Research on the Key Technologies of Intelligent Control for Cap-Shape Bending of Sheet Metal

Abstract:

The blueprint for an intelligent control system of cap-shape bending has been advanced in this paper using neural network technology, aiming at an accurate control of bending springback, the prominent problem during the forming process for the cap-shape bending of sheet metal. The feed-forward neural network of real-time identification for material performance parameters and the friction coefficient have been established. The neural network identifies the parameters for real-time needed material performance, which utilizes the measurability of the physical quantities, and predicts the parameters for optimum technology, so a satisfied accuracy of convergence has been achieved. The intelligent control experimentation system of cap-shape bending has been established, the validity of which has been tested for four kinds of materials. The result of the tests proves the feasibility of the blueprint of the intelligent control system.

• Periodical: Advanced Materials Research (Volumes 239-242)
• Pages: 2867-2872
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.239-242.2867
• Online since: May 2011
• Authors: Hong Lei Sun, Chun Jian Su, Rui Xue Zhai
• Keywords: Cap-Shape Bending, Intelligent Control, Neural Network (NN), Real-time Identification, Springback

References

[1] D. Schmockel, M. Beth: Springback Reduction in Draw-bending Process of Sheet Metals [J]. Annls of the CiRP Vol.42,2002(1):234-237

DOI: 10.1016/s0007-8506(07)62457-3

[2] M. Sunseri, J. Cao, A. P. Karafillis, etc: Accommodation of Springback Error in Channel Forming using Active Binder Force Control: Numerical Simulations and Experiments [J]. Journal of Engineering Materials and Technology, Transactions of the ASME, 1996 (118): 426-435

DOI: 10.1115/1.2806830

[3] C. J. Su: Research on The Rule of Springback and Intelligent Control Technologies for Multangular-Shape Single Bending[D]. Qinhuangdao: Yanshan University, 2008. (In Chinese)

[4] C. J. Su, J. Zhao, Y. P. Guan, R. Ma: China Mechanical Engineering [J], 2008, (3): 351-354 (In Chinese)

[5] G. F. Yin, Y. Q. Wang, X. G. Sun: China Mechanical Engineering [J], 2004, 15(24): 2207-2210. (In Chinese)

[6] F. Q. Wang: Study on the key technologies of intelligent control for rectangular box deep drawing [D]. Qinhuangdao: Yanshan University, 2003.(In Chinese)

[7] Carpenter W C, Hoffman M E: Selecting the architecture of a class of back-propagation neural networks used as approximator [J]. Artificial Intelligence for Engineering Design, Analysis and Manufacturing: AIEDAM, 1997, 11(1): 33-44.

DOI: 10.1017/s0890060400001827

[8] Aberbour M, Mehrez H: Architecture and design methodology of the EBF-DDA neural network [C]. IN: Proceedings IEEE International Symposium on Circuits and Systems, 1998, 3: 199-202.

DOI: 10.1109/iscas.1998.703974

[9] Hagen M T, Menhaj M B: Training feed forward networks with the Levenberg-Marquardt algorithm [J]. IEEE Trans on Neural Networks, 1994, 5(6): 989-993.

DOI: 10.1109/72.329697

[10] X. L. Liu, S. C. Song, H. G. Shi, F. J. Shang: Materials Science and Technology [J]. 2006, 14(1): 63-65. (In Chinese)

[11] Y. X. Yuan, W. Y. Sun: Optimization Theory and Methods[M]. Beijing: Science Press,1997.

[12] Y. Y. Zhang, S. B. Wang: Journal of Fuzhou University(Natural Sciences Edtion) [J], 2001,29(1): 43-46. (In Chinese)

[13] Z. X. Li, X. S. Zheng: Material Science and Technology[J],8(4): 108-111(In Chinese)

[14] X.Wen: MATLAB Neural Network Application Design[M], Beijing: Science Press, 2000, 44-59 (In Chinese)