A Reverse Approach in Optimizing Pass Parameters

Jian Hua Hu; Yuan Hua Shuang

doi:10.4028/www.scientific.net/AMR.113-116.1707

Paper Titles

Hydrometallurgical Process for Recovery of Lithium and Cobalt from Spent Lithium-Ion Secondary Batteries
p.1688

Study on Wood Carbon Sequestration Based on Micro-Characteristics of Wood
p.1693

Utilization of CMC and PVA for the Preparation of Superabsorbent Resin
p.1697

Study on Rapid Startup of Short Cut Nitrification and Denitrification
p.1702

A Reverse Approach in Optimizing Pass Parameters
p.1707

Preparation of Hydrophobic CaCO₃-Wood Composite In Situ
p.1712

Optimization Conditions of Modified Activated Carbon and the Adsorption of Phenol
p.1716

The Preparation of WPC for SLS Rapid Prototyping and Manufacturing
p.1722

Cleaner Dehairing Technology for Goatskins: Effects of Hydrosulfide and Peroxide on Enzyme Unhairing
p.1726

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 113-116A Reverse Approach in Optimizing Pass Parameters

A Reverse Approach in Optimizing Pass Parameters

Abstract:

A method combines a back propagation neural networks (BPNN) with the data obtained using finite element method (FEM) is introduced in this paper as an approach to solve reverse problems. This paper presents the feasibility of this approach. FEM results are used to train the BPNN. Inputs of the network are associated with dimension deviation values of the steel pipe, and outputs correspond to its pass parameters. Training of the network ensures low error and good convergence of the learning process. At last, a group of optimal pass parameters are obtained, and reliability and accuracy of the parameters are verified by FEM simulation.

You might also be interested in these eBooks

Environment Materials and Environment Management, EMEM2010

View Preview

Info:

Periodical:

Advanced Materials Research (Volumes 113-116)

Pages:

1707-1711

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.113-116.1707

Citation:

Cite this paper

Online since:

June 2010

Authors:

Jian Hua Hu, Yuan Hua Shuang

Keywords:

BP Neural Network (BPNN), Finite Element Model (FEM), Reverse Problem

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] Zhao Zhi-ye. Metal Plastic Deformation and Rolling Theory[M]. Beijing: Metallurgical Industry Press, 1999 (in Chinese).

Google Scholar

[2] Li Sheng-zhi , Zhu Cheng-xu. Analysis of Interstand Tension and Deformation of Steel Tube in Stretch Reducing Mill [J]. Journal of East China Institute of Metallurgy, 1993, 10(2): 26 (in Chinese).

Google Scholar

[3] Hambli, A. Potiron, Finite element model for tool wear prediction in blanking process, The Ninth International Conference on Sheet Metal , Leuven, Belgium, 2-4 April (2001).

Google Scholar

[4] Meixing Ji, Sstish Kini and Rajiv Shivpuri, Inverse Engineering Approach in Selecting Process Parameters for Optimum Bar Rolling, 44th MWSP Conference Proceedings, Vol. XL, 2002, 663-672.

Google Scholar

[5] H.C.W. Lau,A. Ning K.F. Pun K.S. Chin, Neural networks for dimensional control of molded parts based on a reverse process model, Joural of Materials Processing Technology 117(2003) 89-96.

DOI: 10.1016/s0924-0136(01)01086-x

Google Scholar

[6] P.D. Wasserman, Neural Computing Theory and Practicek, Van N ostrand Reinhold, New York, (1989).

Google Scholar

[7] I. Alecsander,H. Morton, An Introduction to Neural Computing, Thomson, (2005).

Google Scholar

[8] S. Haykin, Neural Network, A Comprehensive Foundation, 2nd Edition, Prentice-Hall, Englewood Cliffs. NJ. (2004).

Google Scholar