Rolling process plate convexity prediction method based on support vector machine

Abstract

The invention belongs to the technical field of plate shape prediction methods, and particularly relates to a rolling process plate convexity prediction method based on a support vector machine, whichcomprises the following steps: S1, collecting field data by using a high-precision monitoring device; S2, preprocessing the acquired data; S3, establishing a CS-SVM training model; and S4, carrying out CS-SVM network regression prediction. According to the invention, the CS algorithm is combined with the SVM to predict the convexity of the board; the method has the advantages of few parameters, simplicity in operation, easiness in implementation, random path search, high optimization capability, capability of converging to global optimum and the like; the defects of difficult parameter detection and poor precision in the hot rolling production process are overcome; the result shows that the absolute error of 98.11% prediction convexity is smaller than 4.5 mu m, the prediction precision ishigh, the operation speed is high, a large amount of production data collected on site can be directly programmed on a computer to be put into use, the cost is low, and the popularization capacity ishigh. The method is used for predicting the convexity of the plate in the rolling process.

Description

technical field [0001] The invention belongs to the technical field of plate shape prediction methods, and in particular relates to a support vector machine-based method for predicting plate crown in a rolling process. Background technique [0002] The plate shape refers to the appearance shape of the plate and strip, and is one of the indicators of the quality of the plate and strip product. The plate shape actually includes two aspects: the geometric shape of the strip steel section and the flatness of the strip in the natural state. Therefore, quantitative description of the plate shape involves many items such as convexity, wedge shape, edge weakening, local high point, and flatness. Index, among which the plate convexity is the main factor to describe and measure the hot-rolled plate shape. With the increasing requirements for shape quality, the general shape control methods have been difficult to meet the requirements, resulting in huge economic losses. In addition, ...

AI Technical Summary

Problems solved by technology

With the increasing requirements for shape quality, the general shape control method has been difficult to meet the requirements, resulting in huge economic losses

In addition, during the rolling process of the plate and strip, the crown measuring instrument is generally installed at a position 3 to 5 meters away from the exit side of the final stand of the finishing mill. Compared with the rolling process, the acquisition of the crown measurement value has obvious Time lag seriously affects the control effect

Images