Open AccessProfiles’ classifier of hot-rolled rolling
Author(s) -
S. M. Belskiy,
V. A. Pimenov,
А. Н. Шкарин
Publication year - 2020
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/971/2/022075
Subject(s) - strips , hot rolled , waviness , flatness (cosmology) , strip steel , transverse plane , cross section (physics) , parallelogram , mathematics , structural engineering , engineering , algorithm , materials science , mechanical engineering , physics , composite material , cosmology , quantum mechanics , hinge
The geometric parameters describing the features of the cross-sectional profile of the hot-rolled strips do not give a complete picture of the flatness acquired by the cold-rolled strips rolled from these strips. An additional analysis showed that there are four characteristic classes of cross-sectional profiles of hot rolled strips that have a significant effect on the shape of the strips during cold rolling, three of which negatively affect the flatness of the cold rolled strips. The cross-sectional profiles of hot-rolled strips with a concave middle part and (or) marginal thickenings lead to the appearance of edge waviness, peak-like cross-sectional profiles cause central warping. Therefore, the actual task is to determine the factual shape of cross-sectional profile. Sixth order polynomials were used to digitalize and parameterize hot-rolled profile. As a result, we developed analytic function of the transverse profile, which keeps important information about its near-edge areas and features in the middle part. To assign a specific cross-sectional profile of a hot-rolled strip to one of four characteristic classes of cross-sections, mathematical software was developed, called a classifier, and implemented with the programming environment R. To classify the profiles of the hot-rolled cross-section according to characteristic classes, a linear discriminant method was used as a machine learning method analysis. The result is an adequate mathematical model for recognizing the shape of the cross-sectional profile.