Research And Application Of Intelligent Control Of BTP

The sintering process,as a basic link in the steel smelting process,is a very complex nonlinear dynamic time-varying process.As an important parameter of the sintering state,the burn through point(BTP)has a great influence on the grade and output of the sintered ore.Therefore,the accurate prediction and control of BTP has great application value.However,the sintering process has the characteristics of strong coupling,large hysteresis,multivariate,non-linearity,etc.It is difficult to accurately predict and control BTP if traditional modeling and control methods are used.In view of the above problems,this paper has carried out research on the prediction model and predictive controller of BTP,which provides a new method for accurately controlling the position of BTP.The main research of the paper is as follows:First,by analyzing the characteristics of the sintering product process and the sintering process,the key parameters that affect the accurate prediction of the sintering end point and the technical difficulties of control are determined.The location of BTP is judged by fitting the exhaust gas temperature of the wind box,and then the influencing factors of BTP are explained,and the correlation analysis is carried out with SPSS software.Finally,six related influencing factors of high correlation are selected.Then use the improved gray wolf optimization algorithm(IGWO)to optimize the BP neural network,and establish a BTP prediction model based on the IGWO-BP neural network.Through comparative experiments,the mean square error and mean absolute error of the IGWO-BP network prediction model are5.1078e-04 and 0.0163,respectively.The results show that the prediction accuracy and error of the prediction model are better than the other two prediction models,and it is more suitable for predicting the position of BTP.Secondly,in order to better realize the predictive control of BTP,the LM-PSO algorithm is introduced as a rolling optimization strategy,and a rolling optimization controller based on the LM-PSO algorithm is designed.The optimized predictive controller is used to output the optimal initial control value of the trolley speed to realize the control of the BTP position.Through the simulation results under different conditions,it can be concluded that compared with the PID controller,the anti-interference performance of the sintering end prediction controller is stronger.It can be used to control BTP at the sintering site.Finally,the designed intelligent control system of BTP is applied and tested.When the error of BTP is controlled within 0.5 wind box,the stability rate of BTP after the system was put into the system reached 92.7%,which was 11.4% higher than the stability rate without the system.It provides a new way to solve the problem of controlling BTP.