Application Research Based On GA-FWA In Prediction Of Sintering Burning Through Point

As the fastest growing industry in China and occupying an important social status,the steel industry is widely used in all aspects of social life and is an important industry supporting social development.However,due to the rapid development of the steel industry,China's iron ore has been extensively mined,and iron-rich mines are decreasing.In order to solve the shortage of raw materials and not affect the production of the steel industry,sinter has emerged as the main raw material for the production process of blast furnaces in China.The sintering process has also become an important part of blast furnace ironmaking.The stability of the sintering burning through point(BTP)is one of the signs to judge whether the sintering process is normal,which not only affects the quality and yield of the sintered ore,but also has a great influence on the sintering cost.Because the sintering process is a complex,changeable,nonlinear and time-delay problem,it is difficult to predict and control the sintering through point by using the traditional mechanism model or control theory.So this paper adopts a new method: through the newly proposed intelligent optimization algorithm—fireworks optimization algorithm based on genetic algorithm(GA-FWA)to optimize the parameters of support vector machine model to achieve the prediction of sintering endpoint.The GA-FWA combines the advantages of fireworks algorithm and genetic algorithm to find the global optimal value more quickly and accurately.And the support vector machine(SVM)method is based on the principle of statistical and structural risk minimum.It has strict theoretical and mathematical basis,and can solve the problem that the complexity of the algorithm is closely related to the input vector.Therefore,combining the GA-FWA algorithm with the support vector machine can train a higher precision prediction model to achieve accurate prediction of the BTP.Through reviewing a large number of relevant domestic and foreign literatures,this paper first introduces the domestic and international research status of sintering endpoint prediction.Then the basic principle of the sintering process and the basic theory of the intelligent optimization algorithm are analyzed in detail.The GA-FWA algorithm is used to optimize the parameters in the support vector machine to obtain the optimal parameter combination,and the training of the support vector machine model is realized by MATLAB software programming.And predictions,get predictions.Finally,this paper compares the experimental results of the new algorithm with the experimental results of particle swarm optimization,genetic algorithm and fireworks algorithm.The experimental results show that the GA-FWAalgorithm is superior to other algorithms in terms of experimental precision and running time.It can accurately predict the sintering end point and has a good guiding significance for the sintering production process.