JIA Chunyu
,
SHAN Xiuying
,
LIU Hongmin
,
NIU Zhaoping
钢铁研究学报(英文版)
For the problems occurring in a least square method model, a fuzzy model, and a neural network model for flatness pattern recognition, a fuzzy neural network model for flatness pattern recognition with only threeinput and threeoutput signals was proposed with Legendre orthodoxy polynomial as basic pattern, based on fuzzy logic expert experiential knowledge and geneticBP hybrid optimization algorithm. The model not only had definite physical meanings in its inner nodes, but also had strong selfadaptability, antiinterference ability, high recognition precision, and high velocity, thereby meeting the demand of highprecision flatness control for cold strip mill and providing a convenient, practical, and novel method for flatness pattern recognition.
关键词:
flatness;pattern recognition;Legendre orthodoxy polynomial;geneticBP algorithm;fuzzy neural network
WANG Xuesong
,
PENG Yan
,
XU Lipu
,
LIU Hongmin
钢铁研究学报(英文版)
According to the character of the deformation zone on pair cross rolls, which is different from the regular 4-high mill, there are longitudinal and transverse two-way shear deformation in the deformation zone, the character of metal particles flowing velocity is more complicated than normal rolling. Comprehensive influences of normal stress and shear stress in rolling direction, width direction and thickness direction are considered. Establish the rolling force calculation model of PC hot strip mills. After the longitudinal and transverse discretization of deformation zone, the longitudinal and transverse distribution of rolling force is worked out by the differential method, then calculate total rolling force. Calculated results are verified by experimental data.
关键词:
PC rolling mill;rolling force;differential method
