Hot continuous rolling strip steel width prediction method based on cooperation of principal component analysis and random forest

Abstract

The invention provides a hot continuous rolling strip steel width prediction method based on principal component analysis in cooperation with a random forest, and relates to the technical field of hot continuous rolling process control. The method comprises the following steps: firstly, determining an arrangement form of hot continuous rolling production line equipment, determining a temperature system, rolling mill equipment parameters and rolling boundary conditions; then according to characteristics of a production line, determining actually measured data which needs to be acquired and is about steel grade change, specification change and width of a first steel block after roller change; carrying out standardization processing on the acquired actual measurement data; carrying out dimension reduction processing and feature selection on the standardized data set by adopting a principal component analysis method, and determining an input variable of a random forest width prediction model for strip steel width prediction; dividing the data set after dimension reduction processing and feature selection based on principal component analysis into a training set and a test set according to a certain proportion, and constructing and training a random forest width prediction model according to a random forest algorithm; finally evaluating the prediction precision of the random forest width prediction model.

Description

technical field [0001] The invention relates to the technical field of hot continuous rolling rolling process control, in particular to a hot continuous rolling strip width prediction method based on principal component analysis and random forest. Background technique [0002] Strip width is an extremely important quality index in addition to thickness and shape in the hot strip rolling process. Every time the width deviation is reduced by 1mm, the yield can be increased by 0.1%, and the width accuracy is seriously affected. It affects the quality and output of strip steel products. Good width accuracy can not only improve the yield of strip steel products and reduce the loss rate of strips, but also help hot rolling users and subsequent processes to create excellent production conditions. Accurate width control is of great significance to the product quality of strip steel. Improving and seeking a more perfect width control strategy to improve the precision of strip steel ...

AI Technical Summary

Problems solved by technology

However, with the rapid development of artificial intelligence technology, the current width prediction model can no longer meet the current productivity development and the requirements of downstream enterprises for width dimension accuracy. The main reason is that the width control process has characteristics such as nonlinearity, complexity, and coupling, and artificial Although the neural network has been widely used in the control and prediction of strip width, it still has disadvantages such as slow convergence speed, large randomness in network structure selection, easy to fall into local minimum, and limited network generalization ability, which limits the accuracy of width prediction. further improvement of

Images