415results about "Steel manufacturing process aspects" patented technology

Provided are a joint regulation method of material flow, energy flow, and carbon emission flow in a long-process steel enterprise, which belongs to a field of intelligent regulation and control technology of electric power system in the steel industry. The method includes: coupling a material-energy characteristic model of each production process of a steel enterprise and a carbon emission model of the steel enterprise, constructing a material flow-energy flow-carbon emission flow coupling model of the long-process steel enterprise, establishing an objective function using a minimize sum of an electricity purchase cost from a superior grid, a park carbon emission cost, and a production raw material cost as an object, and solving and obtaining an optimal operation mode of a joint regulation of the material flow-energy flow-carbon emission flow in the steel enterprise.

The invention discloses a converter steelmaking endpoint forecasting method and device and a storage medium, and the method comprises the steps: carrying out the multi-scale importance modeling and graph attention mechanism modeling of the multi-dimensional process characteristics of the current heat, and generating the importance weight and the structure perception weight of each dimension of process characteristics; fusing the importance weight and the structure sensing weight, and multiplying the fused weight with the corresponding dimension process characteristics to generate a characteristic regulation and control vector of the current heat; performing multi-scale convolution operation on the feature regulation and control vector, extracting local mode features under different receptive fields, and outputting a spatial feature vector after the local mode features are enhanced by a self-attention mechanism; a plurality of groups of Transformer encoders are adopted to respectively process the furnace feature sequences with different historical window lengths, and cross-furnace time sequence feature vectors are extracted; and carrying out dimension alignment on the spatial feature vector and the time sequence feature vector, carrying out dimension-by-dimension weighted fusion through a learnable fusion weight, and outputting a steelmaking end point state prediction value of the current heat through a regression prediction network.

The embodiment of the invention discloses an intelligent energy consumption regulation and control steel smelting system based on multi-energy complementation, and the system comprises a multi-energy complementation energy supply system which is used for integrating various energy forms, forming a dynamic cooperative energy supply network, and carrying out the energy cooperative operation according to an energy priority strategy and a dynamic matching mechanism; the intelligent regulation and control platform adopts a three-layer framework of'perception-decision-execution 'to coordinate energy flow and process operation between the multi-energy complementary energy supply system and the multi-energy coupling process equipment; the multi-energy coupling process equipment comprises hydrogen-based direct reduction ironmaking equipment, and hydrogen is used for replacing traditional coke to serve as a reducing agent for ironmaking; comprehensive energy supply monitoring and optimization can be carried out on the steel smelting process, various renewable energy sources are combined, and the problems that a single renewable energy source is intermittent, depends on a power grid and the like are effectively solved; meanwhile, the multi-energy complementary hydrogen storage process is coupled with the hydrogen metallurgy process, and the multi-energy cooperation problems of whole-process green power supply, waste heat utilization and the like are solved.

The invention provides a method for making foam slag in LF (ladle furnace) refining by using a waste graphite electrode, which specifically comprises the following steps: grinding the waste graphite electrode to obtain graphite electrode powder, and adding limestone as a foaming agent in the LF refining. 0-1.25 kg / t of steel limestone is added firstly, and 0.018-0.19 kg / t of steel graphite electrode powder is added every 2 min. Compared with the prior art, by utilizing the characteristics of high carbon content, high conductivity and low sulfur of the graphite electrode, the invention aims to realize submerged arc heating, reduce power consumption and shorten refining time so as to meet the requirement of continuously increasing LF smelting indexes under the high-quality development trend of steelmaking.

A blast furnace operation method according to one aspect of the present disclosure comprises: a parameter estimation step for estimating blast parameters and a pulverized coal ratio in a second operation, such that the amount molten iron produced, the molten iron temperature, and the furnace top gas temperature in the second operation match those in a reference operation; a change information acquisition step for acquiring information on a temporal change in one or both of the molten iron temperature and the amount of molten iron produced when performing the second operation based on the blast parameters and the pulverized coal ratio estimated in the parameter estimation step with a delay of a predetermined time after switching from the reference operation to the first operation; a repeating step for performing the change information acquisition step a plurality of times while changing the predetermined time; and an optimum delay time acquisition step for determining, as an optimum delay time, a predetermined time such that the temporal change in the molten iron temperature or the amount of molten iron produced is the smallest, on the basis of the information acquired in the repeating step. After switching from the reference operation to the first operation, the second operation based on the blast parameters and the pulverized coal ratio estimated in the parameter estimation step is started with a delay of the optimum delay time.

The invention relates to a method for optimizing a pig iron desulfurization process (1), wherein the pig iron desulfurization process (1) is carried out by dispensing one or more desulfurization agents (2, 3, 4) into a pig iron ladle (5) or a torpedo car, wherein a plurality of treatment patterns are available which differ with respect to the type of desulfurization agents (2, 3, 4) dispensed. The optimization is based on creating a separate model (8) for each of the plurality of treatment patterns in order to optimize the added amounts of the desulfurization agents (2, 3, 4) for the associated treatment pattern, and training (9) the created separate models (8) for each of the plurality of treatment patterns after a predefined number of performed pig iron desulfurization processes (1) with the corresponding treatment pattern. Future pig iron desulfurization processes (1) are optimized on the basis of the predictions of the separate models (8), wherein the optimization determines a treatment pattern and the added amounts of the desulfurization agents (2, 3, 4) for the treatment pattern by means of a comparison of the predictions of the separate models (8). The invention also relates to a system and a computer program which are designed to carry out the method according to the invention.

The invention provides a load balance control system of a converter tilting device and a control method thereof, and belongs to the field of converter control. The control system comprises a plurality of motors including a first motor and a second motor; the plurality of feedback encoders, the plurality of controllers and the plurality of frequency converters correspond to the plurality of motors; the motor feedback encoders are arranged on rotating shafts of all the motors and used for obtaining the first rotating speed and the second rotating speed; the master controller is used for generating an integral component and a first control reference value, and the slave controller is used for generating a second control reference value; the frequency converters are in data communication connection, the main frequency converter is used for synchronizing integral components to the driven frequency converter, and the main frequency converter and the driven frequency converter are respectively used for controlling the first motor and the second motor to execute first and second control reference values. The method is mainly used for solving the problems of overload, reverse dragging, unstable control and the like caused by non-uniform load distribution when the converter is driven by multiple motors to tilt, the tilting stability is improved, and the wear rate of equipment is reduced.

The invention provides an electroslag remelting smelting endpoint element dynamic forecasting and process decision optimization method and system, and the method comprises the steps: obtaining a historical data set and a real-time data flow in a smelting process, and carrying out the preprocessing of data; an online stochastic gradient descent and incremental learning algorithm is introduced, an element dynamic prediction model is constructed, sensor data in the smelting process are received in real time, and an element concentration prediction model is dynamically optimized; on the basis of a depth deterministic strategy gradient algorithm, an optimization decision model is constructed, and a smelting operation strategy is adjusted in real time according to element components, smelting working conditions and other environment parameters predicted online by the element dynamic forecasting model; and a real-time feedback mechanism is set, so that the element dynamic prediction model and the optimization decision model work cooperatively, and element concentration prediction and real-time synchronous adjustment of a control strategy are realized. The smelting parameters can be adjusted in real time, element prediction precision is improved, energy consumption is reduced, manual intervention is reduced, and smelting efficiency and quality stability are remarkably improved.

The invention discloses a blast furnace working condition knowledge graph construction method and device, and belongs to the field of blast furnace ironmaking intelligent control. The method comprises the following steps: fusing multi-source data, integrating sensor real-time data, process parameters, operation logs and expert rules, and enhancing abnormal working condition data generation capability by using a time sequence generative adversarial network; a three-layer dynamic body structure with the core abnormal furnace condition as the center is constructed, and a dynamic edge weight updating mechanism is designed; extracting multi-region spatial-temporal characteristics of the blast furnace by adopting a spatial-temporal diagram convolutional network, and generating an interpretable knowledge triple in combination with a causal discovery algorithm FGES; and realizing real-time updating of the knowledge graph based on a streaming graph learning framework, generating a regulation and control instruction through multi-agent reinforcement learning, and issuing the regulation and control instruction to a blast furnace control system through a digital twin interface. The method can clearly represent the symptom incidence relation of the abnormal furnace condition of the blast furnace, rapidly position the abnormal source and generate the regulation and control strategy, and has important practical significance for improving the intelligent level of blast furnace ironmaking.

The invention discloses a smelting method of cold direct reduced iron in a Consteel electric furnace, belonging to the technical field of electric furnace steelmaking. The smelting method comprises the following steps: at the beginning of smelting, low-grade power supply is adopted, and at the same time of power-on, oxygen lances and carbon lances on the furnace wall are used to blow oxygen and spray carbon to produce foamed slag for submerged arc. After 1-3 minutes, scrap steel is continuously added by the Consteel system, and cold direct reduced iron is added through the fifth hole of the electric furnace. The molten steel in the furnace is heated by the electric arc, and the molten steel melts the metal materials in the furnace; during the whole smelting process, lime and light burned dolomite are added in batches. The addition amount of lime is 30-50 kg / t of steel, and the addition amount of light burned dolomite is 25-30 kg / t of steel. The invention helps to maintain the whole-process flat bath smelting, reduce the power consumption of electric furnace smelting, and reduce the smelting cost; it provides a technical solution for a short-process demonstration plant for the efficient use of direct reduced iron in an electric furnace, filling the domestic technical research gap in the short-process industry of electric furnaces.

The invention relates to the technical field of converter safety monitoring, in particular to a method for predicting the thickness of refractory bricks based on converter wall temperature. The temperature distribution and the residual thickness of the refractory bricks are estimated according to the external furnace body temperature and the melt smelting temperature, and then the overhaul of the converter is judged according to the temperature distribution and the residual thickness of the refractory bricks, so that the real-time safety monitoring in the operation process of the converter is realized. The problem of how to monitor the operation risk of the converter is solved.

The present application belongs to the field of smelting coal gas recovery, and particularly relates to an optimized control method and system for combustible gas recovery. The method divides the smelting process into N measurement time periods, and calculates the average secondary combustion coefficient of each time period in real time. Meanwhile, M target smelting time zones and their weights are set, and a dynamic target value sequence is established. Based on the initial fan speed, the measured coefficient is adjusted through multiple iterations of the furnace, and when the measured coefficient is greater than the target value, the speed is reduced in steps, and a thermal imager and a differential pressure instrument are introduced to monitor the smoke emission. A smoke emission rate statistics and tolerance threshold judgment mechanism is established to trigger speed backtracking adjustment, and finally the average secondary combustion coefficient of each time period is minimized to generate an optimal fan speed model. The present application maximizes the improvement of the calorific value of coal gas and the recovery of carbon monoxide under the premise of preventing smoke from the furnace mouth.

Provided are a molten iron component estimation device, a component estimation method, and a desulfurization method, whereby it is possible to estimate the component of molten iron after desulfurization with high accuracy in the desulfurization of molten iron using a mechanical stirring facility. A component estimation device (14) that estimates the S concentration in molten iron (3) during desulfurization of the molten iron (3) using a mechanical agitation desulfurization facility (1) is provided with: a data input unit (140) that inputs current operation data during the desulfurization; the current operation data at least comprises the temperature of the molten iron (3) measured by a non-contact temperature measuring device (12) after the stirring of the molten iron (3) is started and before the input of the desulfurizing agent (4) is started, namely the temperature of the molten iron in the desulfurization treatment; and a model calculation unit (142) that estimates the S concentration in the molten iron (3) after desulfurization on the basis of current operation data and a machine learning model that represents the relationship between the temperature of the molten iron during desulfurization and the amount of the desulfurizer (4) introduced and the reaction rate constant during desulfurization on the basis of past operation data during desulfurization.

A dynamic control method and apparatus for an electric arc furnace smelting state, a device, and a medium. The method comprises: collecting smelting data generated by an electric arc furnace during a smelting process; and, calculating an arc length and a foamed slag height using the smelting data, further determining a submerged arc condition of the electric arc furnace on the basis of the arc length and the foamed slag height, and adjusting smelting parameters of the electric arc furnace on the basis of the condition; or, calculating differences between data sub-items and corresponding historical warning thresholds, and adjusting smelting parameters of the electric arc furnace on the basis of the calculation results. The method achieves real-time monitoring and intelligent analysis of the smelting state of the electric arc furnace, ensures the flexibility and efficiency of electric arc furnace operation, and improves energy utilization.

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.

The invention discloses a multi-dimensional fusion sensor data anomaly detection method based on a hydrogen-based shaft furnace, and belongs to the technical field of metallurgical equipment monitoring. The method comprises the steps of data preprocessing, single-variable anomaly detection, multivariable consistency detection, anomaly type judgment and alarm output. The single variable detection adopts a rolling median absolute deviation method, drift detection, continuous tiny variable threshold and border crossing detection; the multivariate detection calculates reconstruction residuals of each sensor through principal component analysis (PCA) and identifies overall consistency anomalies. And the system judges the fault type according to the comprehensive score of the multiple detection results and outputs a detailed alarm record and a statistical report. According to the method, multi-algorithm fusion analysis is carried out on time sequence data collected by a plurality of sensors in the operation process of the shaft furnace, so that the abnormal states of the sensors are accurately recognized. The method can be widely applied to real-time monitoring of the hydrogen-based shaft furnace smelting process, the accuracy and robustness of anomaly detection are improved, and false alarms and missing alarms are reduced.

The invention discloses a converter optimal molten iron scrap ratio dynamic adjustment method which is characterized by comprising the following steps: monitoring the temperature and chemical component data of molten iron entering a converter in real time; establishing a prediction model based on historical data and an intelligent algorithm, and predicting the molten iron temperature and chemical component change trend; calculating first influence data of the scrap steel adding amount on the molten iron temperature according to the physical thermal correction model, and calculating second influence data of element oxidation heat on the total heat according to the chemical thermal correction model; and the molten iron scrap ratio is dynamically adjusted according to the results of the first influence data and the second influence data, and the generated scrap ratio is transmitted to a converter control system in real time. According to the prediction model based on historical data and an intelligent algorithm, the temperature and component change trend of the molten iron is predicted in advance, so that the scrap ratio is adjusted in advance, the steelmaking efficiency is improved, the cost is reduced, and the environmental influence is reduced.

The method for controlling the suction of process gases emitted within a vessel (22) of an electric arc furnace (20) during its operation comprises an adaptation step of adapting the flowrate (Y) of sucked in process gases based on the value of at least one parameter, said at least one parameter comprising a flowrate (X2) of carbonaceous matter added within the vessel (22) during operation of the electric arc furnace (20).

The invention relates to the technical field of thin-strip continuous casting, in particular to an intelligent stainless steel production method combining RKEF smelting and a double-roller thin-strip cast rolling technology.According to the method, the RKEF technology is directly coupled with the stainless steel refining and thin-strip continuous casting technology, firstly, based on target product requirements, an intelligent batching model is adopted for calculating furnace charge of an RKEF furnace; then, based on RKEF molten nickel iron components, an intelligent batching model is adopted to conduct collaborative optimization calculation on added ingredients of the AOD furnace (a dynamic blowing control model is adopted to conduct real-time optimization on the proportion and flow of mixed gas of O2, Ar and N2), and cost optimal dynamic batching under multiple constraints is achieved; then, a neural network algorithm GAN with physical constraint PI is used for predicting components and temperature, predicted values of the components and the temperature and control instructions are output, the metallurgical physical law is used as hard constraint to be embedded into model training, a control decision is made to fit data and conform to scientific rules, process control is conducted accurately, the whole process is more energy-saving, and the method is suitable for large-scale popularization and application. And carbon dioxide emission is reduced.

The present invention belongs to the technical field of automated steel production and discloses a method for predicting the composition of molten iron applied to an automated steel production process, wherein the method is: performing a sampling and an examination of molten iron in a process in which the molten iron is tapped from a torpedo tank into a ladle, and calculating a loss of composition of this molten iron, wherein the composition of the molten iron is calibrated before the molten iron is tapped into the ladle;Performing a sampling and analysis of the molten iron in a process where the molten iron is transferred from the ladle to a converter, and calculating any loss in the composition of this molten iron, wherein the composition of the molten iron is calibrated before the molten iron is transferred to the converter. The present invention is easy to use and implement, and can acquire more accurate and reliable real-time parameters for computational models at all levels; in its specific application, the present invention does not require the modernization of existing automated steelmaking equipment; and it can be applied to a wide range of automated steelmaking scenarios.

Provided is a technology capable of promptly determining the energization condition in an alternating-current electric arc furnace, and stably determining the furnace condition without the influence of dust. Specifically, provided is an apparatus for determining the energized state of an alternating-current electric arc furnace, including a detection means for detecting sound generated within the alternating-current electric arc furnace, an output means for analyzing the frequency of the detected sound, and outputting a frequency -sound pressure signal, and a determination means for determining the covered state of an arc due to slag foaming based on a signal intensity in the range of Fi-0.5×F0 to Fi+0.5×F0, where Fi represents the frequency of an integral multiple of the fundamental frequency F0 of the alternating-current electric arc furnace. Also provided is a method for producing molten steel by melting and refining scrap with an alternating-current electric arc furnace by controlling one or more of a combination of the oxygen-containing gas supply rate, the carbon material supply amount, and the slag forming agent supply amount based on the energized state determined by the apparatus.

Provided is a technique with which it is possible to quickly determine the energization state in an electric arc furnace and to stably determine the furnace condition without being affected by dust. A power-on state determination device for an electric arc furnace is provided with: a detection means for detecting sound generated in the electric arc furnace; an output means for analyzing the frequency of the detected sound and outputting a frequency-sound pressure signal; and a determination means for determining the coverage state of an arc caused by slag formation on the basis of the signal strength of the detected sound in one predetermined frequency range selected from 500 Hz to 1500 Hz or in a plurality of frequencies. A method for producing molten steel by melting and refining waste material in an electric arc furnace controls any one of the oxygen-containing gas supply rate, the carbon material supply amount, and the slag-making material input amount, or a combination of a plurality thereof, on the basis of the energization state determined by the device.

A computer system (100), a computer-implemented method and a computer program product for training a reinforcement learning model (130) to provide operational instructions for blast furnace thermal control are provided. A domain-adaptive machine learning model (110) generates a first domain-invariant dataset (22) from historical operational data (21) obtained as multivariate time series and reflecting thermal states of respective blast furnaces (BF1 to BFn) of a plurality of domains. A transient model (121) of a generic blast furnace process is used to generate artificial operational data (24a) as multivariate time series reflecting thermal states of a generic blast furnace (BFg) for specific thermal control actions (26a). A generative deep learning network (122) generates a second domain-invariant dataset (23a) by transferring features learned from the historical operational data 21 to the artificial operational data (24a). A reinforcement learning model (130) determines (1400) a reward (131) for specific thermal control actions (26a) by processing the combined first and second domain-invariant datasets (22, 23a) in view of a given objective function. In accordance with the reward (131), the second domain-invariant dataset is regenerated based on modified parameters (123-2) and the determination of the reward is repeated to learn optimized operational instructions for optimized thermal control actions to be applied to respective operational states of one or more blast furnaces.

The operation method of a blast furnace improves the ventilation of the lower part of the blast furnace by tuyere injection of fine ore. The operation method of the blast furnace (1) of the invention is characterized in that coal is pulverized as fine coal, and an iron ore having a pulverized ignition loss of 9 mass% or more and 12 mass% or less is pulverized as fine ore, the injection rate of the fine coal is 150 kg / tp or more, the injection rate of the fine ore is 2.5 kg / tp or more and 50.0 kg / tp or less, and the fine coal and the fine ore are injected from the tuyere (2). It is preferable that the iron ore and the coal are pulverized together.

Provided are a state estimation method for vacuum degassing treatment, etc. capable of highly accurate state estimation in vacuum degassing treatment. A state estimation method for vacuum degassing treatment includes: an input step (S1, S2) of receiving input of operation track records related to manipulated variables during vacuum degassing treatment and time-series exhaust gas measured values including a flow rate of exhaust gas discharged from a vacuum degassing line that performs the vacuum degassing treatment and component concentrations of CO gas, CO2 gas, and O2 gas contained in the exhaust gas, as input information; and a calculation step (S3) of, based on the input information, classifying sources of gases that constitute the exhaust gas into a plurality of sources including blown oxygen and air entering a vacuumized region in the vacuum degassing line before or during the treatment, and estimating a constituent ratio of the classified plurality of sources.

The application provides a blast furnace hearth bottom erosion discrimination method based on new installation and old thermocouple combination, which comprises the following steps: (1) constructing a grid node according to a blast furnace structure parameter; (2) discriminating a damaged thermocouple on the grid node, and arranging a new thermocouple in a corresponding area; (3) measuring temperature data of each temperature monitoring node of the new thermocouple and the old thermocouple, and calculating temperature data of the temperature monitoring node at the corresponding damaged thermocouple by using the temperature data of the new thermocouple; and (4) establishing an area grid according to the temperature data of the temperature monitoring node in step (3), so that a hearth bottom erosion condition model is obtained. The application comprehensively considers the existing thermocouple distribution and damage condition of the hearth, reasonably arranges the arrangement points of the new thermocouple, and provides an effective shortcut for improving the long service life level of the blast furnace and guiding the safety production.

A method for measuring the height of a melt in a blast furnace according to the present invention comprises: a measurement step for measuring a vibration frequency distribution in the height direction of a furnace body of the blast furnace using a plurality of vibrometers arranged at predetermined intervals in the height direction of the furnace body; a vibration intensity calculation step in which the vibration intensity of the frequency range originating from the blowing air at each measurement position is calculated by Fourier transform of the vibration frequency distribution; a numerical analysis step for calculating the maximum vibration intensity distribution of the lower part of the blast furnace using a numerical analysis model using the height of the melt in the blast furnace and the amount of blowing air as variables; and a melt height calculation step for calculating the melt height at which the difference between the vibration intensity calculated in the vibration intensity calculation step and the maximum vibration intensity distribution calculated in the numerical analysis step is minimum, and using the calculated melt height as the position of the melt height in the blast furnace.

This process control method includes: a response prediction step of finding a predicted value for a prospective molten-iron temperature by utilizing a physical model with which the state of the interior of a blast furnace can be calculated; and an operational-control-level determination step of, if the absolute value of the difference between the predicted value for the molten-iron temperature found in the response prediction step and a target value is greater than or equal to a prescribed threshold value, finding a deviation between the predicted value for the molten-iron temperature and the target value, to find a pulverized coal ratio and an operational-control level for blown-air moisture content such that an evaluation function having a term corresponding to the deviation and a term for decreasing a reducing-material ratio or the blown-air moisture content is minimized or maximized, and if the absolute value is less than the prescribed threshold value, combining, in accordance with intention, two among pulverized coal ratio, blown-air moisture content, and blown-air temperature, to find an operational-control level such that the predicted value is maintained.

A method and system of extracting iron oxide from ore is provided, which may include adding a chelating agent to an iron ore to form an iron ore and chelating agent solution, heating the solution to reflux in water, and filtering the solution to yield an extraction residue and a chelated iron solution. The chelated iron solution may be treated with a potassium hydroxide and water solution to yield iron hydroxide.

The present application relates to a kind of gas protection high-strength welding wire steel wire rod and its short process low-phosphorus low-nitrogen preparation method, realize the mass content of phosphorus at the end of electric arc furnace smelting less than 0.005%, the mass content of carbon 0.03~0.07%, the mass content of nitrogen less than 0.005%.The present application utilizes end temperature and composition control of electric furnace smelting process, ensures the composition of molten steel at the end of electric furnace smelting, thereby reduces the risk of long refining time and increasing phosphorus content caused by a large amount of alloy addition in LF refining.Secondly, by improving the slagging, oxygen supply and power supply system of electric furnace smelting process, high-efficiency deep dephosphorization is realized in the smelting process, and the nitrogen absorption caused by power supply is reduced.