Intelligent metallurgical coke prediction method combined with coke oven heating schedule parameters

Abstract

The invention discloses an intelligent metallurgical coke prediction method combined with coke oven heating schedule parameters. The method comprises the following steps: 1, determining target variables as main performance indexes of coke, wherein the main performance indexes comprise Ad ash content, St,d sulfur content, M10 abrasive resistance, M40 crushing strength, CRI reactivity and CSR post-reaction strength; 2, determining each characteristic variable; 3, constructing an industrial big data platform; 4, enabling the big data platform to realize the extraction and storage of coke quality data; 5, selecting a plurality of groups of data from the collected data for training a gradient enhanced tree regression model to obtain six coke quality index feature importance evaluation indexes; 6, sorting the main factors influencing each quality index of the coke, completing analysis of the factors influencing the quality of the coke, constructing a multilayer neural network model, and predicting the quality of the coke. The invention provides a brand-new means and a brand-new method for optimizing the proportion of the blended coal for coking engineers.

Description

technical field [0001] The invention relates to the technical field of coking coal blending production, in particular to an intelligent metallurgical coke prediction method combined with coke oven heating system parameters. Background technique [0002] Metallurgical coke is the most important basic raw material in blast furnace smelting. It is the heat source, reducing agent, material column skeleton and penetrating agent in blast furnace smelting production, and it is also the most important adjustment means in the blast furnace production process. In recent years, with the development and progress of blast furnace smelting technology, especially the rapid development of large-scale blast furnace volume, high blast temperature technology and blast oxygen-enriched coal injection technology, coke is used as the skeleton of the blast furnace inner material column to ensure the ventilation and permeability of the blast furnace. Liquid effect is more prominent. The quality of ...

AI Technical Summary

Problems solved by technology

[0004] In view of this, researchers at home and abroad have proposed various construction methods for coke-coal blending ratio optimization models, and the models built are also quite different. The coking process and coking operating conditions of each coking enterprise are different from each other, so the existing models cannot directly meet the actual production of the enterprise, and do not have the characteristics of general applicability

The current coal blending technology models focus on the impact of the quality of a single coking coal on metallurgical coke, and focus on establishing a prediction model based on coal blending theory and test data, ignoring the impact of large-scale industrial production, and seldom pay attention to it. Different process parameters in the coke oven production process are important factors affecting metallurgical coke, and precisely the production process parameters have an important impact on the quality of metallurgical coke. The production process parameters and the quality of a single coking coal have an impact on the quality of metallurgical coke like the wings of a bird. , two-wheeled car

Excessive attention to the quality of a single coal and neglect of the important influence of production process parameters make the current coking coal blending technology model unable to predict the quality of metallurgical coke, which greatly affects the development of coal blending technology model and the application of the industry

Images