Blast furnace hearth activity evaluation and prediction method and system based on big data

Abstract

The invention relates to a blast furnace hearth activeness evaluation and prediction method and system based on big data. The method comprises the steps that blast furnace hearth activeness application data is obtained based on blast furnace production historical data and data preprocessing; establishing a blast furnace hearth activeness evaluation model based on the blast furnace hearth activeness application data and machine learning, and performing preliminary evaluation on the blast furnace hearth activeness through the evaluation model; correcting the blast furnace hearth activity evaluation model on the basis of blast furnace hearth activity application data and machine learning, and performing final evaluation and grading on the blast furnace hearth activity on the basis of the corrected evaluation model; and based on the blast furnace hearth activity application data, deep learning and self-learning, establishing a blast furnace hearth activity prediction model, and predicting the blast furnace hearth activity through the prediction model. Based on the method, accurate evaluation and accurate prediction of the activity of the blast furnace hearth are realized, and guarantee is provided for high quality, high yield, low consumption and smooth operation of the blast furnace.

Description

technical field [0001] The present application belongs to the technical field of data processing, and in particular relates to a method and system for evaluating and predicting the activity of a blast furnace hearth based on big data. Background technique [0002] The state of the blast furnace hearth has an important influence on the "high quality, low consumption, high yield, longevity and high efficiency" of blast furnace production. For example: high-quality molten iron depends on sufficient coupling reaction between slag and iron in the hearth; fuel injection to reduce coke consumption will increase the "skeleton" load in the hearth; blast furnace operators expect stable and efficient production, and this It is also required that the blast furnace hearth can provide sufficient, stable and evenly distributed heat and reducing gas along the radial and circumferential directions of the hearth, and a large amount of water must be smoothly discharged from the hearth; to be c...

AI Technical Summary

Problems solved by technology

[0003] At present, there are certain difficulties and limitations in the implementation of the blast furnace hearth activity evaluation method based on the slag-iron flow resistance coefficient, such as difficult sampling of coke material column in the hearth, related parameters cannot be directly measured, many model experience coefficients, Poor correlation with blast furnace operation and blast furnace conditions, etc.

The activity of the blast furnace hearth is characterized by complexity, variability, and nonlinearity, and its influencing factors are intricate and time-lag. The evaluation method for the activity of the blast furnace hearth based on temperature data has low data utilization and has not been fully excavated. The valuable information in the blast furnace production data leads to waste of data resources; although the current active state of the hearth can be evaluated, it is impossible to predict the change of the state of the hearth in advance and provide feedback on the operation suggestions of the blast furnace. In addition, the integration degree of the algorithm and mechanism is low, and the verification is insufficient , there is a certain gap with the actual production of the blast furnace

Images