The Research And Application Of Sintering Batching Method In Metallurgical Material Yard

Sintering ingredients is the first process before sintering production.The quality of sintering ingredients will directly affect quality of sinter,which will directly affect the production of blast furnace.The sintering batching process is easily affected by factors such as unstable iron ore source and lag quality detection,which makes the whole sintering batching process extremely complicated.Therefore,the selection of a reasonable sintering batching scheme is of great significance for improving the quality of sintered ore,stabilizing sintering production and reducing production costs.In this paper,the sintering batching problem of metallurgical material yard is taken as the research background,and the sintering batching optimization model is established.The model is solved by intelligent optimization algorithm,and the optimal batching scheme is obtained.At the same time,a prediction model for the chemical composition of sinter is established,which can predict the chemical composition of the sinter of different mixing schemes in the metallurgical yard,and plays a guiding role in the actual ingredients.Finally,a sintering batching management subsystem is designed to realize intelligentization of the entire sintering batching process.The main work of the paper is as follows:Firstly,a single-objective sintering batching optimization model and a multi-objective sintering batching optimization model are established based on the process flow of the sintering process and analysis of factors affecting the optimization of sintering ingredients.For the single-objective sintering batching optimization model,GA-PSO algorithm and simulated annealing algorithm are introduced in detail to apply to the optimization of sintering batching,and two algorithms are compared in the example analysis.The result shows that GA-PSO algorithm has lower cost of raw materials and ensures the economics of sintering ingredients.Aiming at the multi-objective sintering batching optimization model,fast and elitist non-dominated sorting genetic algorithm and multi-objective particle swarm optimization algorithm based on adaptive grid algorithm are implemented.The results obtained by the two algorithms are compared.The results of the example show that the Pareto frontier distribution of the Pareto solution obtained by multi-objective particle swarm optimization algorithm based on adaptive grid algorithm is more dispersed.Furthermore,the Pareto solutions solved by multi-objective algorithm,this paper proposes information entropy method and ideal solution method for decision analysis.Then,chemical composition of sinter is predicted,and a prediction model based on extreme learning machine through particle swarm optimization(PSO-ELM)is proposed.The global search ability of the particle swarm optimization algorithm is used to optimize weights and thresholds in extreme learning machine.The simulation results show that compared with the ELM model prediction results,the proposed prediction model based on PSO-ELM algorithm has better prediction effect and can accurately predict chemical composition of sinter.Finally,on the basis of the above research,the main technology and function of the sintering batching management subsystem is analyzed.Combined with the actual metallurgical material yard batching situation,the system architecture,functional structure and database are designed.Batching basic data management,parameter management and ingredient management were achieved.