Blast furnace burden distribution control method and device, electronic equipment and storage medium

Abstract

The invention provides a blast furnace burden distribution control method and device, electronic equipment and a storage medium, and the blast furnace burden distribution control method comprises the following steps: obtaining current production parameter data of a blast furnace and current temperature data of blast furnace edge gas flow, and inputting the current production parameter data into a blast furnace edge gas flow temperature prediction model; obtaining predicted temperature data of the blast furnace edge gas flow at a future moment, determining a temperature change trend of the blast furnace edge gas flow based on the current temperature data and the predicted temperature data, comparing the temperature change trend with a preset change trend, and determining a distribution control strategy of the blast furnace according to a comparison result, controlling the blast furnace to distribute materials according to the material distribution control strategy; according to the method, the temperature change trend of the blast furnace edge gas flow can be determined after the predicted temperature data is obtained, the distribution control strategy is determined based on the comparison result of the temperature change trend and the preset change trend, reference is provided for blast furnace distribution control, and energy consumption of the blast furnace ironmaking process is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of blast furnace burden distribution control, and in particular to a blast furnace burden distribution control method, device, electronic equipment and storage medium. Background Art

[0002] Blast furnace ironmaking is the link with the highest energy consumption in the whole process of steel production. In the blast furnace production process, reasonable control of the gas flow distribution in the upper part of the blast furnace is a key step in the blast furnace production process. This is because the gas flow distribution in the upper part of the blast furnace is related to the temperature distribution in the furnace, the structure of the soft melting zone, the smooth operation of the furnace, the gas utilization rate and the longevity of the blast furnace. The operation of controlling the blast furnace is also mainly carried out around obtaining a reasonable and appropriate gas flow distribution. In actual production, it is mainly achieved through upper and lower adjustments. For example, the gas flow is adjusted by adjusting the air supply system and the material distribution system in order to obtain the best gas distribution effect, maximize the gas utilization rate and reduce production costs.

[0003] However, due to the airtightness and complexity of the blast furnace, and the fact that the gas flow in the furnace is affected by the distribution of the charge, the shape of the soft melting zone, and the position of the raceway, it is very difficult to monitor the gas flow distribution of the blast furnace in real time. Therefore, in actual production, we can only rely on manual experience and indirect observation of the current gas flow distribution state, for example, the measured value of the cross temperature measuring device on the top of the furnace is used to reflect the gas flow distribution state in the furnace at this moment. However, this method cannot predict the development trend of the gas flow in the future and provide a reference for the upper adjustment of the blast furnace (for example, charge distribution control). Summary of the invention

[0004] In view of the above-mentioned shortcomings of the prior art, the present application provides a blast furnace burden distribution control method, device, electronic device and storage medium to solve the above-mentioned technical problems.

[0005] According to one aspect of an embodiment of the present application, a blast furnace charge distribution control method is provided, comprising: obtaining current production parameter data of the blast furnace and current temperature data of the blast furnace edge gas flow; inputting the current production parameter data into a blast furnace edge gas flow temperature prediction model to obtain predicted temperature data of the blast furnace edge gas flow at a future moment; the blast furnace edge gas flow temperature prediction model is obtained by training a preset gas flow temperature prediction model with sample data; determining a temperature change trend of the blast furnace edge gas flow based on the current temperature data and the predicted temperature data; comparing the temperature change trend with a preset change trend, determining a charge distribution control strategy of the blast furnace according to the comparison result, and controlling the blast furnace for charge distribution according to the charge distribution control strategy.

[0006] In one embodiment of the present application, if the sample data includes historical production parameter data of the blast furnace and historical temperature data of the blast furnace edge coal gas flow, the process of training a preset coal gas flow temperature prediction model through the sample data to obtain a blast furnace edge coal gas flow temperature prediction model includes: merging the historical production parameter data and the historical temperature data to obtain a merged data set; preprocessing each type of parameter data in the merged data set to obtain a preprocessed data set, and the preprocessing includes filling missing values, deleting outliers, and / or normalization calculation; inputting the preprocessed data set into a preset parameter type importance ranking model to obtain a parameter type importance ranking sequence in the preprocessed data set, and filtering out a target parameter type from the parameter type importance ranking sequence, and the target parameter type includes a preset number of parameter types that rank high in the parameter type importance ranking sequence; combining the data corresponding to the target parameter type to obtain a characteristic parameter data set; training the preset coal gas flow temperature prediction model through the characteristic parameter data set to obtain the blast furnace edge coal gas flow temperature prediction model.

[0007] In one embodiment of the present application, the historical production parameter data and the historical temperature data are merged to obtain a merged data set. The process includes: calculating the correlation coefficient between the historical production parameter data and the historical temperature data to obtain multiple first correlation coefficients; using a first correlation coefficient greater than or equal to a preset correlation threshold as a first target coefficient, and using the historical production parameter data for which the first target coefficient is calculated as target production parameter data; determining temperature data at different times from the historical temperature data, and calculating the correlation coefficient between the target production parameter data and the temperature data at different times to obtain multiple second correlation coefficients; using the maximum coefficient among the multiple second correlation coefficients as the second target coefficient, and merging the target production parameter data for which the second target coefficient is calculated and the temperature data for which the second target coefficient is calculated to obtain the merged data set.

[0008] In one embodiment of the present application, each type of parameter data in the merged data set is preprocessed to obtain a preprocessed data set, including: comparing the number of each type of parameter data in the merged data set with a first preset sample number and a second preset sample number; if there is any type of parameter data whose number is less than the first preset sample number and greater than the second preset sample number, then filling the any type of parameter data until the number of each type of parameter data is greater than or equal to the first preset sample number, thereby obtaining a filled data set; the filling method includes an average value filling method and a nearest neighbor value filling method; based on the minimum value, lower quartile, upper quartile and maximum value of each type of parameter data in the filled data set, determining the corresponding type parameter data range; deleting the sample point data in each type of parameter data that exceeds the type parameter data range, and filling the deleted sample point data to obtain an updated data set; performing normalization calculation on each type of parameter data in the updated data set, combining each type of parameter data after the normalization calculation, and obtaining a preprocessed data set.

[0009] In one embodiment of the present application, the preset coal gas flow temperature prediction model is trained by the characteristic parameter data set to obtain the blast furnace edge coal gas flow temperature prediction model. The process includes: dividing the characteristic parameter data set into a data training set and a data test set; training the preset coal gas flow temperature prediction model by the data training set to obtain a trained coal gas flow temperature prediction model; inputting the data test set into the trained coal gas flow temperature prediction model to obtain an evaluation coefficient of the trained coal gas flow temperature prediction model; with the goal of maximizing the evaluation coefficient, training the trained coal gas flow temperature prediction model by the characteristic parameter data set until the number of training times reaches a preset threshold number of times, thereby obtaining the blast furnace edge coal gas flow temperature prediction model.

[0010] In one embodiment of the present application, based on the current temperature data and the predicted temperature data, the process of determining the temperature change trend of the blast furnace edge coal gas flow includes: calculating the difference between the predicted temperature data and the current temperature data; if the absolute value of the difference is less than or equal to a preset difference threshold, the temperature change trend is determined to be a stable trend; if the absolute value of the difference is greater than the preset difference threshold, and the predicted temperature data is greater than the current temperature data, the temperature change trend is determined to be an upward trend; if the absolute value of the difference is greater than the preset difference threshold, and the predicted temperature data is less than the current temperature data, the temperature change trend is determined to be a downward trend.

[0011] In one embodiment of the present application, if the current production parameter data includes current distribution operation parameter data, the distribution control strategy of the blast furnace is determined according to the comparison result, and the process of controlling the blast furnace for distribution according to the distribution control strategy includes: if the comparison result is that the change trend is consistent, the current distribution operation parameter data will be maintained as the distribution control strategy, and the blast furnace will be controlled for distribution according to the current distribution operation parameter data; if the comparison result is that the change trend is inconsistent, the current distribution operation parameter data will be adjusted as the distribution control strategy, and the blast furnace will be controlled for distribution according to the adjusted distribution operation parameter data.

[0012] According to one aspect of an embodiment of the present application, a blast furnace charge distribution control device is provided, comprising: a data acquisition module, used to acquire current production parameter data of the blast furnace, and current temperature data of the blast furnace edge gas flow; a temperature prediction module, used to input the current production parameter data into a blast furnace edge gas flow temperature prediction model, and obtain predicted temperature data of the blast furnace edge gas flow at a future moment; the blast furnace edge gas flow temperature prediction model is obtained by training a preset gas flow temperature prediction model with sample data; a trend determination module, used to determine the temperature change trend of the blast furnace edge gas flow based on the current temperature data and the predicted temperature data; a charge distribution control module, used to compare the temperature change trend with the preset change trend, determine the charge distribution control strategy of the blast furnace according to the comparison result, and control the blast furnace for charge distribution according to the charge distribution control strategy.

[0013] According to one aspect of an embodiment of the present application, an electronic device is provided, comprising: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the electronic device implements the blast furnace material distribution control method as described above.

[0014] According to one aspect of an embodiment of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor of a computer, the computer executes the blast furnace burden distribution control method described above.

[0015] Beneficial effects of the present invention: The present invention obtains the current production parameter data of the blast furnace and the current temperature data of the blast furnace edge coal gas flow, inputs the current production parameter data into the blast furnace edge coal gas flow temperature prediction model, obtains the predicted temperature data of the blast furnace edge coal gas flow at a future moment, determines the temperature change trend of the blast furnace edge coal gas flow based on the current temperature data and the predicted temperature data, compares the temperature change trend with the preset change trend, determines the blast furnace distribution control strategy according to the comparison result, and controls the blast furnace for distribution according to the distribution control strategy. The above process predicts the predicted temperature data of the blast furnace edge coal gas flow at a future moment according to the current production parameter data, determines the temperature change trend of the blast furnace edge coal gas flow based on the current temperature data and the predicted temperature data, and determines the distribution control strategy based on the comparison result of the temperature change trend with the preset change trend, provides a reference for the blast furnace distribution control, and reduces the energy consumption of the blast furnace ironmaking process.

[0016] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings herein are incorporated into the specification and constitute a part of the specification, showing embodiments consistent with the present application, and together with the specification, are used to explain the principles of the present application. Obviously, the drawings described below are only some embodiments of the present application, and for those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0018] Figure 1 is a schematic diagram of an exemplary system architecture shown in an exemplary embodiment of the present application;

[0019] Figure 2 is a flow chart of a blast furnace burden distribution control method shown in an exemplary embodiment of the present application;

[0020] Figure 3 is a flow chart of a blast furnace burden distribution control method shown in another exemplary embodiment of the present application;

[0021] Figure 4 is a flow chart of obtaining a feature parameter data set shown in another exemplary embodiment of the present application;

[0022] Figure 5 is a flowchart showing another exemplary embodiment of the present application for predicting the temperature of the gas flow at the edge of a blast furnace and determining a distribution control strategy;

[0023] Figure 6 A block diagram of a blast furnace burden distribution control device suitable for implementing an embodiment of the present application is shown;

[0024] Figure 7 A schematic diagram of the structure of a computer system suitable for implementing an electronic device of an embodiment of the present application is shown. DETAILED DESCRIPTION

[0025] Here, exemplary embodiments will be described in detail, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are only examples of devices and methods consistent with some aspects of the present application as detailed in the attached claims.

[0026] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0027] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to actual conditions.

[0028] The term "multiple" as used in this application refers to two or more than two. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the related objects are in an "or" relationship.

[0029] The technical solution of the embodiment of the present application involves related technologies such as welding of steel structure parts, which is specifically described by the following embodiments:

[0030] Figure 1 It is a schematic diagram of an exemplary system architecture shown in an exemplary embodiment of the present application.

[0031] Reference Figure 1As shown, the system architecture may include a data storage device 101 and a computer device 102. The computer device 102 may be at least one of a desktop graphics processing unit (GPU) computer, a GPU computing cluster, a neural network computer, etc. Relevant technicians may use the computer device 102 to obtain the current production parameter data of the blast furnace and the current temperature data of the blast furnace edge gas flow, input the current production parameter data into the blast furnace edge gas flow temperature prediction model, obtain the predicted temperature data of the blast furnace edge gas flow at a future moment, determine the temperature change trend of the blast furnace edge gas flow based on the current temperature data and the predicted temperature data, compare the temperature change trend with the preset change trend, determine the blast furnace distribution control strategy according to the comparison result, and control the blast furnace to distribute the material according to the distribution control strategy. The data storage device 101 is used to store the current production parameter data of the blast furnace and the current temperature data of the coal gas flow at the edge of the blast furnace. In this embodiment, the data storage device 101 uses a read-only memory (ROM) or a random access memory (RAM) to store the current production parameter data of the blast furnace and the current temperature data of the coal gas flow at the edge of the blast furnace, and provides them to the computer device 102 for processing.

[0032] Schematically, after obtaining the current production parameter data of the blast furnace from the data storage device 101 and the current temperature data of the blast furnace edge gas flow, the computer device 102 inputs the current production parameter data into the blast furnace edge gas flow temperature prediction model to obtain the predicted temperature data of the blast furnace edge gas flow at a future time, determines the temperature change trend of the blast furnace edge gas flow based on the current temperature data and the predicted temperature data, compares the temperature change trend with the preset change trend, determines the blast furnace's charging control strategy according to the comparison result, and controls the blast furnace for charging according to the charging control strategy. The above process predicts the predicted temperature data of the blast furnace edge gas flow at a future time according to the current production parameter data, determines the temperature change trend of the blast furnace edge gas flow based on the current temperature data and the predicted temperature data, and determines the charging control strategy based on the comparison result of the temperature change trend with the preset change trend, thereby providing a reference for the blast furnace charging control and reducing the energy consumption of the blast furnace ironmaking process.

[0033] It should be noted that the blast furnace charge distribution control method provided in the embodiment of the present application is generally executed by the computer device 102 , and accordingly, the blast furnace charge distribution control device is generally arranged in the computer device 102 .

[0034] The implementation details of the technical solution of the embodiment of the present application are described in detail below:

[0035] Figure 2is a flow chart of a blast furnace burden distribution control method shown in an exemplary embodiment of the present application. The blast furnace burden distribution control method can be executed by a computing and processing device. The computing and processing device can be Figure 1 The computer device 102 shown in FIG. Figure 2 As shown, the blast furnace burden distribution control method at least includes steps S210 to S240, which are described in detail as follows:

[0036] In step S210, the current production parameter data of the blast furnace and the current temperature data of the gas flow at the edge of the blast furnace are obtained. In one embodiment of the present application, the current production parameter data include furnace top pressure, furnace top temperature, riser pressure, riser temperature, cross temperature measurement data, gas utilization rate, total pressure difference, wind temperature, wind pressure, furnace gas flow, ore-coke ratio, coke line and ore line, etc.

[0037] In step S220, the current production parameter data is input into the blast furnace edge gas flow temperature prediction model to obtain the predicted temperature data of the blast furnace edge gas flow at the future time. In one embodiment of the present application, the future time is set according to the actual situation. For example, if a prediction cycle of the blast furnace edge gas flow temperature is 6 hours, the future time can be 0.5 hours, 1 hour, 2 hours, etc. after the current time. The blast furnace edge coal gas flow temperature prediction model is obtained by training a preset coal gas flow temperature prediction model with sample data, and the sample data includes historical production parameter data of the blast furnace and historical temperature data of the coal gas flow at the edge of the blast furnace. The process of obtaining the blast furnace edge coal gas flow temperature prediction model by training the preset coal gas flow temperature prediction model with sample data includes: merging the historical production parameter data and the historical temperature data to obtain a merged data set; preprocessing each type of parameter data in the merged data set to obtain a preprocessed data set, and the preprocessing includes filling missing values, deleting outliers, and / or normalization calculation; inputting the preprocessed data set into a preset parameter type importance ranking model to obtain a parameter type importance ranking sequence in the preprocessed data set, and filtering out a target parameter type from the parameter type importance ranking sequence, and the target parameter type includes a preset number of parameter types that rank high in the parameter type importance ranking sequence; combining the data corresponding to the target parameter type to obtain a characteristic parameter data set; training the preset coal gas flow temperature prediction model with the characteristic parameter data set to obtain a blast furnace edge coal gas flow temperature prediction model.

[0038] In step S230, the temperature change trend of the blast furnace edge gas flow is determined based on the current temperature data and the predicted temperature data. In one embodiment of the present application, the temperature change trend includes a stable trend, an upward trend and a downward trend. Based on the current temperature data and the predicted temperature data, the process of determining the temperature change trend of the blast furnace edge gas flow includes: calculating the difference between the predicted temperature data and the current temperature data; if the absolute value of the difference is less than or equal to the preset difference threshold, the temperature change trend is determined to be a stable trend; if the absolute value of the difference is greater than the preset difference threshold, and the predicted temperature data is greater than the current temperature data, the temperature change trend is determined to be an upward trend; if the absolute value of the difference is greater than the preset difference threshold, and the predicted temperature data is less than the current temperature data, the temperature change trend is determined to be a downward trend.

[0039] In step S240, the temperature change trend is compared with the preset change trend, and the charge distribution control strategy of the blast furnace is determined according to the comparison result, and the blast furnace is controlled to distribute the charge according to the charge distribution control strategy. In one embodiment of the present application, the comparison result includes consistent change trends and inconsistent change trends, and the charge distribution control strategy includes maintaining the current charge distribution operation parameter data and adjusting the current charge distribution operation parameter data, predicting the predicted temperature data of the blast furnace edge gas flow at a future time according to the current production parameter data, determining the temperature change trend of the blast furnace edge gas flow based on the current temperature data and the predicted temperature data, and determining the charge distribution control strategy based on the comparison result of the temperature change trend and the preset change trend, providing a reference for the blast furnace charge distribution control, and reducing the energy consumption of the blast furnace ironmaking process.

[0040] In one embodiment of the present application, if the sample data includes historical production parameter data of a blast furnace and historical temperature data of a blast furnace edge gas flow, the process of training a preset gas flow temperature prediction model using the sample data to obtain a blast furnace edge gas flow temperature prediction model includes:

[0041] The historical production parameter data and the historical temperature data are merged to obtain a merged data set. In one embodiment of the present application, the process of merging the historical production parameter data and the historical temperature data to obtain a merged data set includes: calculating the correlation coefficient between the historical production parameter data and the historical temperature data to obtain multiple first correlation coefficients; using the first correlation coefficient greater than or equal to the preset correlation threshold as the first target coefficient, and using the historical production parameter data obtained by calculating the first target coefficient as the target production parameter data; determining the temperature data at different times from the historical temperature data, and calculating the correlation coefficient between the target production parameter data and the temperature data at different times to obtain multiple second correlation coefficients; using the maximum coefficient among the multiple second correlation coefficients as the second target coefficient, and merging the target production parameter data obtained by calculating the second target coefficient with the temperature data obtained by calculating the second target coefficient to obtain a merged data set. By calculating the correlation coefficient between historical production parameter data and historical temperature data, target production parameter data with a high correlation with historical temperature data is obtained. By using the correlation coefficient between the target production parameter data and the temperature data at different times, the target production parameter data with the highest correlation with the temperature data at each moment is obtained. The temperature data at each moment and the target production parameter data with the highest correlation with the temperature data at the corresponding moment are merged, fully considering that the target production parameter data has a lag factor on the historical temperature data, thereby improving the correlation between the target production parameter data and the temperature data at different times in the merged data set in the time dimension, which is beneficial to improving the training effect of the preset coal gas flow temperature prediction model.

[0042] Preprocess each type of parameter data in the merged data set to obtain a preprocessed data set. In one embodiment of the present application, the preprocessing includes filling missing values, deleting outliers, and / or normalization calculation. Preprocess each type of parameter data in the merged data set to obtain a preprocessed data set. The process includes: comparing the number of each type of parameter data in the merged data set with the first preset sample number and the second preset sample number. If there is any type of parameter data whose number is less than the first preset sample number and greater than the second preset sample number, fill any type of parameter data until the number of each type of parameter data is greater than or equal to the first preset sample number to obtain a filled data set; the filling method includes an average filling method and a nearest neighbor value filling method; based on the minimum value, lower quartile, upper quartile and maximum value of each type of parameter data in the filled data set, determine the corresponding type parameter data range; delete the sample point data in each type of parameter data that exceeds the type parameter data range, and fill the deleted sample point data to obtain an updated data set; perform normalization calculation on each type of parameter data in the updated data set, and combine each type of parameter data after normalization calculation to obtain a preprocessed data set. By preprocessing each type of parameter data in the merged data set, the integrity and accuracy of the data in the merged data set are improved, which is beneficial to improving the training effect of the preset coal gas flow temperature prediction model.

[0043] The preprocessed data set is input into the preset parameter type importance ranking model to obtain the parameter type importance ranking sequence in the preprocessed data set, and the target parameter type is screened out from the parameter type importance ranking sequence. In one embodiment of the present application, the parameter type importance ranking is embodied in the form of a numerical value and is displayed by drawing a parameter type importance ranking bar chart. The target parameter type includes a preset number of parameter types that rank high in the parameter type importance ranking sequence. The preset number is set according to the actual situation and is not specifically limited here. The preset parameter type importance ranking model can be a random forest model or other machine learning models. By calling the random forest model interface, a random forest model is obtained, and the importance of the parameter types in the preprocessed data set is sorted by the random forest model, so as to facilitate the screening of target parameter types with higher importance.

[0044] The data corresponding to the target parameter type are combined to obtain a characteristic parameter data set. In one embodiment of the present application, the characteristic parameter data set includes data corresponding to target parameter types with higher importance. Training the preset gas flow temperature prediction model through the characteristic parameter data set is conducive to reducing the complexity of model training and improving the accuracy and speed of model training.

[0045] The preset coal gas flow temperature prediction model is trained by the characteristic parameter data set to obtain the blast furnace edge coal gas flow temperature prediction model. In one embodiment of the present application, the preset coal gas flow temperature prediction model can be an XGBoost (eXtremeGradient Boosting) regression model or other machine learning models, which are not specifically limited here. The XGBoost regression model is obtained by calling the XGBoost regression model interface.

[0046] In one embodiment of the present application, the process of merging historical production parameter data and historical temperature data to obtain a merged data set includes:

[0047] The correlation coefficient between the historical production parameter data and the historical temperature data is calculated to obtain multiple first correlation coefficients. In one embodiment of the present application, the correlation coefficient between the historical production parameter data and the historical temperature data may be a cosine similarity or a Pearson correlation coefficient. Taking the Pearson correlation coefficient as an example, if the historical production parameter data includes multiple types of parameter data, the expression of the correlation coefficient between the historical production parameter data and the historical temperature data is as follows:

[0048]

[0049] Among them, r 1,j represents the correlation coefficient between the jth parameter data in the first type parameter in the historical production parameter data and the jth temperature data in the historical temperature data, x 1,j Indicates the jth parameter data of the first type parameter in the historical production parameter data, Represents the average value of the first type of parameter data in the historical production parameter data, y j represents the jth temperature data in the historical temperature data, It represents the average value of historical temperature data, and n represents the number of parameter data in the first type of parameters in the historical production parameter data or the number of data in the historical temperature data.

[0050] In this embodiment, the average value calculation formula of the first type parameter data in the historical production parameter data is as follows:

[0051]

[0052] in, represents the average value of the first type parameter data in the historical production parameter data, n represents the number of parameter data in the first type parameter, x 1,j Represents the jth parameter data of the first type of parameters in the historical production parameter data.

[0053] In this embodiment, the calculation formula of the average value of historical temperature data is as follows:

[0054]

[0055] in, represents the average value of historical temperature data, n represents the number of data in the historical temperature data, y j Represents the jth temperature data in the historical temperature data.

[0056] The first correlation coefficient that is greater than or equal to the preset correlation threshold is used as the first target coefficient, and the historical production parameter data obtained by calculating the first target coefficient is used as the target production parameter data. In one embodiment of the present application, the preset correlation threshold can be set according to actual conditions and is not specifically limited here. By comparing the first correlation coefficient with the preset correlation threshold, and using the historical production parameter data obtained by calculating the first target coefficient as the target production parameter data, the historical production parameter data is screened, so that the obtained target production parameter data has a high correlation with the historical production parameter data.

[0057] Determine the temperature data at different times from the historical temperature data, and calculate the correlation coefficient between the target production parameter data and the temperature data at different times to obtain multiple second correlation coefficients. In one embodiment of the present application, if the target production parameter data includes multiple types of parameter data, the expression of the correlation coefficient between the target production parameter data and the temperature data at different times is as follows:

[0058]

[0059] Among them, r 1,t represents the correlation coefficient between the jth parameter data in the first type parameter in the target production parameter data and its temperature data with time interval t, x 1,j Indicates the jth parameter data of the first type parameter in the target production parameter data, Represents the average value of the first type parameter data in the target production parameter data, y t represents the temperature data with a time interval t from the j-th parameter data of the first type parameter in the target production parameter data, represents the average value of historical temperature data, n1 represents the number of parameter data in the first type of parameters in the target production parameter data, T is an integer multiple of the time interval t, and the time interval t is determined according to the sampling interval. For example, the time interval t can be a few seconds, a few minutes or a few hours.

[0060] In this embodiment, the expression of the average value of the first type parameter data in the target production parameter data is as follows:

[0061]

[0062] in, Indicates the average value of the first type parameter data in the target production parameter data, x 1,j It represents the jth parameter data of the first type parameter in the target production parameter data, and n1 represents the number of parameter data of the first type parameter in the target production parameter data.

[0063] The maximum coefficient among the multiple second correlation coefficients is used as the second target coefficient, and the target production parameter data for calculating the second target coefficient and the temperature data for calculating the second target coefficient are merged to obtain a merged data set. In one embodiment of the present application, if the target production parameter data includes multiple types of parameter data, the correlation coefficient between each parameter data of each type of parameter in the target production parameter data and one of the temperature data is the largest, then the parameter data for each type of parameter for which the maximum correlation coefficient is calculated and the temperature data for each type of parameter for which the maximum correlation coefficient is calculated are merged, fully considering that the target production parameter data has a lag factor on the historical temperature data, thereby improving the temporal correlation between the target production parameter data and the temperature data at different times in the merged data set, which is conducive to improving the training effect of the preset coal gas flow temperature prediction model.

[0064] In one embodiment of the present application, the process of preprocessing each type of parameter data in the merged data set to obtain the preprocessed data set includes:

[0065] The number of each type of parameter data in the merged data set is compared with the first preset sample number and the second preset sample number. If the number of any type of parameter data is less than the first preset sample number and greater than the second preset sample number, the parameter data of any type is filled until the number of each type of parameter data is greater than or equal to the first preset sample number, thereby obtaining a filled data set. In one embodiment of the present application, the filling method includes an average value filling method and a nearest neighbor value filling method. The first preset sample number and the second preset sample number are set according to actual conditions. If the number of a certain type of parameter data is less than the second preset sample number, all parameter data of this type are deleted; if the number of a certain type of parameter data is greater than or equal to the second preset sample number, and the number of parameter data of this type is less than the third preset sample number, then the missing type of the parameter data of this type is determined to be long-term missing, and the average value filling method is used to fill the missing data of the parameter data of this type. The third preset sample number is less than the first preset sample number and greater than the second preset sample number; if the number of a certain type of parameter data is greater than or equal to the third preset sample number, and the number of parameter data of this type is less than the first preset sample number, then the missing type of the parameter data of this type is determined to be short-term missing or point missing, and the nearest neighbor value filling method is used to fill the missing data of the parameter data of this type.

[0066] In another embodiment of the present application, when the number of parameter data of a certain type is less than the first preset sample number, the difference between the first preset sample number and the number of parameter data of this type is taken as the number of missing data. If the proportion of missing data in the preset sample number is less than 5%, the missing type of parameter data of this type is determined to be short-term missing or point missing, and the missing data of parameter data of this type is filled using the nearest neighbor value filling method; if the proportion of missing data in the preset sample number is greater than or equal to 5% and less than or equal to 60%, the missing type of parameter data of this type is determined to be long-term missing, and the missing data of parameter data of this type is filled using the average value filling method; if the proportion of missing data in the preset sample number is greater than 60%, all parameter data of this type is deleted.

[0067] Based on the minimum value, lower quartile, upper quartile and maximum value of each type of parameter data in the filled data set, the corresponding type parameter data range is determined; the sample point data of each type of parameter data that exceeds the type parameter data range is deleted, and the deleted sample point data is filled to obtain an updated data set. In one embodiment of the present application, the minimum value, lower quartile, median, upper quartile, maximum value and interquartile range of each type of parameter data are calculated, and the process of determining the range of the corresponding type of parameter data is realized by means of a box plot in multivariate statistical analysis. The lower quartile is represented by Q1, the upper quartile is represented by Q3, and the interquartile range is represented by IQR. A line segment identical to the median line (the horizontal line where the median is located) is drawn at Q1-3IQR as the lower limit of the range of a certain type of parameter data. A line segment identical to the median line is drawn at Q3+3IQR as the upper limit of the range of a certain type of parameter data. Sample point data outside the range of the type of parameter data are recorded as abnormal data. The sample points marked as abnormal data are filled by the average value filling method. The abnormal data is eliminated by deleting the sample point data of each type of parameter data that exceeds the range of the type of parameter data to which it belongs, thereby avoiding inaccurate collected data due to damage to the furnace sensor, which affects the training effect of the preset coal gas flow temperature prediction model.

[0068] Normalization calculation is performed on each type of parameter data in the updated data set, and each type of parameter data after normalization calculation is combined to obtain a preprocessed data set. In one embodiment of the present application, the expression for normalization calculation of each type of parameter data in the updated data set is as follows:

[0069]

[0070] in, Indicates the normalized calculated value of the jth parameter data in the i-th type parameter in the updated data set, x i,j Indicates updating the jth parameter data of the i-th type parameter in the data set, x i represents the average value of the i-th type parameter data in the updated data set, σ i Indicates the standard deviation of the i-th type parameter data in the updated dataset.

[0071] In this embodiment, the calculation formula for the average value of the i-th type parameter data is as follows:

[0072]

[0073] in, Indicates the average value of the i-th type parameter data in the updated data set, x i,j Indicates the jth parameter data of the i-th type parameter in the updated data set, and m indicates the number of i-th type parameter data in the updated data set.

[0074] In this embodiment, the calculation formula for updating the standard deviation of the i-th type parameter data in the data set is as follows:

[0075]

[0076] Among them, σ i represents the standard deviation of the i-th type parameter data in the updated data set, m represents the number of i-th type parameter data in the updated data set, Indicates the average value of the i-th type parameter data in the updated data set, x i,j Indicates updating the j-th parameter data of the i-th type parameter in the data set.

[0077] In this embodiment, normalization calculation is performed on each type of parameter data in the updated data set, which is helpful to reduce the dimensional difference between the historical production parameter data and the historical temperature data in the updated data set.

[0078] In one embodiment of the present application, the process of training a preset coal gas flow temperature prediction model through a characteristic parameter data set to obtain a blast furnace edge coal gas flow temperature prediction model includes:

[0079] The feature parameter data set is divided into a data training set and a data test set. In one embodiment of the present application, the division ratio of the data training set and the data test set is set according to actual conditions. For example, the data training set accounts for 70% of the feature parameter data set, and the data test set accounts for 30% of the feature parameter data set.

[0080] The preset gas flow temperature prediction model is trained by the data training set to obtain the trained gas flow temperature prediction model. In one embodiment of the present application, the preset gas flow temperature prediction model is provided with parameters such as preset column sampling, preset learning rate, preset maximum tree depth, preset number of trees, preset cross-validation multiplicity (i.e. preset number threshold), wherein the preset column sampling is [0,1,0.1], i.e. the minimum value of the preset column sampling is 0, the maximum value is 1, and the step length is 0.1, the preset learning rate is [0,1,0.05], i.e. the minimum value of the preset learning rate is 0, the maximum value is 1, and the step length is 0.05, the preset maximum tree depth is [1,100,10], i.e. the minimum value of the preset maximum tree depth is 0, the maximum value is 100, and the step length is 10, the preset number of trees is [1,300,50], i.e. the maximum value of the preset number of trees is 1, the minimum value is 300, the step length is 50, and the preset cross-validation multiplicity is 5.

[0081] The data test set is input into the trained coal gas flow temperature prediction model to obtain the evaluation coefficient of the trained coal gas flow temperature prediction model. In one embodiment of the present application, the evaluation coefficient includes a coefficient of determination and a trend hit rate, etc.

[0082] With the goal of maximizing the evaluation coefficient, the trained coal gas flow temperature prediction model is trained through the characteristic parameter data set until the number of training times reaches a preset threshold, and the blast furnace edge coal gas flow temperature prediction model is obtained. In one embodiment of the present application, the process of training the trained coal gas flow temperature prediction model through the characteristic parameter data set includes: re-dividing the data training set and the data test set according to the division ratio, the re-divided data training set is different from the previously divided data training set, the re-divided data test set is different from the previously divided data test set, the trained coal gas flow temperature prediction model is trained through the re-divided data training set to obtain a re-trained coal gas flow temperature prediction model; the re-divided data test set is input into the re-trained coal gas flow temperature prediction model to obtain the evaluation coefficient again, and the above method is used to train the trained coal gas flow temperature prediction model. The formula continues to train the re-trained coal gas flow temperature prediction model until the number of training times reaches the preset threshold, and the blast furnace edge coal gas flow temperature prediction model is obtained, so as to continuously optimize the parameters in the preset coal gas flow temperature prediction model and improve the prediction effect of the blast furnace edge coal gas flow temperature prediction model. After continuously optimizing the parameters in the preset coal gas flow temperature prediction model, the optimized column sampling is 0.7, the optimized learning rate is 0.05, the optimized maximum tree depth is 10, the optimized number of trees is 200, the optimized determination coefficient is 0.741, and the optimized trend hit rate is 0.725.

[0083] In one embodiment of the present application, the process of determining the temperature change trend of the blast furnace edge gas flow based on the current temperature data and the predicted temperature data includes:

[0084] Calculate the difference between the predicted temperature data and the current temperature data. In one embodiment of the present application, after obtaining the difference, the temperature change trend is determined by fully considering the absolute value of the difference and the size relationship between the predicted temperature data and the current temperature data.

[0085] If the absolute value of the difference is less than or equal to the preset difference threshold, the temperature change trend is determined to be a stable trend. In one embodiment of the present application, the preset difference threshold is set according to actual conditions and is not specifically limited here.

[0086] If the absolute value of the difference is greater than a preset difference threshold, and the predicted temperature data is greater than the current temperature data, the temperature change trend is determined to be an upward trend. In one embodiment of the present application, when the absolute value of the difference is greater than a preset difference threshold, and the predicted temperature data is greater than the current temperature data, it indicates that the blast furnace edge gas flow temperature is in an upward trend.

[0087] If the absolute value of the difference is greater than the preset difference threshold, and the predicted temperature data is less than the current temperature data, the temperature change trend is determined to be a downward trend. In one embodiment of the present application, when the absolute value of the difference is greater than the preset difference threshold, and the predicted temperature data is less than the current temperature data, it indicates that the blast furnace edge gas flow temperature is in a downward trend.

[0088] In one embodiment of the present application, if the current production parameter data includes current material distribution operation parameter data, the material distribution control strategy of the blast furnace is determined according to the comparison result, and the process of controlling the material distribution of the blast furnace according to the material distribution control strategy includes:

[0089] If the comparison result shows that the change trend is consistent, the current distribution operation parameter data will be maintained as the distribution control strategy, and the blast furnace will be controlled to distribute the charge according to the current distribution operation parameter data. In one embodiment of the present application, if the comparison result shows that the change trend is consistent, indicating that the current distribution operation parameter data meets the preset change trend, the blast furnace will continue to be controlled to distribute the charge according to the current distribution operation parameter data.

[0090] If the comparison result is that the change trend is inconsistent, the current distribution operation parameter data is adjusted as the distribution control strategy, and the blast furnace is controlled to distribute the material according to the adjusted distribution operation parameter data. In one embodiment of the present application, if the comparison result is that the change trend is inconsistent, it means that the current distribution operation parameter data meets the preset change trend, and the current distribution operation parameter data needs to be adjusted. The method for adjusting the current distribution operation parameter data is determined according to the actual situation. After controlling the blast furnace for charging according to the adjusted charging operation parameter data, the current production parameter data of the blast furnace and the current temperature data of the coal gas flow at the edge of the blast furnace are obtained again; and the current production parameter data obtained again are input into the coal gas flow temperature prediction model at the edge of the blast furnace to obtain the predicted temperature data of the coal gas flow at the edge of the blast furnace at a future moment; based on the current temperature data obtained again and the predicted temperature data obtained again, the temperature change trend of the coal gas flow at the edge of the blast furnace is determined again; the temperature change trend determined again is compared with the preset change trend, and the charging control strategy of the blast furnace is determined again according to the comparison result; the blast furnace is controlled for charging according to the charging control strategy determined again, and the above-mentioned blast furnace charging control method is repeated within a prediction cycle to realize continuous control of the blast furnace charging. The preset change trend is set according to different time periods in the prediction cycle. For example, if the time period between the current moment and the future moment belongs to the front period divided in the prediction cycle, the preset change trend is determined according to the expected change of the coal gas flow temperature at the edge of the blast furnace in the front period; if the time period between the current moment and the future moment belongs to the middle period divided in the prediction cycle, the preset change trend is determined according to the expected change of the coal gas flow temperature at the edge of the blast furnace in the middle period; if the time period between the current moment and the future moment belongs to the back period divided in the prediction cycle, the preset change trend is determined according to the expected change of the coal gas flow temperature at the edge of the blast furnace in the back period.

[0091] Figure 3 is a flow chart of a blast furnace burden control method shown in another exemplary embodiment of the present application. Figure 3As shown, the blast furnace charge distribution control method includes: (1) determining the production parameter type related to the historical temperature data from the relevant production parameter data of blast furnace ironmaking, and constructing a historical production parameter data set based on the historical data corresponding to the relevant production parameter type; (2) merging the historical production parameter data in the historical production parameter data set with the historical temperature data to obtain a merged data set; preprocessing each type of parameter data in the merged data set to obtain a preprocessed data set; (3) inputting the preprocessed data set into a preset parameter type importance ranking model to obtain a parameter type importance ranking sequence in the preprocessed data set, and filtering out the target parameter type from the parameter type importance ranking sequence, combining the data corresponding to the target parameter type to obtain a characteristic parameter data set; (4) training a preset coal gas flow temperature prediction model through the characteristic parameter data set to obtain a blast furnace edge coal gas flow temperature prediction model; (5) determining the temperature change trend of the blast furnace edge coal gas flow based on the current temperature data and the predicted temperature data; comparing the temperature change trend with the preset change trend, and determining the blast furnace charge distribution control strategy according to the comparison result.

[0092] Figure 4 is a flowchart of obtaining a feature parameter data set shown in another exemplary embodiment of the present application, such as Figure 4 As shown, the process of obtaining the characteristic parameter data set includes: (1) determining the production parameter type related to the historical temperature data from the relevant production parameter data of blast furnace ironmaking, and constructing the historical production parameter data set based on the historical data corresponding to the relevant production parameter type; (2) determining the target production parameter data from the historical production parameter data: calculating the correlation coefficient between the historical production parameter data and the historical temperature data to obtain multiple first correlation coefficients; taking the first correlation coefficient greater than or equal to the preset correlation threshold as the first target coefficient, and taking the historical production parameter data for which the first target coefficient is calculated as the target production parameter data; (3) determining the optimal time lag between the target production parameter data and the historical temperature data: calculating the time lag between each type of target parameter data and the temperature data at different times; Pearson correlation coefficient, and the time difference between the target production parameter data and the temperature data corresponding to the maximum Pearson correlation coefficient in each type is taken as the optimal time lag; (4) the target production parameter data and the temperature data corresponding to the optimal time lag in each type are spliced ​​to obtain a merged data set; (5) the outliers in each type of parameter in the merged data set are deleted using the box plot in multivariate statistical analysis to obtain a preprocessed data set; (6) the parameter data of each type in the merged data set are standardized using the standard score method to obtain a preprocessed data set; (7) the preprocessed data set is input into a preset parameter type importance ranking model to obtain a parameter type importance ranking sequence in the preprocessed data set; (8) the target parameter type is screened out from the parameter type importance ranking sequence.

[0093] Figure 5 FIG. 1 is another exemplary embodiment of the present application showing a flow chart for predicting the temperature of the gas flow at the edge of a blast furnace and determining a distribution control strategy, such as Figure 5 As shown, the process of predicting the temperature of the coal gas flow at the edge of the blast furnace and determining the distribution control strategy includes: (1) training the preset coal gas flow temperature prediction model through the characteristic parameter data set to obtain the blast furnace edge coal gas flow temperature prediction model; (2) inputting the current production parameter data into the blast furnace edge coal gas flow temperature prediction model to obtain the predicted temperature data of the blast furnace edge coal gas flow at the future moment; (3) based on the current temperature data and the predicted temperature data, determining the temperature change trend of the coal gas flow at the edge of the blast furnace, and judging whether the temperature change trend conforms to the preset change trend. If the temperature change trend conforms to the preset change trend, the blast furnace is controlled to distribute according to the current distribution operation parameter data; if the temperature change trend does not conform to the preset change trend, the blast furnace is controlled to distribute according to the adjusted distribution operation parameter data.

[0094] In an exemplary embodiment of the present application, the process of training a preset coal gas flow temperature prediction model using a characteristic parameter data set includes: (1) determining a parameter range in the preset coal gas flow temperature prediction model; (2) determining a cross-validation multiplicity (a preset number threshold); and (3) optimizing the parameter range in the preset coal gas flow temperature prediction model using a grid search method to obtain optimized model parameters.

[0095] In another exemplary embodiment of the present application, the process of inputting current production parameter data into a blast furnace edge coal gas flow temperature prediction model to obtain predicted temperature data of the blast furnace edge coal gas flow at a future time includes: (1) determining the blast furnace edge coal gas flow temperature prediction model through optimized model parameters; (2) inputting current production parameter data into a blast furnace edge coal gas flow temperature prediction model to obtain predicted temperature data of the blast furnace edge coal gas flow at a future time.

[0096] In another exemplary embodiment of the present application, by performing correlation analysis on the historical production parameter data and historical temperature data of the blast furnace, the target production parameter data is obtained, and the time-lag correlation analysis is performed on the target production parameter data and the temperature data at different times, the production parameter data with the strongest correlation with the temperature data at each time in the time dimension is obtained, and the temperature data with the strongest correlation is merged with the production parameter data to obtain a merged data set, and the sample data set is reconstructed, which effectively improves the quality of the sample data. The parameter types in the preprocessed data set are sorted by importance by a preset random forest model, which reduces the dimension of the parameter types in the preprocessed data set and effectively reduces the complexity of training the preset gas flow temperature prediction model. By inputting the current production parameter data into the blast furnace edge gas flow temperature prediction model, the real-time prediction of the blast furnace edge gas flow temperature is realized, and the temperature change trend of the blast furnace edge gas flow is determined based on the current temperature data and the predicted temperature data, and the comparison result of the temperature change trend and the preset change trend is provided for the blast furnace burden operation.

[0097] The following describes an apparatus embodiment of the present application, which can be used to execute the blast furnace charge distribution control method in the above-mentioned embodiment of the present application. For details not disclosed in the apparatus embodiment of the present application, please refer to the embodiment of the blast furnace charge distribution control method in the above-mentioned embodiment of the present application.

[0098] Figure 6 is a block diagram of a blast furnace burden control device shown in an exemplary embodiment of the present application. The device can be applied to Figure 1 The implementation environment shown in the figure is specifically configured in the computer device 102. The device can also be applied to other exemplary implementation environments and specifically configured in other devices. This embodiment does not limit the implementation environment to which the device is applied.

[0099] like Figure 6 As shown, the exemplary blast furnace burden distribution control device comprises:

[0100] The data acquisition module 601 is used to acquire the current production parameter data of the blast furnace and the current temperature data of the coal gas flow at the edge of the blast furnace;

[0101] The temperature prediction module 602 is used to input the current production parameter data into the blast furnace edge coal gas flow temperature prediction model to obtain the predicted temperature data of the blast furnace edge coal gas flow at a future time; the blast furnace edge coal gas flow temperature prediction model is obtained by training the preset coal gas flow temperature prediction model with sample data;

[0102] The trend determination module 603 is used to determine the temperature change trend of the blast furnace edge coal gas flow based on the current temperature data and the predicted temperature data;

[0103] The charge distribution control module 604 is used to compare the temperature change trend with the preset change trend, determine the charge distribution control strategy of the blast furnace according to the comparison result, and control the charge distribution of the blast furnace according to the charge distribution control strategy.

[0104] In one embodiment of the present application, the current production parameter data include furnace top pressure, furnace top temperature, riser pressure, riser temperature, cross temperature measurement data, gas utilization rate, total pressure difference, wind temperature, wind pressure, furnace belly gas flow, ore-coke ratio, coke line and ore line, etc.

[0105] In one embodiment of the present application, the future moment is set according to the actual situation. For example, a prediction cycle of the blast furnace edge coal gas flow temperature is 6 hours, and the future moment can be 0.5 hours, 1 hour, 2 hours, etc. after the current moment. The blast furnace edge coal gas flow temperature prediction model is obtained by training a preset coal gas flow temperature prediction model with sample data, and the sample data includes historical production parameter data of the blast furnace and historical temperature data of the coal gas flow at the edge of the blast furnace. The process of obtaining the blast furnace edge coal gas flow temperature prediction model by training the preset coal gas flow temperature prediction model with sample data includes: merging the historical production parameter data and the historical temperature data to obtain a merged data set; preprocessing each type of parameter data in the merged data set to obtain a preprocessed data set, and the preprocessing includes filling missing values, deleting outliers, and / or normalization calculation; inputting the preprocessed data set into a preset parameter type importance ranking model to obtain a parameter type importance ranking sequence in the preprocessed data set, and filtering out a target parameter type from the parameter type importance ranking sequence, and the target parameter type includes a preset number of parameter types that rank high in the parameter type importance ranking sequence; combining the data corresponding to the target parameter type to obtain a characteristic parameter data set; training the preset coal gas flow temperature prediction model with the characteristic parameter data set to obtain a blast furnace edge coal gas flow temperature prediction model.

[0106] In one embodiment of the present application, the temperature change trend includes a stable trend, an upward trend and a downward trend. Based on the current temperature data and the predicted temperature data, the process of determining the temperature change trend of the blast furnace edge gas flow includes: calculating the difference between the predicted temperature data and the current temperature data; if the absolute value of the difference is less than or equal to the preset difference threshold, the temperature change trend is determined to be a stable trend; if the absolute value of the difference is greater than the preset difference threshold, and the predicted temperature data is greater than the current temperature data, the temperature change trend is determined to be an upward trend; if the absolute value of the difference is greater than the preset difference threshold, and the predicted temperature data is less than the current temperature data, the temperature change trend is determined to be a downward trend.

[0107] In one embodiment of the present application, the comparison results include consistent change trends and inconsistent change trends, and the distribution control strategy includes maintaining the current distribution operation parameter data and adjusting the current distribution operation parameter data, by predicting the predicted temperature data of the blast furnace edge gas flow at a future time based on the current production parameter data, and determining the temperature change trend of the blast furnace edge gas flow based on the current temperature data and the predicted temperature data. Based on the comparison results of the temperature change trend and the preset change trend, the distribution control strategy is determined to provide a reference for blast furnace distribution control and reduce the energy consumption of the blast furnace ironmaking process.

[0108] It should be noted that the blast furnace charge distribution control device provided in the above embodiment and the blast furnace charge distribution control method provided in the above embodiment belong to the same concept, wherein the specific manner in which each module and unit performs the operation has been described in detail in the method embodiment, and will not be repeated here. In practical applications, the blast furnace charge distribution control device provided in the above embodiment can distribute the above functions to different functional modules as needed, that is, divide the internal structure of the device into different functional modules to complete all or part of the functions described above, and this is not limited here.

[0109] An embodiment of the present application also provides an electronic device, comprising: one or more processors; a storage device for storing one or more programs, and when the one or more programs are executed by one or more processors, the electronic device implements the blast furnace material distribution control method provided in the above-mentioned embodiments.

[0110] Figure 7 The structure diagram of the computer system suitable for implementing the electronic device of the embodiment of the present application is shown. It should be noted that: Figure 7 The computer system 700 of the electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0111] like Figure 7 As shown, the computer system 700 includes a central processing unit (CPU) 701, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 702 or the program loaded from the storage part 708 to the random access memory (RAM) 703, such as executing the method in the above embodiment. In the RAM 703, various programs and data required for system operation are also stored. The CPU 701, the ROM 702 and the RAM 703 are connected to each other through the bus 704. The input / output (I / O) interface 705 is also connected to the bus 704.

[0112] The following components are connected to the I / O interface 705: an input section 706 including a keyboard, a mouse, etc.; an output section 707 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 708 including a hard disk, etc.; and a communication section 709 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to the I / O interface 705 as needed. A removable medium 711, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 710 as needed so that a computer program read therefrom is installed into the storage section 708 as needed.

[0113] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication section 709, and / or installed from a removable medium 711. When the computer program is executed by a central processing unit (CPU) 701, various functions defined in the system of the present application are executed.

[0114] It should be noted that the computer-readable medium shown in the embodiment of the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, wherein a computer-readable computer program is carried. This propagated data signal can take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. A computer program contained on a computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0115] The flowchart and block diagram in the accompanying drawings illustrate the possible architecture, functions and operations of the system, method and computer program product according to various embodiments of the present application. Wherein, each box in the flowchart or block diagram can represent a module, a program segment, or a part of the code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0116] The units involved in the embodiments described in this application may be implemented by software or hardware, and the units described may also be set in a processor. The names of these units do not, in some cases, constitute limitations on the units themselves.

[0117] Another aspect of the present application provides a computer-readable storage medium on which computer-readable instructions are stored. When the computer-readable instructions are executed by a processor of a computer, the computer executes the blast furnace charge distribution control method provided in the above-mentioned embodiments. The computer-readable storage medium may be included in the electronic device described in the above-mentioned embodiments, or may exist independently without being assembled into the electronic device.

[0118] It should be noted that, although several modules or units of the equipment for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into being embodied by multiple modules or units.

[0119] Through the description of the above implementation methods, it is easy for those skilled in the art to understand that the example implementation methods described here can be implemented by software or by combining software with necessary hardware. Therefore, the technical solution according to the implementation methods of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the implementation methods of the present application.

[0120] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the embodiments disclosed herein. The present application is intended to cover any variations, uses or adaptations of the present application, which follow the general principles of the present application and include common knowledge or customary technical means in the art that are not disclosed in the present application.

[0121] It should be understood that the above content is only a preferred exemplary embodiment of the present application and is not intended to limit the implementation scheme of the present application. Ordinary technicians in this field can easily make corresponding changes or modifications based on the main concept and spirit of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection required by the claims.

Claims

1. A blast furnace charge distribution control method, characterized in that: include: Obtaining current production parameter data of the blast furnace and current temperature data of the coal gas flow at the edge of the blast furnace; Input the current production parameter data into a blast furnace edge coal gas flow temperature prediction model to obtain predicted temperature data of the blast furnace edge coal gas flow at a future time; the blast furnace edge coal gas flow temperature prediction model is obtained by training a preset coal gas flow temperature prediction model with sample data; Determine the temperature change trend of the blast furnace edge coal gas flow based on the current temperature data and the predicted temperature data; The temperature change trend is compared with a preset change trend, a charge distribution control strategy of the blast furnace is determined according to the comparison result, and the blast furnace is controlled to distribute charge according to the charge distribution control strategy.

2. The blast furnace charge distribution control method according to claim 1, characterized in that: If the sample data includes historical production parameter data of the blast furnace and historical temperature data of the blast furnace edge gas flow, the process of training a preset gas flow temperature prediction model through the sample data to obtain a blast furnace edge gas flow temperature prediction model includes: Merging the historical production parameter data and the historical temperature data to obtain a merged data set; Preprocessing each type of parameter data in the merged data set to obtain a preprocessed data set, wherein the preprocessing includes filling missing values, deleting outliers, and / or normalization calculation; Inputting the preprocessed data set into a preset parameter type importance ranking model to obtain a parameter type importance ranking sequence in the preprocessed data set, and screening out target parameter types from the parameter type importance ranking sequence, wherein the target parameter types include a preset number of parameter types that rank high in the parameter type importance ranking sequence; Combining the data corresponding to the target parameter type to obtain a characteristic parameter data set; The preset coal gas flow temperature prediction model is trained by using the characteristic parameter data set to obtain the blast furnace edge coal gas flow temperature prediction model.

3. The blast furnace charge distribution control method according to claim 2, characterized in that: The process of merging the historical production parameter data and the historical temperature data to obtain a merged data set includes: Calculating the correlation coefficient between the historical production parameter data and the historical temperature data to obtain a plurality of first correlation coefficients; Using a first correlation coefficient that is greater than or equal to a preset correlation threshold as a first target coefficient, and using historical production parameter data obtained by calculating the first target coefficient as target production parameter data; Determining temperature data at different times from the historical temperature data, and calculating correlation coefficients between the target production parameter data and the temperature data at different times to obtain a plurality of second correlation coefficients; The maximum coefficient among the plurality of the second correlation coefficients is used as the second target coefficient, and the target production parameter data obtained by calculating the second target coefficient and the temperature data obtained by calculating the second target coefficient are merged to obtain the merged data set.

4. The blast furnace charge distribution control method according to claim 2, characterized in that: The process of preprocessing each type of parameter data in the merged data set to obtain the preprocessed data set includes: The number of each type of parameter data in the merged data set is compared with the first preset sample number and the second preset sample number. If the number of any type of parameter data is less than the first preset sample number and greater than the second preset sample number, the any type of parameter data is filled until the number of each type of parameter data is greater than or equal to the first preset sample number, thereby obtaining a filled data set; the filling method includes an average value filling method and a nearest neighbor value filling method; Based on the minimum value, lower quartile, upper quartile and maximum value of each type of parameter data in the filled data set, determine the corresponding type parameter data range; delete the sample point data of each type of parameter data that exceeds the corresponding type parameter data range, and fill the deleted sample point data to obtain an updated data set; Normalization calculation is performed on each type of parameter data in the update data set, and each type of parameter data after the normalization calculation is combined to obtain a preprocessed data set.

5. The blast furnace charge distribution control method according to claim 2, characterized in that: The process of training the preset coal gas flow temperature prediction model by using the characteristic parameter data set to obtain the blast furnace edge coal gas flow temperature prediction model includes: Dividing the characteristic parameter data set into a data training set and a data test set; The preset coal gas flow temperature prediction model is trained by using the data training set to obtain a trained coal gas flow temperature prediction model; Inputting the data test set into the trained coal gas flow temperature prediction model to obtain an evaluation coefficient of the trained coal gas flow temperature prediction model; With the goal of maximizing the evaluation coefficient, the trained coal gas flow temperature prediction model is trained using the characteristic parameter data set until the number of training times reaches a preset threshold, thereby obtaining the blast furnace edge coal gas flow temperature prediction model.

6. The blast furnace charge distribution control method according to any one of claims 1 to 5, characterized in that: The process of determining the temperature change trend of the blast furnace edge gas flow based on the current temperature data and the predicted temperature data includes: Calculating a difference between the predicted temperature data and the current temperature data; If the absolute value of the difference is less than or equal to a preset difference threshold, the temperature change trend is determined to be a stable trend; If the absolute value of the difference is greater than the preset difference threshold, and the predicted temperature data is greater than the current temperature data, then it is determined that the temperature change trend is an upward trend; If the absolute value of the difference is greater than the preset difference threshold, and the predicted temperature data is less than the current temperature data, it is determined that the temperature change trend is a downward trend.

7. The blast furnace charge distribution control method according to any one of claims 1 to 5, characterized in that: If the current production parameter data includes current charging operation parameter data, the charging control strategy of the blast furnace is determined according to the comparison result, and the process of controlling the charging of the blast furnace according to the charging control strategy includes: If the comparison result shows that the change trends are consistent, the current charge distribution operation parameter data is maintained as the charge distribution control strategy, and the blast furnace is controlled to distribute charge according to the current charge distribution operation parameter data; If the comparison result shows that the change trends are inconsistent, the current burden distribution operation parameter data is adjusted as the burden distribution control strategy, and the blast furnace is controlled to distribute burden according to the adjusted burden distribution operation parameter data.

8. A blast furnace burden control device, characterized in that: include: A data acquisition module is used to acquire the current production parameter data of the blast furnace and the current temperature data of the coal gas flow at the edge of the blast furnace; A temperature prediction module is used to input the current production parameter data into a blast furnace edge coal gas flow temperature prediction model to obtain predicted temperature data of the blast furnace edge coal gas flow at a future time; the blast furnace edge coal gas flow temperature prediction model is obtained by training a preset coal gas flow temperature prediction model with sample data; A trend determination module, used for determining the temperature change trend of the blast furnace edge coal gas flow based on the current temperature data and the predicted temperature data; The charge distribution control module is used to compare the temperature change trend with a preset change trend, determine the charge distribution control strategy of the blast furnace according to the comparison result, and control the charge distribution of the blast furnace according to the charge distribution control strategy.

9. An electronic device, characterized in that: include: one or more processors; A storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, enables the electronic device to implement the blast furnace distribution control method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: Computer-readable instructions are stored thereon, and when the computer-readable instructions are executed by a processor of a computer, the computer is caused to execute the blast furnace burden distribution control method according to any one of claims 1 to 7.

Images