Adaptive Learning of Bending Force Presetting Model in a Six-High Cold Rolling Mill

Abstract:

In this paper, adaptive learning method of bending force presetting model in a six-high cold rolling mill is introduced. Adaptive learning coefficient of bending force presetting model is calculated by contrast between measured and model calculated actual bending force, then exponential method is used to modify the adaptive learning coefficient to improve the precision of the bending force presetting model. While calculating model calculated actual bending force, Legendre polynomials are used to convert measured flatness data to quadratic and quartic flatness coefficient, then regulating quantity on the quadratic flatness coefficient of intermediate roll bending force and work roll bending force is determined based on their regulate capability. Practical application shows that precision of the bending force presetting model has improved significantly by adaptive learning.

• Periodical: Advanced Materials Research (Volumes 291-294)
• Pages: 601-605
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.291-294.601
• Online since: July 2011
• Authors: Jin Lan Bai, Jun Sheng Wang
• Keywords: Adaptive Learning, Bending Force Presetting Model, Exponential Smoothing, Flatness Control, Six-High Cold Rolling Mill

References

[1] G.D. Wang: Shape control and shape theory(Metallurgical Industry Press, Beijing 1986). (in Chinese)

[2] Kern P, Mehich F, Schumacher J: Iron and Steel Engineer Vol. 76(1999), p.38.

[3] Liu Y, Lee W H: ISIJ International Vol. 45 (2005), p.1173.

[4] Egan S J, Fryer C A, Lubomirski M S, et al: Iron and Steel Engineer Vol. 76(1999), p.38.

[5] J Yang: Mathematical model of rolling process(Metallurgical Industry Press, Beijing 1992). (in Chinese)