A method and an apparatus method for producing direct reduced iron (DRI) from iron ore using biomass as a source of reductant and as a heating source of the iron ore and electromagnetic energy as a further heating source in a furnace having multiple zones. The zones include a preheat zone and a reduction zone between an inlet for briquettes of iron ore and biomass and an outlet for direct reduced iron. The method includes counter-current movement of (a) briquettes of iron ore and biomass in a direction from the inlet to the outlet and (b) combustible gases in an opposite direction in the furnace.

A fine ratio measuring device that measures the fine ratio of fines adhering to the surface of the material in the form of lumps includes: an illumination unit that illuminates the material in the form of lumps; an imaging unit that captures an image of the material in the form of lumps and produces image data; and an arithmetic unit including a computation unit that computes a characteristic quantity of the image data produced by the imaging unit and a conversion unit that converts the characteristic quantity computed by the computation unit to the fine ratio.

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.

Disclosed is a blast furnace apparatus includes: a rotating chute; a plurality of tuyeres; a profile measurement device configured to measure surface profiles of a burden charged into the blast furnace through the rotating chute; and a blowing amount controller configured to control a blowing amount of at least one of hot blast or pulverized coal in each of the plurality of tuyeres, in which the profile measurement device includes: a radio wave distance meter installed on the blast furnace top and configured to measure the distance to the surface of the burden charged; and an arithmetic unit configured to derive the surface profiles of the burden on a basis of distance data for the entire blast furnace related to distances to the surface of the burden obtained by scanning a detection wave of the radio wave distance meter in the blast furnace in a circumferential direction.

This diagnosis support apparatus is a diagnosis support apparatus of a vacuum degassing tank having an immersion tube that extends downward, the diagnosis support apparatus including a camera that is configured to capture an image of an inner circumferential surface of an immersion tube seen from below at an angle in a state of being disposed outside the inner circumferential surface of the immersion tube in a plan view and acquire the image as data and an image processor that is configured to be connected to the camera and carry out image-processing of the data.

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.

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.

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.