Multi-objective Robust Optimization Of Ladle Refining Production Process Based On Soft Measurement

LF furnace has simple equipment and flexible smelting process which needs less investment.The gas and harmful impurities will be lower by refining that make sure the molten steel maintains a constant composition.Therefore,LF refining has been widely used in iron and steel enterprises.At the same time,LF furnace refining technology can increase the variety and quality of steel.In this paper,the experiments'data which collected from Fujian Sangang's 100tLF are used to predict the temperature of molten steel.Then optimizing the operation parameters of the ladle refining process in order to improve the quality of steel,save the production cost and shorten the smelting period.The main contents and results of the study are summarized as follows:Aiming at the characters of ladle furnace refining,a new algorithm AdaBoost.RS is proposed for soft sensors modeling in industry.The slack variable and forgetting factor are introduced to increase the accuracy of the soft sensor model and fit the noisy industrial data.At the same time,the incremental learning can reduce the impact of historical data on the model.It demonstrates that more than ninety percent of the sample data's absolute error is less than 10 through the experiments of dynamic and static data.A new multi-objective robust operation optimization method of molten steel temperature is proposed in LF refining process.The improved Harmony Search Algorithms is proposed in this paper.The algorithm introduces the diversity of solutions to guide the search's direction.It also reduces the number of parameters to make the application simple.Four testing function are used to test the convergence rate of the algorithm.At the same time,the LF ladle furnace multi-objective robust optimization model has been solved by the improved Hannony Search Algorithms.Optimizing the operation parameters of the ladle refining process is very important to the robust results.It can improve the stability of the system and the quality of steel with lower cost and energy.