Open Access
This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

Volume Title
Proceedings of the 2016 3rd International Conference on Mechatronics and Information Technology
Series
Advances in Computer Science Research
Publication Date
April 2016
ISBN
978-94-6252-184-1
ISSN
2352-538X
DOI
10.2991/icmit-16.2016.80How to use a DOI?
Copyright
© 2016, the Authors. Published by Atlantis Press.
Open Access
This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Cite this article

TY  - CONF
AU  - Zhaohu Deng
PY  - 2016/04
DA  - 2016/04
TI  - Research On Springback Control Based On GRNN-ES
BT  - Proceedings of the 2016 3rd International Conference on Mechatronics and Information Technology
PB  - Atlantis Press
SP  - 447
EP  - 450
SN  - 2352-538X
UR  - https://doi.org/10.2991/icmit-16.2016.80
DO  - 10.2991/icmit-16.2016.80
ID  - Deng2016/04
ER  -