Molten iron automatic slagging-off control method based on deep learning

Abstract

The invention provides a molten iron automatic slagging-off control method based on deep learning. The method comprises the following steps: performing feature extraction on a collected ladle liquid level image, and manually labeling to obtain a slag quantity grade for constructing a data set of a deep convolutional neural network; establishing a deep convolutional neural network framework, and performing training optimization on the deep convolutional neural network model by using an Adam algorithm to obtain an optimized network model; constructing factor types through factors influencing molten iron desulphurization slag, selecting the factor types to which the slag quantity grade standard belongs through a k-nearest neighbor method, and obtaining deep convolutional neural network modelsof different factor types according to the steps 1 to 3; and determining the overall slag quantity grade according to the corresponding network model output layer data, and making a corresponding slagging-off action through system judgment according to the model output. According to the method, the on-site image information data can be fully mined, the optimal slagging-off process can be calculated, the model robustness is high, the slagging-off time can be effectively shortened, molten iron waste is reduced, and the production benefits of enterprises are improved.

Description

technical field [0001] The invention relates to the technical field of desulfurization and slag removal of molten iron, in particular to a control method for automatic slag removal of molten iron based on deep learning. Background technique [0002] As steel mills pay more and more attention to energy saving and emission reduction, it is necessary to be efficient and reduce losses in each process section. In the hot metal desulfurization and slag removal process, there is still the phenomenon of hot metal waste and low efficiency. Reducing waste and improving efficiency have become the development goals of all enterprises. In this process, the most important link is the judgment of slag level, slag thickness and slag profile, which determines the final slag removal time and slag removal accuracy. The slag removal time and slag removal accuracy of desulfurization and slag removal determine the waste and efficiency of molten iron in this process section. Therefore, the accura...

AI Technical Summary

Problems solved by technology

The core technology of molten iron slag removal is liquid level image processing and slag volume decision-making. Deep removal will bring out a large amount

Images