Research On Development And Application Of Intelligent Warning Terminal For Pre-Ironmaking Raw Materials

Steel is an important raw material for construction and technological development,and most of steel companies use blast furnace to smelt iron now.The internal operating conditions of blast furnace are very complicated.There are many factors that affect the quality of molten iron,but the key factor is the quality of raw materials.There are many raw materials for blast furnace.Realizing coke quality prediction and collection,classification,display and analysis of raw material production data such as sintering,pellets and coke can provide necessary data support for the stable operation of blast furnaces,thereby promoting the quality of molten iron and economic benefits.Mixed coal quality and coking process control are the main key factors affecting coke quality.In this thesis,the influence of mixed coal quality on coke quality prediction is investigated based on the premise of stable coking process control,and a coke quality prediction model based on gradient boosting decision tree is proposed.Due to the large number of mixed coal quality parameters,input variables are selected based on expert experience and correlation analysis,and the gradient boosting decision tree algorithm is adopted for modeling to predict the sulfur content,ash content,M10 and M40 of coke quality parameters.The experimental results show that the coke quality prediction model based on gradient boosting decision tree has less error and higher accuracy than linear regression model,decision tree model,and random forest model.It is can provide certain reference value for coke production as well.An intelligent warning terminal for pre-ironmaking raw materials is designed and developed based on the coke quality prediction model.The terminal includes some modules such as coke quality prediction,pre-ironmaking raw material report and warning.The coke quality prediction module can predict the coke quality in real time.The pre-ironmaking raw material report module can query the raw material inspection data and inventory information in different time periods.When the key parameters of coke and the system data are abnormal,the warning information can be transmitted to the relevant engineers so that the loss can be reduced to a controllable range.The mobile terminal can provide procedure monitoring for technicians and managers to discover production problems and diagnose in time remotely.