Research On Production Scheduling And Charge Energy Consumption Prediction Of Converter In Steelmaking Works

Implementing precise production operation regulation and energy prediction analysis have important sense for iron and steel enterprises to enhance energy saving,reduce costs and increase efficiency and enhance market competitiveness.The converter is the core process in steelmaking production,and production schedule provides decisionmaking support for the operation and control.Therefore,The organic combination of the energy control of converter with the steelmaking production scheduling to promote efficient production,energy-saving and emission-reduction,which is one of the key issues that needs to be addressed in current steel companies.In view of the target,production scheduling optimization converter energy prediction and energy consumption analysis are studied respectively in this thesis.In the research of production operation control in the steelmaking plant,an improved hybrid bat algorithm is proposed.Firstly,on the premise of the scheduling constraints,such as the process constraints,the time of the operation and the uncertainty of the transportation time between the processes,the optimization model of the production scheduling is built,aiming at minimization of the deviation of the casting time of the caster and the total waiting time before the process equipment.And then,a variety of improvement strategies are designed for the hybrid bat algorithm,such as the location selection rule,the neighborhood search structure and the inverse algorithm based on the minimum location value.An example of a steel plant production data is used to simulate the model and algorithm.The results show that the model and algorithm can improve the actual production efficiency.In the research of converter energy prediction,oxygen is the key energy medium for converter to realize "negative energy steelmaking,according to the difficulty of oxygen consumption in converter,such as intermittence,complex factors and so on,a charge oxygen consumption model of converter based on mechanism analysis and data driving is established.Through the mechanism analysis of the oxygen consumption of the converter,the extraction and calculation of the influence factors are carried out.The data driven prediction model is built on the basis of LMBP neural network method;the attribute reduction is carried out by the Pearson correlation analysis method and the network topology optimization is designed by the design of the width and depth comparison experiment of the hidden layer.Combined with the converter production scheduling plan,the oxygen prediction simulation of converter is carried out.The test results show that the model has good prediction accuracy up to 84.80% and the oxygen supply and demand forecast can meet the actual demand better.In the analysis of converter energy consumption,in order to effectively depict the fluctuation of energy consumption between charges,the charge energy consumption analysis method based on comprehensive energy consumption is carried out to promote the organic combination of production scheduling technology and energy prediction.Based on the prediction of the charge oxygen consumption of converter,according to the historical data of converter production,the consumption rule of converter gas,steam,power consumption and nitrogen energy medium is analyzed.Combined with the production scheduling plan of converter,the calculation and analysis of comprehensive energy consumption of charge are carried out,and the directions of energy saving for converter unit is pointed out.In conclusion,based on the practical needs of multi objective optimization,such as efficient production,energy saving and emission reduction of iron and steel enterprises,the related research is carried out on the optimization of production scheduling,the prediction of oxygen consumption in converter and t energy consumption analysis in this thesis.The off-line simulation experiment based on the actual data shows that the optimization,prediction and analysis models are effective and provide effective research route for production operation optimization and energy precise control in steel plant.