A method for processing deviation curve between finishing strip steel stands based on machine vision

Abstract

The invention provides a machine vision-based method for processing deviation curves between finishing strip steel stands, and belongs to the technical field of steel rolling automation. This method uses the binocular line array camera installed on the top of the frame to detect the strip steel. First, extract the strip steel edge from the collected strip steel image, and obtain the edge coordinates of the left and right sides of the strip steel image; then calculate the width of the strip steel. Then calculate the difference between the actual strip width measured by the exit width measuring instrument and the strip width obtained by detection, and form a judgment model through data fitting, and carry out the deviation data corresponding to the width difference exceeding the threshold. Filter, take the previous deviation value as the deviation value of this point. The method calculates the difference between the strip width measured at the detection moment and the actual width, and filters the deviation data corresponding to the width difference data whose difference exceeds a threshold, so as to achieve the purpose of removing noise from the deviation curve.

Description

technical field [0001] The invention relates to the technical field of steel rolling automation, in particular to a machine vision-based method for processing deviation curves between finishing strip steel stands. Background technique [0002] Hot-rolled steel strip is an important steel product, which is widely used in various sectors of the national economy such as construction, bridges, ships, and vehicles. Under the background of product structure adjustment, cost reduction and efficiency increase in the domestic iron and steel industry, the production capacity of products with excess capacity, low technical content and added value has been gradually compressed or withdrawn from major iron and steel manufacturers, while hot-rolled strip steel is constantly changing its product structure. New application areas are constantly being explored in adjustment and quality optimization, and the steel market is gradually developing from cold rolling to hot rolling, which determine...

AI Technical Summary

Problems solved by technology

[0005] Through this system, the strip width data and the strip deviation data can be obtained, and the strip deviation can be displayed in real time. There are many noise points in the offset curve, which affect the judgment and adjustment of the operator, and have a certain degree of influence on the subsequent shape control

[0006] In the current technical publications, the curve fitting method is mostly used for the curve filtering method. This method can fit the observed data through an appropriate curve type, but it can only reflect the general trend of the data, and try to make the curve have no local fluctuations. During the strip rolling process, it is necessary to obtain accurate deviation values ​​for subsequent adjustments, so this method is not suitable for the treatment of deviation curves between finish rolling strip racks

Images