An object is to measure the fine ratio, or the ratio of fines adhering to the surface of lumps of material, in real time with high accuracy.

A fine ratio measuring method includes a step S1 of measuring a distance between a distance measuring device and lumps of material, a step S2 of calculating a feature quantity from distance data obtained in the step S1, and a step S3 of converting the feature quantity calculated in the step S2 to a fine ratio. The feature quantity calculated in the step S2 represents distance variation calculated from the distance data obtained in the step S1. A higher fine ratio in lumps of material means greater microscopic distance variation caused by microscopic irregularities in the surface of the lumps of material in the height direction within a three-dimensional shape. Therefore, by using the distance variation as the feature quantity, the fine ratio in the lumps of material can be measured in real time with high accuracy.

A method for a blast furnace includes pulverizing coal to make pulverized coal, and pulverizing iron ore to make pulverized iron ore, and injecting the pulverized coal and the pulverized iron ore from a tuyere. A loss on ignition of the iron ore is greater than or equal to 9% by mass and less than or equal to 12% by mass, an injection rate of the pulverized coal is greater than or equal to 150 kg/tp, and an injection rate of the pulverized iron ore is greater than or equal to 2.5 kg/tp and less than or equal to 50.0 kg/tp.

A blast furnace fault determination apparatus includes a processor configured to: calculate a fault index indicative of a degree of fault in a blast furnace; calculate a ventilation index of the blast furnace; and determine a fault condition in the blast furnace using the fault index and the ventilation index.

A method for controlling a hot metal temperature, includes: a first control loop for calculating a target value of pulverized coal ratio such that a hot metal temperature, predicted by a physical model that is able to calculate conditions inside a blast furnace, falls within a preset target range; and a second control loop for calculating pulverized coal flow rate manipulation quantity to compensate for a deviation between the pulverized coal ratio target value and a current pulverized coal ratio actual value.

A method for monitoring the wear of a refractory lining of a blast furnace using modelling of a part of the blast furnace and thermal field calculation. Computer program allowing to perform such a method.

A blast furnace operation method according to one aspect of the present invention includes: a process of acquiring a correlation between a carbon consumption in reducing gas and a reduction InputΔC in specific carbon consumption caused by blowing the reducing gas into the blast furnace per molar ratio C/H of carbon atoms to hydrogen atoms in the reducing gas; a process of determining a carbon consumption in the reducing gas where the reduction InputΔC in specific carbon consumption is a predetermined target value or higher on the basis of the correlation acquired per C/H; and a process of adjusting the amount of the reducing gas blown into the blast furnace on the basis of the determined carbon consumption in the reducing gas and the carbon proportion in the reducing gas.

The present disclosure discloses a method for deriving fault diagnosis rules of a blast furnace based on a deep neural network, which relates to the field of industrial process monitoring, modeling and simulation. Firstly, a deep neural network is used to model historical fault data of the blast furnace. Then, for each kind of fault, the process starts from the output layer of the network, wherein sub-models of nodes in the adjacent layers in the deep neural network are established by using the decision tree in sequence, and the if-then rule is derived. Finally, the if-then rules are merged layer by layer, so as to finally obtain fault diagnosis rules of the blast furnace with blast furnace process variables being the rule antecedents and with fault categories being the rule consequents.

An operation guidance method includes: predicting a state in a blast furnace when a current operation state is retained in a future, by using a physical model that is able to calculate the state in the blast furnace; and displaying, on an output device, an oxygen balance in a raceway region, a carbon balance in an entire furnace, and an oxygen balance derived from iron oxide in the entire furnace, when the state in the blast furnace is predicted.

A production method of pig iron using a blast furnace with a tuyere includes: charging a first layer containing an iron ore material and a second layer containing coke alternately in the blast furnace; and reducing and melting the iron ore material in the charged first layer while injecting an auxiliary reductant into the blast furnace by hot air blown from the tuyere, in which: an aggregate for letting through the hot air to a central portion of the blast furnace is blended into the first layer; and the aggregate contains a reduced iron molded product obtained through compression molding of reduced iron.

Computer system, computer-implemented method and computer program product are provided for training a reinforcement learning model to provide operating instructions for thermal control of a blast furnace, where a domain adaptation machine learning model generates a first domain invariant dataset from historical operating data obtained as multivariate time series and reflecting thermal states of respective blast furnaces of multiple domains, a transient model of a generic blast furnace process is used to generate artificial operating data as multivariate time series reflecting a thermal state of a generic blast furnace for a particular thermal control action, a generative deep learning network generates a second domain invariant dataset by transferring the features learned from the historical operating data 21 to the artificial operating data, where the reinforcement learning model determines a reward for the particular thermal control action in view of a given objective function by processing the combined first and second domain invariant datasets, and dependent on the reward, the second domain invariant data set is regenerated based on modified parameters, and repeating the determining of the reward to learn optimized operating instructions for optimized thermal control actions to be applied for respective operating states of one or more blast furnaces.