A blast furnace utilization rate prediction method and device, electronic equipment and storage medium

Abstract

A blast furnace utilization rate prediction method and device, electronic equipment and storage medium are provided in an embodiment of the present application. The method obtains a production parameter time sequence and a coal gas utilization rate parameter time sequence, aligns the production parameter time sequence and the coal gas utilization rate parameter time sequence, constructs a data regression model according to the aligned production parameter and coal gas utilization rate parameter, and performs data fitting processing on a to-be-predicted production parameter to obtain a coal gas predicted utilization rate parameter. The method determines the time lag length between the obtained production parameter time sequence and the coal gas utilization rate parameter time sequence, aligns the production parameter and the coal gas utilization rate according to the time lag length, eliminates the time lag between the parameters, avoids the occurrence of coupling time difference, and, secondly, constructs a regression model according to the aligned parameters, constructs a regression model based on actual parameters, optimizes the parameter basis of the model training process better, and makes the prediction result more accurate.

Description

Technical Field

[0001] This application relates to the field of computers, and more particularly to a method, apparatus, electronic device, and storage medium for predicting blast furnace utilization. Background Technology

[0002] Blast furnace gas utilization rate is the proportion of carbon monoxide and hydrogen, the reducing components in the gas, participating in the reduction reaction, as well as the proportion of heat absorbed by the furnace charge. It directly reflects the degree of reduction within the furnace and is an important indicator for measuring the efficiency of energy utilization within the blast furnace. Predicting blast furnace gas utilization rate can help identify areas for process optimization and provides significant guidance for energy conservation and consumption reduction in blast furnaces.

[0003] The relevant technologies generally involve preprocessing the collected data and then transmitting it to a pre-built general prediction model to fit and predict the gas utilization rate based on the current state parameters. However, in the actual data processing, the time lag matching degree between the relevant parameters of the blast furnace is not considered, resulting in a coupling reaction time difference between the data at the same time scale in the database. Furthermore, the combination and optimization of the data with the intermediate training model are not considered during the model training process, which makes the practical application reference value of the prediction results slightly lacking. Summary of the Invention

[0004] The purpose of this invention is to provide a method, device, electronic device and storage medium for predicting blast furnace utilization, in order to solve the problem that there is a coupling time difference between parameters on the same time axis, and that the training of the model cannot be well optimized to make the prediction results more accurate.

[0005] This invention provides a method for predicting blast furnace utilization rate. The method includes: acquiring a time series of production parameters and a time series of gas utilization rate parameters, wherein the production parameter time series includes production parameters at multiple time points, and the gas utilization rate parameter time series includes gas utilization rate parameters at multiple time points; determining the time lag between the production parameter time series and the gas utilization rate parameter time series, wherein the time lag is the minimum time difference between the production parameter time series and the gas utilization rate parameter time series; aligning the production parameter time series and the gas utilization rate parameter time series based on the time lag; constructing a data regression model based on the aligned production parameters and gas utilization rate parameters; and performing data fitting processing on the production parameters to be predicted based on the data regression model to obtain the predicted gas utilization rate parameters of the production parameters to be predicted.

[0006] In one embodiment of the present invention, before obtaining the production parameter time series, the method further includes: obtaining initial production parameters; determining the initial production parameters according to preset parameter anomaly determination conditions, wherein the preset parameter anomaly determination conditions include at least one of the following: within the blast furnace shutdown period, within the blast furnace shutdown and reduced ventilation plan period; if the initial production parameters are determined to be abnormal parameters, the abnormal parameters are removed from the initial production parameters to obtain the production parameters.

[0007] In one embodiment of the present invention, before obtaining the initial production parameters, the method further includes: obtaining historical production parameters and historical gas utilization rate parameters, wherein the historical production parameters include at least one parameter category; determining a correlation coefficient between the historical production parameters and the historical gas utilization rate parameters based on the historical production parameters and the historical gas utilization rate parameters; if the correlation coefficient is within a preset correlation determination threshold range, then determining the parameter category of the historical production parameters as a parameter category that is correlated with the historical gas utilization rate parameters; and determining at least some parameters in the parameter category as the initial production parameters.

[0008] In one embodiment of the present invention, if the initial production parameters are determined to be abnormal parameters, the abnormal parameters are removed from the initial production parameters, and the method further includes: setting the removed parameter points to empty; if the parameters in the initial production parameters are determined to be normal parameters, parameters to be filled are obtained based on at least a portion of the normal parameters, and the parameters to be filled are determined as interpolation parameters for the empty parameter points; the interpolation parameters are interpolated to the empty parameter points to obtain the production parameters.

[0009] In one embodiment of the present invention, aligning the production parameter time series and the gas utilization rate parameter time series based on the time lag duration includes: dividing the production parameter time series and the gas utilization rate parameter time series into periods according to a preset period division standard; aligning the production parameter time series and the gas utilization rate parameter time series within each period after division with the period start time as the starting point; determining the time difference between each time point of the production parameter time series and the gas utilization rate parameter time series based on the position of the production parameter at the same time point in the production parameter time series and the position of the gas utilization rate parameter in the gas utilization rate parameter time series; and determining the minimum difference among the time differences at each time point as the time lag duration.

[0010] In one embodiment of the present invention, constructing a data regression model based on aligned production parameters and gas utilization rate parameters includes: constructing a sample dataset based on the aligned production parameters and gas utilization rate parameters; dividing the sample dataset into a training dataset and a test dataset; constructing an initial data regression model based on the training dataset and training it to obtain a trained data regression model; and optimizing the trained data regression model based on the test dataset until the data regression model is obtained.

[0011] In one embodiment of the present invention, constructing an initial data regression model based on the training dataset and training it includes: labeling the production parameters according to the gas utilization rate parameter to obtain production parameters labeled with the gas utilization rate parameter; constructing an initial data regression model based on the production parameters labeled with the gas utilization rate parameter and training it to obtain a trained data regression model.

[0012] This invention also provides a blast furnace utilization rate prediction device, comprising: an acquisition module for acquiring a production parameter time series and a gas utilization rate parameter time series, wherein the production parameter time series includes production parameters at multiple time points, and the gas utilization rate parameter time series includes gas utilization rate parameters at multiple time points; a sequence integration module for aligning the production parameter time series and the gas utilization rate parameter time series based on the time lag between the production parameter time series and the gas utilization rate parameter time series, wherein the time lag is the minimum time difference between the production parameter time series and the gas utilization rate parameter time series; and a data processing module for constructing a data regression model based on the aligned production parameters and gas utilization rate parameters; and performing data fitting processing on the production parameters to be predicted based on the data regression model to obtain the predicted gas utilization rate parameters of the production parameters to be predicted.

[0013] This invention also provides an electronic device, including: one or more processors; and a storage device for storing one or more programs, which, when executed by the one or more processors, enable the electronic device to implement the blast furnace utilization prediction method described above.

[0014] This invention also provides a computer-readable storage medium storing computer-readable instructions, which, when executed by a computer's processor, cause the computer to perform the blast furnace utilization prediction method described in any of the preceding embodiments.

[0015] This invention discloses a method, apparatus, electronic device, and storage medium for predicting blast furnace utilization rate. The method acquires time series data of production parameters and gas utilization rate parameters, aligns these time series, constructs a data regression model based on the aligned production parameters and gas utilization rate parameters, and performs data fitting processing on the production parameters to be predicted to obtain the predicted gas utilization rate parameters. This method determines the time lag between the acquired production parameter time series and gas utilization rate parameter time series, aligns the production parameters and gas utilization rate based on the time lag, eliminating the time lag between parameters and avoiding coupling time differences. Furthermore, this method constructs a regression model based on the aligned parameters, using actual parameters as the basis for model training, thus better optimizing the parameter foundation and making the prediction results more accurate.

[0016] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. It is obvious that the drawings described below are merely some embodiments of this application, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort. In the drawings:

[0018] Figure 1 This is a schematic diagram illustrating an exemplary system architecture as shown in an exemplary embodiment of this application;

[0019] Figure 2 This is a flowchart illustrating a blast furnace utilization prediction method in an exemplary embodiment of this application;

[0020] Figure 3 This is an exemplary embodiment of the present application illustrating the execution flowchart of a specific blast furnace utilization prediction method;

[0021] Figure 4 This is a flowchart illustrating a specific model training and optimization prediction process, as shown in an exemplary embodiment of this application.

[0022] Figure 5 This application illustrates an exemplary embodiment of a blast furnace utilization prediction device;

[0023] Figure 6 This is a schematic diagram of the structure of a computer system for an electronic device, as illustrated in an exemplary embodiment of this application. Detailed Implementation

[0024] The embodiments of the present invention will be described below with reference to the accompanying drawings and specific examples. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are only for illustrating the present invention and not for limiting the scope of protection of the present invention.

[0025] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of the present invention. Therefore, the illustrations only show the components related to the present invention and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0026] In the following description, numerous details are explored to provide a more thorough explanation of embodiments of the invention. However, it will be apparent to those skilled in the art that embodiments of the invention may be practiced without these specific details. In other embodiments, well-known structures and devices are shown in block diagram form rather than in detail to avoid obscuring embodiments of the invention.

[0027] The term "and / or" used in this application describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. The character " / " generally indicates that the related objects before and after it are in an "or" relationship.

[0028] First, it should be noted that Statistical Process Control (SPC) is a process control tool that uses mathematical statistics methods. It analyzes and evaluates the production process, promptly identifies signs of systematic factors based on feedback information, and takes measures to eliminate their impact, maintaining the process in a controlled state where it is only affected by random factors, thereby achieving the goal of quality control.

[0029] Figure 1 This is a schematic diagram illustrating an exemplary system architecture as shown in an exemplary embodiment of this application.

[0030] Reference Figure 1As shown, the system architecture may include a blast furnace parameter database 101 and a computer device 102. The blast furnace parameter database 101 is used to obtain the current state parameters of the blast furnace and multiple historical state parameters, and provides them to the computer device 102 for processing. The computer device 102 may be at least one of a microcomputer, an embedded computer, a network computer, or any computer device capable of implementing the methods described in this embodiment. Those skilled in the art can use the computer device 102 to align production parameters with gas utilization rate parameters based on the time series of production parameters and the time series of gas utilization rate parameters, construct a data regression model based on the aligned production parameters and gas utilization rate parameters, and perform data fitting processing on the production parameters to be predicted to obtain the predicted gas utilization rate parameters.

[0031] Indicatively, after acquiring the time series of blast furnace production parameters and the time series of gas utilization rate parameters from the blast furnace parameter database 101, computer device 102 aligns the production parameter time series with the gas utilization rate parameter time series. Based on the aligned production parameters and gas utilization rate parameters, a data regression model is constructed, and data fitting processing is performed on the production parameters to be predicted to obtain the predicted gas utilization rate parameters. This method determines the time lag between the acquired production parameter time series and gas utilization rate parameter time series, aligns the production parameters with the gas utilization rate based on the time lag, eliminating the time lag between parameters and avoiding coupling time differences. Furthermore, this method constructs a regression model based on the aligned parameters, using actual parameters as the basis for the regression model construction, thus better optimizing the parameter foundation during model training and making the prediction results more accurate.

[0032] Figure 2 This is a flowchart illustrating an exemplary embodiment of a blast furnace utilization prediction method. This blast furnace utilization prediction method can be executed using a computing processing device, which may be... Figure 1 The computer device 102 shown is illustrated. (Refer to...) Figure 2 As shown, the flowchart of this blast furnace utilization prediction method includes at least steps S210 to S250, which are described in detail below:

[0033] In step S210, the production parameter time series and the gas utilization rate parameter time series are obtained. The production parameter time series includes production parameters at multiple time points, and the gas utilization rate parameter time series includes gas utilization rate parameters at multiple time points.

[0034] In one embodiment of this application, before obtaining the production parameter time series, it is also necessary to obtain the initial production parameters, and then determine the initial production parameters according to the preset parameter anomaly determination conditions. The preset parameter anomaly determination conditions include at least one of the following: during the blast furnace shutdown period or during the blast furnace shutdown and wind reduction plan period, if the initial production parameters are determined to be abnormal parameters, the abnormal parameters are removed from the initial production parameters to obtain the production parameters after removing the abnormal values.

[0035] In one embodiment of this application, the production parameters during the blast furnace shutdown period refer to the production parameters recorded when the blast furnace is scheduled to shut down for maintenance or when it is not scheduled to shut down. The production parameters during the blast furnace blast reduction plan period refer to the production parameters recorded when the blast furnace needs to interrupt production during the production process due to maintenance, handling accidents or other reasons, and when the air supply to the blast furnace is stopped or reduced, and the hot blast valve is closed or reduced.

[0036] In one embodiment of this application, if the initial production parameters are determined to be abnormal parameters, the abnormal parameters are removed from the initial production parameters, and the removed parameter points are also set to empty. According to the above-mentioned abnormal determination process, if the parameters in the initial production parameters are determined to be normal parameters, the parameters to be filled are obtained based on at least some of the normal parameters, and the parameters to be filled are determined as the interpolation parameters of the empty parameter points. The interpolation parameters are then interpolated to the empty parameter points to obtain the production parameters.

[0037] In one embodiment of this application, the determination of the threshold range of abnormal parameters in the anomaly determination method can be achieved by using the box-ratio method to define the threshold range of parameters. The box-ratio method is a standardized method that displays the data distribution based on a five-digit summary of the minimum, first quartile, median, third quartile, and maximum value. In an exemplary embodiment of this application, the threshold range for determining abnormal parameters can be values ​​greater than the maximum value and less than the minimum value.

[0038] It should be noted that the method for determining the threshold range of the abnormal parameter is only an exemplary example of this implementation, and there is no specific limitation on the method for determining the threshold range of the abnormal parameter here.

[0039] In one embodiment of this application, the filling method for empty parameter points includes, but is not limited to: mean interpolation, median interpolation, mode interpolation, and adjacent value interpolation.

[0040] In one embodiment of this application, before obtaining the initial production parameters, it is also necessary to obtain the historical production parameters and historical gas utilization rate parameters. The historical production parameters include at least one parameter category. Then, the correlation coefficient between the historical production parameters and the historical gas utilization rate parameters is determined based on the historical production parameters and the historical gas utilization rate parameters. If the correlation coefficient is within the preset correlation judgment threshold range, the parameter category of the historical production parameters is determined as the parameter category that is correlated with the historical gas utilization rate parameters. Finally, at least some of the parameters in the parameter category are determined as the initial production parameters.

[0041] The Pearson correlation coefficient method can be used to calculate the correlation coefficient between historical production parameters and historical gas utilization rate parameters. Specifically, the historical production parameters and historical gas utilization rate parameters are used as variables. The Pearson correlation coefficient between the historical production parameters and historical gas utilization rate parameters is obtained by taking the historical production parameters and historical gas utilization rate parameters as variables and the product of the covariance and the standard deviation of the two parameters.

[0042] It should be noted that in the above example, the Pearson correlation coefficient was used as an example for solving the correlation coefficient. In the actual production process, the production correlation coefficient can be technically adjusted according to the parameter selection standard. For example, Spearman's rank correlation coefficient and Kendall's rank correlation coefficient can also be used to solve and determine the correlation of the parameters. Here, no specific limitation is made on the solution method of the correlation coefficient.

[0043] In one embodiment of this application, the types of production parameters include, but are not limited to: air temperature, air pressure, blast humidity, theoretical combustion temperature, standard wind speed, top pressure, cold air volume, oxygen enrichment rate, steel brick temperature, pulverized coal injection rate, coke M40, coke M10, pellet grade, pellet compressive strength, sinter grade, sinter basicity, average sinter particle size, molten iron silicon content, edge ore coke ratio, platform ore coke ratio, and center ore coke ratio.

[0044] The blast furnace status parameters can be obtained by collecting data from the set sensors, by obtaining data from the instrument panel of the monitoring instrument, or by extracting the required data from the final database. The specific data acquisition method can be adjusted according to the actual needs of parameter monitoring. No specific data acquisition method is limited here.

[0045] In one embodiment of this application, if the frequency of the acquisition and storage of the production parameters to be obtained is inconsistent, such as when the frequency of data such as inspection and testing cannot meet the requirements of time delay calculation in subsequent steps, the missing data is filled with the latest value to ensure the integrity of the basic data and the consistency of the time series.

[0046] In step S220, the time lag between the production parameter time series and the gas utilization rate parameter time series is determined, and the time lag is the minimum time difference between the production parameter time series and the gas utilization rate parameter time series.

[0047] In one embodiment of this application, the production parameter time series and the gas utilization rate parameter time series are first divided into periods according to a preset period division standard. For example, if each period is set to 1 hour, the production parameter time series and the gas utilization rate parameter time series are divided into multiple parameter collection periods with 1 hour as the unit. Then, the production parameter time series and the gas utilization rate parameter time series in each period are aligned with the starting time point of the period. Based on the position of the production parameter in the production parameter time series and the position of the gas utilization rate parameter in the gas utilization rate parameter time series at the same time point, the duration difference of each time point in the production parameter time series and the gas utilization rate parameter time series is determined. The minimum difference among the duration differences of each time point is determined as the time lag duration.

[0048] In step S230, the production parameter time series is aligned with the gas utilization rate parameter time series based on the time lag duration.

[0049] In one embodiment of this application, after determining the time lag duration, the time axis of the production parameter time series and the gas utilization rate parameter time is shifted according to the determined time lag duration to eliminate the time lag between the production parameters and the gas utilization rate at the corresponding time point, thus avoiding the occurrence of coupling time difference.

[0050] In step S240, a data regression model is constructed based on the aligned production parameters and gas utilization rate parameters.

[0051] In one embodiment of this application, a sample dataset is constructed based on the aligned production parameters and gas utilization parameters, and the sample dataset is divided into a training dataset and a test dataset. Then, an initial data regression model is constructed and trained based on the training dataset to obtain the trained data regression model. Finally, the trained data regression model is optimized based on the test dataset until the data regression model is obtained.

[0052] In one embodiment of this application, to build and train an initial data regression model based on a training dataset, it is necessary to first label the production parameters according to the gas utilization rate parameter to obtain the production parameters labeled with the gas utilization rate parameter. Then, an initial data regression model is built and trained based on the production parameters labeled with the gas utilization rate parameter to obtain the trained data regression model.

[0053] In one embodiment of this application, during the training of a data regression model, the ratio of dividing the sample dataset into a training dataset and a test dataset can be 8:2. The model optimization method for tuning the trained data regression model based on the test dataset can be to set K-fold cross-validation for model tuning to optimize the performance of the trained model, wherein the initial learning rate can be set to 0.01.

[0054] It should be noted that the above-mentioned partitioning ratio of the sample dataset is only an exemplary partitioning standard in a specific embodiment. The partitioning ratio can be adjusted according to the model building requirements. There is no specific limitation on the partitioning ratio of the sample dataset here. Secondly, the model tuning method can be any model optimization method that can achieve the purpose of this application under the final optimization requirements of the model. For example, it can also be simulated annealing optimization method, gradient descent method, etc. This is only an exemplary method example and does not specifically limit the model tuning method.

[0055] In step S240, the data regression model is used to perform data fitting on the production parameters to be predicted, and the gas prediction utilization rate parameters of the production parameters to be predicted are obtained.

[0056] In one embodiment of this application, the model to be predicted is input into a trained data regression model to obtain the gas prediction utilization rate parameter of the production parameter to be predicted under the current production state, so as to predict the production status in the blast furnace and configure the corresponding blast furnace production plan.

[0057] In one embodiment of this application, the production parameter data predicted in the data regression model can be compared with the obtained gas prediction utilization rate parameters to obtain the magnitude of the influencing factors of each production parameter on the gas utilization rate. The greater the influencing factor, the greater the importance of the parameter. The production parameters are ranked according to their importance and injected back into the data regression model to adjust the parameter prediction order, so that the prediction results obtained by the data regression model are presented intuitively.

[0058] Please see Figure 3 , Figure 3 This is an exemplary embodiment of the present application illustrating the execution flowchart of a specific blast furnace utilization prediction method. This method can be applied to... Figure 3 The implementation environment is shown, and is specifically executed by the blast furnace parameter database 101 and / or computer device 102 in that implementation environment. It should be understood that the method can also be applied to other exemplary implementation environments and specifically executed by devices in other implementation environments, and this embodiment does not limit the implementation environment to which the method is applicable.

[0059] As shown in Figure 3, in an exemplary embodiment, the types of correlated parameters are first calculated based on the correlation between parameters. Then, the blast furnace process parameters are selected based on the parameter selection method derived from manual production experience. The blast furnace process parameters are the same as the initial production parameters in the above embodiment. Then, abnormal production parameter data in the selected blast furnace process parameters are removed based on the blast reduction and shutdown records, equipment maintenance records, and other external conditions. After that, the outliers in the initially removed production parameters are identified and removed using the box-ring method. The removed parameters are then empty, and the empty parameters are filled using the mean interpolation method. Then, based on the processed parameters, the time lag duration of the influencing parameters is mined and calculated. The influencing parameters are consistent with the production parameters in the above embodiment. The time lag duration between the production parameters and the gas utilization rate parameters is obtained. The time series of the influencing parameters is matched and aligned according to the obtained time lag duration. Based on the aligned influencing parameters and the gas utilization rate, a regression model is trained. The prediction results of the influencing parameters to be predicted are generated according to the trained regression model. The prediction results and the importance ranking of the parameters are obtained. The importance ranking of the parameters is injected back into the regression model training to adjust the prediction order of the regression model in order to optimize the model.

[0060] Please see Figure 4 , Figure 4 This is a flowchart illustrating a specific model training and optimization prediction process, as shown in an exemplary embodiment of this application. This method can be applied to... Figure 4 The implementation environment is shown, and is specifically executed by the blast furnace parameter database 101 and / or computer device 102 in that implementation environment. It should be understood that the method can also be applied to other exemplary implementation environments and specifically executed by devices in other implementation environments, and this embodiment does not limit the implementation environment to which the method is applicable.

[0061] As shown in Figure 4, in an exemplary embodiment, the time-matched parameter base data is divided into a training set and a test set. First, the parameters in the training set are standardized, and then the standardized parameters are trained to obtain a pre-trained regression model. Then, the pre-trained regression model is subjected to K-fold cross-validation to provide feedback tuning and obtain a trained regression model. Based on the trained regression model, the parameters to be predicted in the test set are fitted to obtain the predicted output value. Then, based on the importance of the parameter indicators in the tuned model, the time-matched parameter base data is adjusted to optimize the regression model and make the parameter structure more reflective of important factors.

[0062] The following describes an apparatus embodiment of this application, which can be used to execute the blast furnace utilization rate prediction method described in the above embodiments of this application. For details not disclosed in the system embodiments of this application, please refer to the embodiments of the blast furnace utilization rate prediction method described in the above embodiments of this application.

[0063] Figure 5 This application provides an exemplary embodiment of a blast furnace utilization prediction device. This device can be applied to… Figure 2 The implementation environment shown is specifically configured in computer device 102. This 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 applicable.

[0064] like Figure 5 As shown, the exemplary blast furnace utilization prediction device includes: an acquisition module 501, a sequence integration module 502, and a data processing module 503.

[0065] The system includes: an acquisition module 501, which acquires time series of production parameters and time series of gas utilization rate parameters, the production parameter time series including production parameters at multiple time points and the gas utilization rate parameter time series including gas utilization rate parameters at multiple time points; a sequence integration module 502, which aligns the production parameter time series and the gas utilization rate parameter time series based on the time lag between them, where the time lag is the minimum time difference between the two time series; and a data processing module 503, which constructs a data regression model based on the aligned production parameters and gas utilization rate parameters, and performs data fitting processing on the production parameters to be predicted based on the data regression model to obtain the predicted gas utilization rate parameters for the production parameters to be predicted.

[0066] Embodiments of this application also provide an electronic device, including: one or more processors; and a storage device for storing one or more programs, which, when executed by one or more processors, cause the electronic device to implement the blast furnace utilization prediction method provided in the above embodiments.

[0067] Figure 6 A schematic diagram of a computer system suitable for implementing the embodiments of this application is shown. It should be noted that... Figure 6 The computer system 600 of the electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0068] like Figure 6As shown, the computer system 600 includes a Central Processing Unit (CPU) 601, which can perform various appropriate actions and processes, such as executing the methods described in the above embodiments, based on a program stored in Read-Only Memory (ROM) 602 or a program loaded from storage into Random Access Memory (RAM) 603. The RAM 603 also stores various programs and data required for system operation. The CPU 601, ROM 602, and RAM 603 are interconnected via a bus. An Input / Output (I / O) interface 605 is also connected to the bus 604.

[0069] The following components are connected to I / O interface 605: an input section 606 including a keyboard, mouse, etc.; an output section 607 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN (Local Area Network) card, modem, etc. The communication section performs communication processing via a network such as the Internet. A drive is also connected to I / O interface 605 as needed. A removable medium 611, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 610 as needed so that computer programs read from it can be installed into storage section 608 as needed.

[0070] Specifically, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program including a computer program for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 609, and / or installed from removable medium 611. When the computer program is executed by central processing unit (CPU) 601, it performs various functions defined in the system of this application.

[0071] It should be noted that the computer-readable medium shown in the embodiments of this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying a computer-readable computer program. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The computer program contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wired, etc., or any suitable combination thereof.

[0072] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. Each block in a flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0073] In the corresponding figures of the above embodiments, connecting lines can represent the connection relationship between various components, indicating more constitutive signal paths and / or one or more ends of some lines having arrows to indicate the main information flow direction. Connecting lines are an identifier and are not a limitation on the scheme itself, but rather the use of these lines in combination with one or more exemplary embodiments helps to more easily connect circuits or logic units. Any signal represented (determined by design requirements or preferences) can actually include one or more signals that can be transmitted in any direction and can be implemented in any suitable type of signal scheme.

[0074] The units described in the embodiments of this application can be implemented in software or hardware, and the described units can also be located in a processor. The names of these units do not necessarily limit the specific unit itself.

[0075] Another aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the aforementioned blast furnace utilization prediction method. This computer-readable storage medium may be included in the electronic device described in the above embodiments, or it may exist independently and not assembled into the electronic device.

[0076] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to the embodiments of this application, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0077] Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, touch terminal, or network device, etc.) to execute the method according to the embodiments of this application.

[0078] It should be noted that this application can be used in a wide range of general-purpose or special-purpose computing system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc.

[0079] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the embodiments disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein.

[0080] It should be understood that the above content is only a preferred exemplary embodiment of this application and is not intended to limit the implementation of this application. Those skilled in the art can easily make corresponding modifications or alterations based on the main concept and spirit of this application. Therefore, the scope of protection of this application should be the scope of protection claimed in the claims.

Claims

1. A method for predicting blast furnace utilization rate, characterized in that, The method includes: Initial production parameters are obtained, and the initial production parameters are judged according to preset parameter anomaly judgment conditions. The preset parameter anomaly judgment conditions include at least one of the following: during the blast furnace shutdown period or during the blast furnace shutdown and blast reduction plan period. If the initial production parameter is determined to be an abnormal parameter, the abnormal parameter is removed from the initial production parameter to obtain the production parameter after removing the abnormal value, and the removed parameter point is set to empty; wherein, the abnormal parameter threshold range is determined by using the box method to define the parameter threshold range in the abnormal determination method; If the parameters in the initial production parameters are determined to be normal parameters, then the parameters to be filled are obtained based on at least some of the normal parameters, the parameters to be filled are determined as the interpolation parameters of the empty parameter points, and the interpolation parameters are interpolated to the empty parameter points to obtain the production parameters; Obtain time series of production parameters and time series of gas utilization rate parameters. The time series of production parameters includes production parameters at multiple time points, and the time series of gas utilization rate parameters includes gas utilization rate parameters at multiple time points. Determining the time lag between the production parameter time series and the gas utilization rate parameter time series includes dividing the production parameter time series and the gas utilization rate parameter time series into periods according to a preset period division standard; aligning the production parameter time series and the gas utilization rate parameter time series within each period after division, taking the period's start time as the starting point; determining the time difference between each time point in the production parameter time series and the gas utilization rate parameter time series based on the positions of the production parameters and the gas utilization rate parameters at the same time point; and determining the minimum difference among the time differences at each time point as the time lag duration. The production parameter time series is aligned with the gas utilization rate parameter time series based on the time lag duration; wherein, the production parameter time series and the gas utilization rate parameter time series are offset on the time axis according to the time lag duration to eliminate the time lag between the production parameters and the gas utilization rate at the corresponding time point. A data regression model is constructed based on the aligned production parameters and gas utilization rate parameters; The data regression model is used to fit the production parameters to be predicted, and the gas utilization rate parameters to be predicted are obtained. By comparing the predicted gas utilization rate parameters, the influencing factors of each production parameter on the gas utilization rate are obtained. The larger the influencing factor, the greater the importance of the corresponding production parameter. The production parameters are ranked according to their importance and then injected back into the data regression model to adjust the prediction order of the parameters.

2. The blast furnace utilization rate prediction method according to claim 1, characterized in that, Before obtaining the initial production parameters, the following is also included: Obtain historical production parameters and historical gas utilization rate parameters, wherein the historical production parameters include at least one parameter category; The correlation coefficient between the historical production parameters and the historical gas utilization rate parameters is determined based on the historical production parameters and the historical gas utilization rate parameters. If the correlation coefficient is within the preset correlation determination threshold range, then the parameter category of the historical production parameter is determined as the parameter category that is correlated with the historical gas utilization rate parameter. At least some of the parameters in the parameter category are determined as the initial production parameters.

3. The blast furnace utilization rate prediction method according to claim 1, characterized in that, A data regression model is constructed based on the aligned production parameters and gas utilization rate parameters, including: A sample dataset is constructed based on the aligned production parameters and gas utilization rate parameters. The sample dataset is divided into a training dataset and a test dataset; An initial data regression model is constructed based on the training dataset and trained to obtain a trained data regression model. The trained data regression model is tuned based on the test dataset until the data regression model is obtained.

4. The blast furnace utilization rate prediction method according to claim 3, characterized in that, An initial data regression model is constructed based on the training dataset and trained, including: The production parameters are labeled according to the gas utilization rate parameter to obtain the production parameters labeled with the gas utilization rate parameter; An initial data regression model is constructed based on the production parameters labeled with gas utilization rate parameters, and then trained to obtain a trained data regression model.

5. A blast furnace utilization rate prediction device, characterized in that, The blast furnace utilization rate prediction device includes: The acquisition module is used to acquire initial production parameters and determine the initial production parameters according to preset parameter anomaly determination conditions. The preset parameter anomaly determination conditions include at least one of the following: within the blast furnace shutdown period or within the blast furnace reduced ventilation plan period. If the initial production parameters are determined to be abnormal parameters, the abnormal parameters are removed from the initial production parameters to obtain production parameters after removing abnormal values, and the removed parameter points are set to empty. The abnormal parameter threshold range is determined using a box-line method to define the parameter threshold range. If the parameters in the initial production parameters are determined to be normal parameters, parameters to be filled are obtained based on at least some of the normal parameters. The parameters to be filled are determined as interpolation parameters for the empty parameter points, and the interpolation parameters are interpolated to the empty parameter points to obtain the production parameters. The module also acquires a production parameter time series and a gas utilization rate parameter time series. The production parameter time series includes production parameters at multiple time points, and the gas utilization rate parameter time series includes gas utilization rate parameters at multiple time points. The sequence integration module is used to determine the time lag between the production parameter time series and the gas utilization rate parameter time series. This includes dividing the production parameter time series and the gas utilization rate parameter time series into periods using a preset period division standard; aligning the production parameter time series and the gas utilization rate parameter time series within each period starting from the beginning of the period; determining the time difference between each time point in the production parameter time series and the gas utilization rate parameter time series based on the positions of the production parameters and the gas utilization rate parameters at the same time point; determining the minimum difference among the time differences at each time point as the time lag; and aligning the production parameter time series and the gas utilization rate parameter time series based on the time lag. Specifically, the time axis of the production parameter time series and the gas utilization rate parameter time series is offset according to the time lag to eliminate the time lag between the production parameters and the gas utilization rate at the corresponding time point. The data processing module is used to construct a data regression model based on the aligned production parameters and gas utilization rate parameters; perform data fitting processing on the production parameters to be predicted according to the data regression model to obtain the gas utilization rate parameters to be predicted; compare the gas utilization rate parameters to obtain the influencing factors of each production parameter on the gas utilization rate, and the larger the influencing factor, the greater the importance of the corresponding production parameter; sort the production parameters according to their importance and inject them back into the data regression model to adjust the parameter prediction order.

6. An electronic device, characterized in that, include: One or more processors; A storage device for storing one or more programs, which, when executed by the one or more processors, cause the electronic device to implement the blast furnace utilization prediction method as described in any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that, It stores computer-readable instructions that, when executed by a computer's processor, cause the computer to perform the blast furnace utilization prediction method according to any one of claims 1 to 4.

Images