A method to manufacture a global tonnage of steel products in at least two steelmaking units wherein expected level emissions are calculated and compared with pre-defined targets.

A residual molten material amount detection method and detection apparatus that can detect a residual amount of molten material in a vertical furnace and a method for operating a vertical furnace by using the detection method. The residual molten material amount detection method detects a residual amount of molten material remaining in a bottom portion of a vertical furnace after end of discharge of the molten material. The method includes detecting the residual amount of the molten material by using a difference between a production speed of the molten material and a discharge speed of the molten material that is calculated by using a discharge acceleration, a discharge period, and an initial discharge speed of the discharge of the molten material through a taphole.

A molten material liquid level detection method that can detect a liquid level of molten material from a residual amount of the molten material with high accuracy and a method for operating a vertical furnace by using the detection method. The molten material liquid level detection method detects a liquid level of molten material remaining in a bottom portion of a vertical furnace after end of discharge of a molten material. The molten material liquid level detection method includes calculating a void fraction of the solid-filled structure, and detecting a liquid level of the molten material after the end of the discharge by using the calculated void fraction and a residual amount of the molten material after the end of the discharge.

A detection wave from a transmitting/receiving means is guided to the interior of a blast furnace via an antenna and a reflecting plate, and when a reflected wave from the surface of a loaded material is reflected by the reflecting plate and received by the transmitting/receiving means, the reflecting plate is rotated together with the antenna, or the reflecting plate is rotated additionally, and the surface profile of the loaded material is measured by scanning the surface of the loaded material in a linear manner or a planar manner during the turning of a chute or for each prescribed turn of the chute. A deposition profile is obtained on the basis of this surface profile and is compared to a predetermined theoretical deposition profile, and the chute is controlled so as to correct the error with respect to the theoretical deposition profile and then which new loaded material is introduced.

A method for producing pig iron using a blast furnace containing a tuyere, including stacking a first layer including an iron ore material and a second layer including coke alternately in the blast furnace, charging the coke to a central portion of the blast furnace, and reducing and melting the iron ore material in the first layer while injecting an auxiliary reductant into the blast furnace by hot air blown from the tuyere. In the stacking, the charging of the coke is carried out once or a plurality of times during one charge of stacking a stacking unit composed of one of the first layer and one of the second layer, and a ratio R of a mass (ton/ch) of the coke accumulated in the central portion to a mass of the iron ore material charged in the one charge is greater than or equal to a predetermined value a.

A supplied heat quantity estimation method estimates a quantity of heat supplied to pig iron in a blast furnace from a quantity of heat supplied into the blast furnace and a production speed of molten iron in the blast furnace, and includes an estimation step of estimating a change in carried out sensible heat by in-furnace passing gas and a change in carried in sensible heat supplied by a raw material preheated by the in-furnace passing gas, and estimating the quantity of heat supplied to pig iron in the blast furnace in consideration of the estimated changes of the carried out sensible heat and the carried in sensible heat. The estimation step includes calculating an iron making speed and estimating a quantity of heat held in furnace core coke present in the blast furnace to estimate the quantity of heat supplied to pig iron.

A blast furnace control system may include a hardware processor that generates a deep learning based predictive model for forecasting hot metal temperature, where the actual measured HMT data is only available sparsely, and for example, measured at irregular interval of time. HMT data points may be imputed by interpolating the HMT measurement data. HMT gradients are computed and a model is generated to learn a relationship between state variables and the HTM gradients. HMT may be forecasted for a time point, in which no measured HMT data is available. The forecasted HMT may be transmitted to a controller coupled to a blast furnace, to trigger a control action to control a manufacturing process occurring in the blast furnace.

A blast furnace control system may include a hardware processor that generates a deep learning based predictive model for forecasting hot metal temperature, where the actual measured HMT data is only available sparsely, and for example, measured at irregular interval of time. HMT data points may be imputed by interpolating the HMT measurement data. HMT gradients are computed and a model is generated to learn a relationship between state variables and the HTM gradients. HMT may be forecasted for a time point, in which no measured HMT data is available. The forecasted HMT may be transmitted to a controller coupled to a blast furnace, to trigger a control action to control a manufacturing process occurring in the blast furnace.

Controlling circumferential variability in a blast furnace may include generating a predictive model that sets up a relationship between a standard deviation of a selected state variable, state variables and one or more control variables in blast furnace operation for predicting the standard deviation. A number of circumferential sections of the blast furnace is defined, and the predictive model associated with the selected state variable for each of the circumferential sections is trained based on process data of the blast furnace. A plurality trained predictive models is generated associated with different circumferential sections and different selected state variables. One or more future control variable set points that minimize a sum of the plurality of predictive models, is determined. One or more future control variable set points is transmitted to a control system to control the blast furnace operation.

Controlling circumferential variability in a blast furnace may include generating a predictive model that sets up a relationship between a standard deviation of a selected state variable, state variables and one or more control variables in blast furnace operation for predicting the standard deviation. A number of circumferential sections of the blast furnace is defined, and the predictive model associated with the selected state variable for each of the circumferential sections is trained based on process data of the blast furnace. A plurality trained predictive models is generated associated with different circumferential sections and different selected state variables. One or more future control variable set points that minimize a sum of the plurality of predictive models, is determined. One or more future control variable set points is transmitted to a control system to control the blast furnace operation.