The Research On Optimization Of Mixed Coal Ratio For Coke Quality

Coke is one of the important raw materials in metallurgical industry,and its quality has a direct impact on the quality of smelting steel.In order to ensure coke quality,coking enterprises often use the method of improving the proportion of high-quality coal to produce coke,which will lead to excessive consumption of scarce coal resources and rising production costs.Therefore,on the basis of ensuring the coke quality,optimizing the coal blending scheme and reducing the proportion of high-quality coal,so as to reduce the production cost and improve the utilization efficiency of resources is of great significance to the production and development of coking enterprises.The specific work mainly includes the following aspects:(1)The problem of coal blending in coking plant is defined.Firstly,the distribution and classification of coking coal are introduced.Then,based on the analysis of the overall process flow and coal blending process of coking production,the influencing factors of coke quality and the requirements of coke quality index,the input and output variables of coke quality prediction model are determined,and the process of coal blending optimization model for coke quality is clarified.(2)The coke quality prediction model is constructed.In order to solve the problem of complex coking reaction and difficult to model according to mechanism,a coke quality prediction model is established by using support vector regression(SVR)with Gaussian function as kernel function and chaotic sparrow search algorithm(TSSA).After selecting and preprocessing the actual production data of coking plant,the simulation experiment is carried out.The experimental results show that tssa-svr has good prediction performance,and its prediction of coke quality can meet the actual production demand.(3)Taking a coking plant in Henan Province as the background,the mixed coal ratio optimization model is constructed and applied.In order to reduce the cost of coal blending,combined with the actual production situation of coking plant,the constraint range of coal blending index and coke quality index is determined,and the coal blending optimization model for coke quality is constructed.The TSSA algorithm of diversity variation is used to solve the model,and the actual production data in September are selected for verification.The experimental results show that the optimized coal blending scheme can effectively reduce the coal blending cost and ensure that the coke quality index produced by this scheme meets the production requirements of coking plant.The research results of this paper can provide help for the further development of coal blending optimization related research.The models and algorithms obtained in this paper are of certain significance to optimize coal blending structure,reduce high-quality resource consumption and improve the economic benefits of coking enterprises.