Intelligent blast furnace data set preparation method and system, computing device, and storage medium

Abstract

The embodiment of the application provides a smart blast furnace data set preparation method and system, a computing device and a storage medium, relates to the technical field of device control data preparation, and comprises the following steps: constructing a first data set based on the charge type and the charge batch number; establishing a charge analysis moving database based on the charge detection frequency analysis result; calculating charge component data based on the first data set and the charge analysis moving database, and constructing a second data set based on the first data set and the charge component data; cross-filling the charge batch data into coke and ore units based on the second data set to calculate the current charge batch number and generate a blast furnace shaft simulation data set; dynamically matching the furnace thermal lag time based on the blast furnace ironmaking theory, determining the reference data and calculating the average coke ratio of the adjacent area, combining the real-time coal ratio to realize the process load connection, and fusing the latest state and operation data to construct a smart blast furnace data set, so that the whole chain data management preparation of the blast furnace is realized.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the technical field of device control data preparation, in particular to a smart blast furnace data set preparation method and system, a computing device and a storage medium. BACKGROUND

[0002] The data base is a solid foundation for the development of smart blast furnaces. As a black box type large closed container, there are many parameters for blast furnace regulation and influence, and the time lag between parameters is obvious. For example, the raw fuel is affected by the funnel effect of the receiving bin, the time of entering the furnace is affected by the belt transmission, which will cause large errors in the composition of the raw materials entering the furnace; the coal powder injection and its action lag time and the coke ratio connection also have time lag effect. In addition, the position of the furnace batch has obvious difference on the influence of the furnace condition. The existing data processing of smart blast furnace lacks consideration of blast furnace production process, and each part of the data flow is only spliced by time, resulting in mismatch between the data of the raw materials entering the furnace, technical indicators and operation or state parameters, and the prepared data set has obvious problems such as incomplete dimension consideration, low process connection and poor process interpretation. SUMMARY

[0003] Therefore, the embodiments of the present application provide a smart blast furnace data set preparation method. One or more embodiments of the present application also relate to a smart blast furnace data set preparation system, a computing device, a computer readable storage medium and a computer program to solve the technical defects in the prior art.

[0004] In a first aspect, the embodiments of the present application provide a smart blast furnace data set preparation method, comprising:

[0005] constructing a first data set based on the type of raw materials entering the furnace and the batch number of raw materials entering the furnace;

[0006] establishing a furnace material analysis moving database based on the frequency analysis results of the furnace material detection;

[0007] calculating the composition data of the furnace material based on the first data set and the furnace material analysis moving database, and constructing a second data set based on the first data set and the composition data of the furnace material;

[0008] based on the second data set, the raw material batch data is disassembled into coke and ore units for cross filling to calculate the current number of furnace batches, and a blast furnace shaft simulation data set is generated;

[0009] based on the dynamic matching of the blast furnace ironmaking theory and the furnace heat lag time, the reference data is determined and the average coke ratio of the adjacent area is calculated, the process load connection is realized in combination with the real-time coal ratio, and the latest state and operation data are fused to construct a smart blast furnace data set.

[0010] In one possible implementation, the first data set is constructed based on the type of raw materials entering the furnace and the batch number of raw materials entering the furnace, comprising:

[0011] determining whether the latest data item MtralData_i of the type coke C in the real-time judgment database Mtral table has been added to the Batch table;

[0012] If not, the start time of MtralData_i is taken as the start time of a new batch record BatchData_i, the batch number of MtralData_i is taken as the batch number of BatchData_i, and the discharged material name and the discharged quantity of MtralData_i are dynamically added as the column name and value of BatchData_i;

[0013] After a data item MtralData_j of the same batch number and of the type ore O is generated, the end time of MtralData_j is taken as the end time of BatchData_i, and the discharged material name and the discharged quantity of MtralData_j are dynamically added to the corresponding columns of BatchData_i;

[0014] The coke and ore data after the adjustment are regarded as a batch of materials, and the creation of a BatchData_i record is completed.

[0015] In a possible implementation, the establishing a furnace burden analysis migration database based on the frequency analysis result of the furnace burden detection comprises:

[0016] analyzing the time node position of the furnace burden composition detection in the process procedure and the time consumed by the belt conveying into the furnace top, and the difference between the sampling and secondary analysis results of the furnace top material and the discharged material;

[0017] based on the analysis result, determining the furnace burden object of the time lag experiment;

[0018] based on the test data of the furnace burden object of the time lag experiment, establishing a material migration rule standard, and selecting a migration batch number, wherein the material comprises one or more of the following: sinter, pellet, lump ore, flux, coke;

[0019] based on the furnace burden migration research result, formulating a furnace burden composition migration rule, and establishing a furnace burden analysis migration database.

[0020] In a possible implementation, the calculating furnace burden brought-in composition data based on the first data set and the furnace burden analysis migration database, and the constructing a second data set based on the first data set and the furnace burden brought-in composition data comprises:

[0021] based on the first data set and the furnace burden analysis migration database, calculating the furnace burden brought-in composition data in the batch material, wherein the furnace burden brought-in composition data at least comprises ore volume, ore total iron, ore calcium oxide, ore silicon dioxide, ore titanium dioxide, coke volume, coke ash, coke calcium oxide, and coke silicon dioxide.

[0022] Calculate the furnace charge batch basic data based on the furnace charge composition derived calculation data, the furnace charge batch basic data including molten iron quantity, slag quantity, binary basicity, ternary basicity, quaternary basicity and various loads;

[0023] Form the second data set based on the furnace charge batch basic data, the furnace charge composition data and the process theoretical calculation data.

[0024] In a possible implementation, based on the second data set, the furnace charge batch data is split into coke and ore units for cross filling to calculate the current furnace batch number and generate the blast furnace shaft simulation data set, which includes:

[0025] Calculate the full furnace compression ratio based on the compression ratios of the blast furnace body throat, upper shaft, lower shaft, bosh, belly and hearth;

[0026] Based on the infinite separation principle, the blast furnace is infinitely separated from the zero charge line to the tuyere center line, and based on the target separation unit containing volume, the corresponding charge line, radial length and containing volume after compression of each section are calculated;

[0027] Based on the second data set, each batch of material data is split into coke and ore to form two pieces of data, which are cross filled into the blast furnace shaft simulation model until the blast furnace working volume condition is met, and the number of existing batches in the furnace at the current time is calculated;

[0028] Based on the number of containable batches, the first half of the data in the furnace charge batch table Batch arranged in reverse order of time is read, and the ore and coke are split and appended to the data table MirrorData to form the blast furnace shaft simulation data set calculated at the current time.

[0029] In a possible implementation, based on the blast furnace ironmaking theoretical dynamic matching of the furnace heat hysteresis time, the reference data bar is determined and the average coke ratio of the adjacent area is calculated, the process load is connected in combination with the real-time coal ratio, the latest state and operation data are fused, and the intelligent blast furnace data set is constructed, which includes:

[0030] Calculate the blast furnace heat hysteresis time;

[0031] Based on the blast furnace heat hysteresis time, the corresponding data bar of the blast furnace heat hysteresis time is backstepped;

[0032] Based on the reference data bar, the average coke ratio of the data bar within the fluctuation range before and after the time node is regarded as the current coke ratio, and the current coal ratio is connected to realize the load processing;

[0033] Based on the data bar of realizing the load, as the raw material related data at the current time, the state class and the operation class data are taken as the latest, forming the intelligent blast furnace full-chain data set covering the four-in-one of raw material, state, operation and assay based on the furnace shaft simulation model.

[0034] In a possible implementation, the corresponding data bar of the inverse deduction of the furnace heat hysteresis time based on the furnace heat hysteresis time comprises:

[0035] By downward compatibility and selection of preset charging time range data bar.

[0036] In a second aspect, the embodiments of the present application provide an intelligent blast furnace data set preparation system, comprising:

[0037] A first construction module configured to construct a first data set based on the charging material type and the charging material batch number;

[0038] A second construction module configured to establish a furnace material analysis transition database based on the furnace material detection frequency analysis result;

[0039] A third construction module configured to calculate furnace material brought-in component data based on the first data set and the furnace material analysis transition database, and construct a second data set based on the first data set and the furnace material brought-in component data;

[0040] A fourth construction module configured to decompose the charging material batch data into coke and ore units based on the second data set for cross filling to calculate the current furnace material batch number and generate a blast furnace shaft simulation data set;

[0041] A fifth construction module configured to dynamically match the furnace heat hysteresis time based on the blast furnace ironmaking theory, determine the reference data bar and calculate the average coke ratio of the adjacent area, realize the process load connection in combination with the real-time coal ratio, and fuse the latest state and operation data to construct the intelligent blast furnace data set.

[0042] In a third aspect, the embodiments of the present application provide a computing device, comprising:

[0043] A memory and a processor;

[0044] The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions, which realize the steps of the above-mentioned intelligent blast furnace data set preparation method.

[0045] In a fourth aspect, the embodiments of the present application provide a computer readable storage medium, which stores computer executable instructions, which realize the steps of the above-mentioned intelligent blast furnace data set preparation method when executed by a processor.

[0046] In a fifth aspect, an embodiment of the present application provides a computer program, which, when executed in a computer, causes the computer to perform the steps of the above-mentioned method for preparing a data set of a smart blast furnace.

[0047] The technical scheme provided by the embodiment of the present application is from the perspective of connecting load from the field coke ratio-coal ratio, and aims to provide a method for preparing a data set of a smart blast furnace based on furnace shaft simulation, which guarantees the accuracy of the information of raw materials and fuels, charging information, state / operation information, slag and iron information connected by the frequency of the charging period, especially the calculation of the connection of the coal ratio and the fuel ratio, which is consistent with the actual calculation logic and operation in the field, and strongly consolidates the data base of the smart blast furnace, guarantees the data set prepared to cover the whole process, solves the process interpretation, reduces the time lag, and guarantees the data accuracy. In this process, the present application not only considers the analysis of the movement of the furnace charge to realize the data derivation calculation of the charging batch data set, but also establishes a blast furnace shaft simulation model through the full furnace compression rate and the way of filling an infinite window, and completes the load connection and the data management and preparation of the whole chain of the blast furnace according to the furnace heat lag level. BRIEF DESCRIPTION OF DRAWINGS

[0048] Figure 1 is a flowchart of a method for preparing a data set of a smart blast furnace provided by an embodiment of the present application;

[0049] Figure 2 is a structural schematic diagram of a system for preparing a data set of a smart blast furnace provided by an embodiment of the present application;

[0050] Figure 3 is a structural block diagram of a computing device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0051] In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application. However, it will be apparent to one skilled in the art that the present application can be practiced without the specific details presented herein. In other instances, well-known methods have not been described in detail in order to avoid obscuring the present application.

[0052] The terms used in one or more embodiments of the present application are merely for the purpose of describing specific embodiments, and are not intended to limit one or more embodiments of the present application. The singular forms "a", "an" and "the" used in one or more embodiments of the present application and the appended claims are also intended to include the plural forms, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in one or more embodiments of the present application means and includes any or all possible combinations of one or more associated listed items.

[0053] It should be understood that, although the terms first, second, etc. can be employed in describing various information in one or more embodiments, such information should not be limited to these terms. These terms are only used to distinguish one category of information from another. For example, without departing from the scope of one or more embodiments, first can be termed second, and, similarly, second can be termed first. Depending on the context, the word "if' as used herein can be interpreted to mean "when" or "in response to determining" or "in response to ascertaining."

[0054] In the present application, a smart blast furnace data set preparation method is provided, and the present application also relates to a smart blast furnace data set preparation system, a computing device, and a computer readable storage medium, which are described in detail one by one in the following embodiments.

[0055] Figure 1 A flowchart of a smart blast furnace data set preparation method provided for an embodiment of the present application.

[0056] Referring to Figure 1 , specifically comprising the following steps.

[0057] Step 101: constructing a first data set (i.e., a charging batch basic data set) based on the charging material type and the charging batch number.

[0058] Step 102: establishing a material analysis transition database based on the charging material detection frequency analysis result.

[0059] Step 103: calculating charging material composition data based on the first data set and the material analysis transition database, and constructing a second data set (i.e., a charging batch complete data set) based on the first data set and the charging material composition data.

[0060] Step 104: decomposing the charging batch data into coke and ore units based on the second data set for cross filling to calculate the current furnace batch number and generate a blast furnace shaft simulation data set.

[0061] Step 105: dynamically matching the furnace thermal lag time based on the blast furnace ironmaking theory to determine the reference data bar and calculate the average coke ratio of the adjacent area, realize process load connection in combination with the real-time coal ratio, fuse the latest state and operation data, and construct a smart blast furnace data set.

[0062] In some embodiments, constructing a first data set based on the charging material type and the charging batch number comprises:

[0063] determining whether the latest data bar MtralData_i of the type coke C in the database Mtral table has been added to the Batch table in real time;

[0064] If not added, the start time of MtralData_i is taken as the start time of BatchData_i, the batch number of MtralData_i is taken as the batch number of BatchData_i, and the discharged material name and the discharged amount of MtralData_i are dynamically added as the column name and value of BatchData_i;

[0065] After waiting for the generation of the data record MtralData_j with the same batch number and of the type ore O, the end time of MtralData_j is taken as the end time of BatchData_i, and the discharged material name and the discharged amount of MtralData_j are dynamically added to the corresponding columns of BatchData_i;

[0066] The reconciled coke and ore data are regarded as a batch of materials, and the creation of a BatchData_i record is completed.

[0067] In other embodiments, constructing the first data set based on the charging material type and the charging material batch number comprises:

[0068] Based on the data table Mtral table stored by the blast furnace charging material weighing system, through computer and process theory cross technology, it is determined in real time whether the data record in the Mtral table has been added to the charging material batch table Batch (the charging of the blast furnace charging material is alternately performed by coke (C) and ore (O)).

[0069] Based on the batch integrity principle, it is determined in real time whether the latest data record MtralData_i of the type C in the Mtral table has been added to the charging material batch table Batch. If not added, the start time of MtralData_i is taken as the start time of the data record BatchData_i in the Batch table, the batch number is taken as the batch number of BatchData_i, the discharged material name is dynamically added as the column name of the data record BatchData_i, and the discharged amount of each material is taken as the value of the corresponding column name, and the coke-related data addition operation is completed;

[0070] Based on the added coke batch number, the data processing program waits in real time for the generation of the data record MtralData_j with the same batch number but of the type O in the Mtral table (j=i+1), and the end time of the data record MtralData_j is taken as the end time of the data record BatchData_i, the discharged material name is dynamically added as the column name of the data record BatchData_i, and the discharged amount of each material is taken as the value of the corresponding column name, and the ore-related data addition is completed to form a batch of data;

[0071] Based on the data processing module integrity and fault tolerance, the latest C, O has been added Batch table, that is, the latest data strip MtralData_i in the Mtral table or the O of the same batch number has been added into the batch table Batch, then the current processing is exited, and the module is re-run after 1 minute.

[0072] By monitoring and dynamically associating the coke and ore unloading data in real time, and automatically classifying them into a single structured batch record based on the same batch number, the completeness, accuracy and real-time of the blast furnace charging batch data are effectively guaranteed, and a reliable data foundation is provided for subsequent process calculation, shaft simulation and full-chain data analysis.

[0073] In some embodiments, establishing a furnace charge analysis migration database based on the frequency analysis results of the furnace charge detection includes:

[0074] Based on the method of visiting the scene and investigation, the time node position of the furnace charge component detection in the process sequence and the time consumed by the belt conveying into the top of the furnace are analyzed, and the difference between the sampling and secondary analysis results of the top charge and the unloading is analyzed;

[0075] Based on the analysis and research results, determine the furnace charge objects that need to be subjected to time lag experiments;

[0076] Based on the determination of the furnace charge that needs to use time lag experiments, design and implement time lag experiments, establish material migration rule standards, and select migration batch quantity on the basis of ensuring credibility and stability, wherein the material includes one or more of the following: sinter, pellet, lump ore, flux, coke;

[0077] Based on the furnace charge migration research results, formulate the furnace charge component migration rules, and use computer technology to establish a furnace charge analysis migration database.

[0078] By establishing accurate furnace charge component migration rules and databases, the core problem of mismatch between component analysis data and actual material into the furnace caused by material transmission time difference and hopper effect is effectively solved, the timeliness and accuracy of component data in the blast furnace ironmaking process are significantly improved, and a stable and reliable data foundation is provided for subsequent process calculation and optimization.

[0079] In some embodiments, calculating furnace charge component data based on the first data set and the furnace charge analysis migration database, and constructing a second data set based on the first data set and the furnace charge component data include:

[0080] Based on the furnace charge batch basic data set and the furnace charge analysis migration database, dozens of furnace charge component data including but not limited to ore volume, ore total iron, ore calcium oxide, ore silicon dioxide, ore titanium dioxide, coke volume, coke ash, coke calcium oxide, coke silicon dioxide, etc. are calculated.

[0081] Based on the classical theory of blast furnace ironmaking, the theoretical molten iron quantity, slag quantity, binary basicity, ternary basicity, quaternary basicity and various loads are calculated on the basis of the derived calculation data of the furnace charge composition;

[0082] Based on the basic data of the charging batch, the furnace charge composition data and the process theoretical calculation data, a complete data set of the charging batch is formed.

[0083] By systematically calculating and integrating the various key component data brought by the furnace charge and the process theoretical derived data, a second data set that comprehensively reflects the blast furnace smelting process is constructed, providing a solid data core and decision basis for precise operation, process optimization and intelligent control of the blast furnace.

[0084] In some embodiments, based on the second data set, the charging batch data is disassembled into coke and ore units for cross-filling to calculate the current number of batches in the furnace and generate a blast furnace shaft simulation data set, including:

[0085] Based on the compression rates of the blast furnace throat, upper shaft, lower shaft, belly, bosh and hearth, the overall furnace compression rate is calculated;

[0086] Based on the principle of infinite separation, the blast furnace is infinitely separated from the zero material line to the tuyere center line, and based on the target separation unit volume, the corresponding material line, radial length and accommodated volume after compression are calculated for each section;

[0087] Based on the second data set, each batch of material data is disassembled into coke and ore to form two pieces of data, which are cross-filled into the shaft simulation model until the blast furnace working volume condition is met, and the number of batches present in the furnace at the current time is calculated;

[0088] Based on the accommodated batch number, the first half of the data in the charging batch table Batch arranged in reverse order of time is read and appended to the data table MirrorData after separating ore and coke to form the blast furnace shaft simulation data set calculated at the current time.

[0089] By constructing an accurate blast furnace shaft simulation model and dynamically filling batch data, accurate virtual reproduction of real-time material layer structure and chemical composition distribution in the blast furnace is achieved, providing operators with intuitive and reliable insights into the furnace state, significantly improving the transparency and intelligent control level of the blast furnace smelting process.

[0090] In some embodiments, based on the dynamic matching of the blast furnace ironmaking theory to the furnace heat lag time, the reference data bar is determined and the average coke ratio of the adjacent area is calculated, the process load is connected in combination with the real-time coal ratio, and the latest state and operation data are integrated to construct a smart blast furnace data set, including:

[0091] The blast furnace heat lag time is calculated;

[0092] Based on the high furnace thermal hysteresis time, the corresponding data bar of the inverse thermal hysteresis time is deduced;

[0093] Based on the reference data bar, the average coke ratio of the bar data within the fluctuation range before and after the time node is regarded as the current coke ratio, and the current coal ratio is accessed to realize the load connection processing;

[0094] Based on the data bar of realizing the load connection, as the raw material related data at the current time, the state and operation data can be taken as the latest, forming a four-in-one intelligent blast furnace full-chain data set based on the shaft simulation model, covering raw materials, states, operations and tests.

[0095] By dynamically matching the thermal hysteresis time and calculating the average coke ratio, the precise connection and real-time optimization of thermal load and raw material load in the blast furnace smelting process are realized, and at the same time, through the fusion of the latest state and operation data, a full-chain integrated data set covering raw materials, states, operations and tests is constructed, which significantly improves the stability, energy efficiency control level and intelligent decision-making ability of blast furnace production.

[0096] In some embodiments, the corresponding data bar of the inverse thermal hysteresis time is deduced based on the high furnace thermal hysteresis time, which includes: through downward compatibility and selection of data bars in a preset furnace time range, that is, through downward compatibility and selection of data bars with the closest furnace time.

[0097] By adopting the data bar matching strategy of "downward compatibility and selection of the closest furnace time", the accuracy and engineering practicability of the thermal hysteresis time calculation are effectively ensured, and the matching deviation caused by data dispersion or loss is avoided, which significantly improves the stability and reliability of the blast furnace load connection control.

[0098] In some embodiments, the specific method steps of the intelligent blast furnace data set preparation method provided by the embodiment are as follows:

[0099] The basic dataset of the charging batch is prepared based on the burden cycle. The coke (C) and ore (O) are alternately charged in the blast furnace, and the usage amount of each material is stored in the Mtral table of the database through the burden weighing system. Based on computer technology and process theory, it is judged in real time whether the latest data item MtralData_i of the type belonging to C in the Mtral table has been added to the Batch table. If not, the start time of MtralData_i is the start time of BatchData_i in the Batch table, the batch number is BatchData_i, the dynamic addition of the material name is added as the column name of BatchData_i, and the amount of each material is added as the value of the corresponding column name. At this time, the coke data is added; the data processing program waits for the generation of the data item MtralData_j of the same batch number but the type belonging to O in the Mtral table in real time (j = i + 1), and the end time of the data item MtralData_j is used as the end time of the data item BatchData_i. The dynamic addition of the material name is added as the column name of BatchData_i, and the amount of each material is added as the value of the corresponding column name. At this time, the ore data is added and integrated with the coke data as one data, which is regarded as one batch; if the latest data item MtralData_i of the type belonging to C in the Mtral table has been added to the Batch table, then the selection continues to wait and no operation is performed.

[0100] The pushover database of the burden analysis is established. The burden composition detection is completed before the charging bin, and the analysis at the charging time point is not the real analysis of a certain burden due to the influence of the funnel effect of the receiving bin and the time consumed by the belt conveyor on the top of the blast furnace. Since the detection frequency of sinter in the burden is higher, and the detection frequency of pellets, lump ore and coke is low, and the usage amount is much smaller than that of sinter, therefore, the experimental test model is used to set markers for different heights and different radial regions of the sinter bin to analyze the discharge time of the bin, and then the relationship between the height, storage capacity, hourly usage amount, return ore rate and sinter pushover time is fitted. The latest analysis is taken for the analysis of the remaining burden. In addition, in order to improve the credibility and stability of the sinter analysis pushover, the average value of 3-5 pushover batches can be taken.

[0101] The basic dataset of the charging batch is derived based on the classical theory of blast furnace ironmaking. The composition of the charging batch is crucial to the operation of the blast furnace, and the classical theory of blast furnace ironmaking is used to calculate the volume of ore, coke, the amount of coke ash and important components such as calcium, silicon, magnesium and aluminum brought in by the batch; in addition, according to the theory of iron amount calculation of the charging batch, the amount of molten iron, the amount of slag, the binary basicity, the ternary basicity, the quaternary basicity and various loads are calculated to form a complete dataset of the charging batch.

[0102] Construct a blast furnace shaft simulation model and a data table. Calculate the overall compression rate of the blast furnace according to the compression rates of different parts of the blast furnace, such as the throat, upper shaft, lower shaft, belly, bosh, and hearth. Based on the principle of infinite division, divide the blast furnace from the zero charge line to the center line of the tuyere into n segments, ensuring that each segment is located in a part that can accommodate a volume of less than 1 cubic meter. Calculate the corresponding charge line, radial length, and accommodated volume after compression for each segment. Cross-fill the volumes of ore and coke into the n segments from the latest time, until the maximum volume that the n segments can accommodate is approached, to calculate the number of charge batches N present in the furnace at the current time. Read the first ⌊N / 2⌋ data from the charge batch table Batch arranged in reverse order of time, and append the ore and coke to the data table MirrorData after being separated, which is the calculated blast furnace shaft simulation data set at the current time. In addition, each blast furnace shaft simulation data set needs to use the current time as the calculation time, which becomes the unique identifier to distinguish the remaining blast furnace shaft simulation data sets.

[0103] Based on the blast furnace shaft simulation, process the load, solve the data management problem, realize the whole chain data management of the blast furnace, and prepare the smart blast furnace data set based on the blast furnace shaft simulation. Calculate the blast furnace heat lag time Time1 by the quotient of the volume of the high-temperature zone of the blast furnace and the hourly discharge amount, find the last data entry time Time2 in the calculated blast furnace shaft simulation data set table at the current time, and inversely deduce the corresponding data item found by Time1, whose entry time is near Time1-Time2 (here, the data item i closest to the later time is specified); the coke ratio smoothed by the 5 data items above and below data item i is the current coke ratio, which successfully realizes the load processing; finally, the whole chain data construction method of the blast furnace is constructed based on the dynamic change data item i with the frequency of distribution as the basis, and the latest state and operation data can be obtained.

[0104] Through the above technical solution, the time lag experiment can be performed on the high-frequency detection of the furnace charge according to the frequency analysis result of the furnace charge detection, the furnace charge analysis result collection rule can be formulated, and the furnace charge analysis transition database can be prepared, so as to solve the problem of time lag between the raw material charging and the component detection; based on the basic data set of the charging batch and the furnace charge analysis transition database, the batch data is derived by using the classical theory of the blast furnace, so as to ensure the multidimensionality and timeliness of the data; by calculating the overall compression rate and the window division method, a dynamic blast furnace shaft simulation model based on the distribution cycle is established, the basic data set of the charging batch is associated with the batch number, and a dynamic real-time blast furnace shaft simulation data table is formed; the load data processing of the blast furnace shaft simulation data table is realized by inversely deducing the blast furnace heat lag time, so as to solve the problem of matching the coke ratio and the coal ratio technical indicators, and realize the whole chain data preparation of the smart blast furnace, which is an effective solution for the smart blast furnace model data base.

[0105] Corresponding to the method embodiments described above, the present application also provides a smart blast furnace data set preparation system embodiment, Figure 2 A structural schematic diagram of a smart blast furnace data set preparation system according to an embodiment of the present application is shown. As shown in the figure, Figure 2 The system comprises:

[0106] A first construction module 201 is configured to construct a first data set based on the type of charging material and the batch number of charging material;

[0107] A second construction module 202 is configured to establish a furnace material analysis moving database based on the frequency analysis result of furnace material detection;

[0108] A third construction module 203 is configured to calculate furnace material carrying component data based on the first data set and the furnace material analysis moving database, and to construct a second data set based on the first data set and the furnace material carrying component data;

[0109] A fourth construction module 204 is configured to disassemble the batch data of charging material into coke and ore units based on the second data set for cross filling to calculate the current batch number of furnace material and generate a simulation data set of blast furnace shaft;

[0110] A fifth construction module 205 is configured to determine the reference data bar based on the dynamic matching of blast furnace ironmaking theory and furnace thermal hysteresis time, calculate the average coke ratio of adjacent areas, realize process load connection in combination with real-time coal ratio, and construct a smart blast furnace data set by integrating the latest state and operation data.

[0111] The above is a schematic scheme of a smart blast furnace data set preparation system according to the present embodiment. It should be noted that the technical scheme of the smart blast furnace data set preparation system belongs to the same concept as the technical scheme of the smart blast furnace data set preparation method described above, and the details of the technical scheme of the smart blast furnace data set preparation system that are not described in detail can be referred to the description of the technical scheme of the smart blast furnace data set preparation method.

[0112] Figure 3 A structural block diagram of a computing device 300 according to an embodiment of the present application is shown. The components of the computing device 300 include but are not limited to a memory 310 and a processor 320. The processor 320 is connected to the memory 310 through a bus 330, and a database 350 is used to save data.

[0113] The computing device 300 also includes an access device 340 that enables the computing device 300 to communicate via one or more networks 360. Examples of these networks include a public switched telephone network (PSTN), a local area network (LAN), a wide area network (WAN), a personal area network (PAN), or combinations of these and / or other types of networks that are suitable for the communication of data. The access device 340 can include one or more of any type of network interface (for example, a network interface card (NIC)), wired or wireless, such as an IEEE 802.11 wireless local area network (WLAN) wireless interface, a Worldwide Interoperability for Microwave Access (Wi-MAX) interface, an Ethernet interface, a Universal Serial Bus (USB) interface, a cellular network interface, a Bluetooth interface, a Near Field Communication (NFC).

[0114] In one embodiment of the present application, the above-described components of the computing device 300, as well as other components not shown in FIG. 3, can be connected to each other by a bus. It should be understood that Figure 3 Figure 3 The computing device structure diagram shown is merely for the purpose of example, and is not a limitation on the scope of the present application. Other components can be added or replaced as needed by those skilled in the art.

[0115] The computing device 300 can be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (for example, a tablet computer, a personal digital assistant, a laptop computer, a notebook computer, a netbook, and the like), a mobile phone (for example, a smartphone), a wearable computing device (for example, a smart watch, smart glasses, and the like), or other types of mobile devices, or a stationary computing device such as a desktop computer or a personal computer (PC). The computing device 300 can also be a mobile or stationary server.

[0116] ​The processor 320 is configured to execute the following computer-executable instructions, which implement the steps of the above-mentioned intelligent blast furnace dataset preparation method when executed by the processor. The above is a schematic scheme of a computing device according to an embodiment of the present application. It should be noted that the technical scheme of the computing device and the technical scheme of the above-mentioned intelligent blast furnace dataset preparation method belong to the same concept, and the details of the technical scheme of the computing device that are not described in detail can be seen from the description of the technical scheme of the above-mentioned intelligent blast furnace dataset preparation method.

[0117] An embodiment of the present application further provides a computer-readable storage medium storing computer-executable instructions, which implement the steps of the above-mentioned intelligent blast furnace dataset preparation method when executed by a processor.

[0118] The above is a schematic scheme of a computer-readable storage medium according to an embodiment of the present application. It should be noted that the technical scheme of the storage medium and the technical scheme of the above-mentioned intelligent blast furnace dataset preparation method belong to the same concept, and the details of the technical scheme of the storage medium that are not described in detail can be seen from the description of the technical scheme of the above-mentioned intelligent blast furnace dataset preparation method.

[0119] An embodiment of the present application further provides a computer program, which causes a computer to perform the steps of the above-mentioned intelligent blast furnace dataset preparation method when the computer program is executed in the computer.

[0120] The above is a schematic scheme of a computer program according to an embodiment of the present application. It should be noted that the technical scheme of the computer program and the technical scheme of the above-mentioned intelligent blast furnace dataset preparation method belong to the same concept, and the details of the technical scheme of the computer program that are not described in detail can be seen from the description of the technical scheme of the above-mentioned intelligent blast furnace dataset preparation method.

[0121] The above describes specific embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the acts or steps recited in the claims can be performed in a different order than the order in which they are recited and still achieve desirable results. In addition, the processes depicted in the figures do not necessarily require the particular order shown, or sequential order to achieve the desired results. In certain implementations, multitasking and parallel processing can be advantageous.

[0122] The computer readable medium can include any entity or apparatus capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, software distribution medium, etc. It should be noted that the computer readable medium can include appropriate additions or subtractions according to the requirements of legislation and patent practice in the jurisdiction, for example, in some jurisdictions, according to legislation and patent practice, the computer readable medium does not include electrical carrier signals and telecommunication signals.

[0123] It should be noted that for the foregoing method embodiments, the descriptions are expressed as a combination of a series of actions for the sake of simplicity and brevity, but those skilled in the art should appreciate that the embodiments of the present application are not limited by the order of the actions described, because according to the embodiments of the present application, certain steps can be performed in other orders or at the same time. Secondly, those skilled in the art should appreciate that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to the embodiments of the present application.

[0124] In the above embodiments, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0125] The preferred embodiments of the present application disclosed above are only used to help explain the present application. The alternative embodiments do not describe all the details and limit the application to the specific embodiments described. Obviously, according to the content of the embodiments of the present application, many modifications and changes can be made. The present application selects and describes these embodiments in order to better explain the principles and practical applications of the embodiments of the present application, so that those skilled in the art can well understand and utilize the present application. The present application is limited by the claims and their entire scope and equivalents.

Claims

1. A method for preparing a smart blast furnace dataset, characterized in that, The method comprises the following steps: constructing a first data set based on the type and batch number of the charging material; establishing a charging material analysis migration database based on the frequency analysis results of the charging material detection; calculating the charging material composition data based on the first data set and the charging material analysis migration database, and constructing a second data set based on the first data set and the charging material composition data; based on the second data set, the charging material batch data is disassembled into coke and ore units for cross filling to calculate the current number of batches in the blast furnace and generate a blast furnace shaft simulation data set; based on the dynamic matching of the blast furnace ironmaking theory and the furnace thermal lag time, the reference data bar is determined and the average coke ratio of the adjacent area is calculated, the process load is connected in combination with the real-time coal ratio, the latest state and operation data are fused, and a smart blast furnace data set is constructed; wherein, the establishment of the charging material analysis migration database based on the frequency analysis results of the charging material detection comprises: analyzing the time node position of the charging material composition detection in the process sequence and the time consumed by the belt conveying into the furnace top, and the difference between the sampling and secondary analysis results of the furnace top material and the discharged material; based on the analysis results, determining the charging material objects of the time lag experiment; based on the test data of the charging material objects of the time lag experiment, establishing material migration rule standards, and selecting the number of migration batches, wherein the material includes one or more of the following: sinter, pellet, lump ore, flux, coke; based on the judgment results of the charging material migration, the charging material composition migration rules are formulated, and the charging material analysis migration database is established.

2. The smart blast furnace data set preparation method according to claim 1, characterized in that, The construction of the first data set based on the type and batch number of the charging material comprises: real-time judgment of whether the latest data bar MtralData_i of the type coke in the database Mtral table has been added to the Batch table; if not, the start time of MtralData_i is taken as the start time of the new batch record BatchData_i, the batch number of MtralData_i is taken as the batch number of BatchData_i, and the discharged material name and amount of MtralData_i are dynamically added to the column name and value of BatchData_i; after waiting for the generation of the data bar MtralData_j with the same batch number and the type of ore, taking its end time as the end time of BatchData_i, and dynamically adding the discharged material name and amount of MtralData_j to the corresponding column of BatchData_i; the sorted coke and ore data are regarded as a batch of materials, and the creation of a BatchData_i record is completed.

3. The smart blast furnace data set preparation method according to claim 1, characterized in that, The calculation of the charging material composition data based on the first data set and the charging material analysis migration database, and the construction of the second data set based on the first data set and the charging material composition data comprise: based on the first data set and the charging material analysis migration database, the charging material composition data in the batch material is calculated, which at least includes ore volume, ore total iron, ore calcium oxide, ore silicon dioxide, ore titanium dioxide, coke volume, coke ash, coke calcium oxide, and coke silicon dioxide; Calculate the batch basis data based on the derived calculation data of the charge composition, which includes the amount of molten iron, the amount of slag, the binary basicity, the ternary basicity, the quaternary basicity, and various loads; Based on the batch basis data, the charge composition data, and the process theoretical calculation data, form the second data set.

4. The smart blast furnace data set preparation method according to claim 1, characterized in that, Based on the second data set, the batch data is decomposed into coke and ore units for cross-filling to calculate the current batch number in the furnace, and a blast furnace shaft simulation data set is generated, which includes: Based on the compression rates of the blast furnace body throat, upper shaft, lower shaft, belly, bosh, and hearth, the overall furnace compression rate is calculated; Based on the infinite separation principle, the blast furnace is infinitely separated from the zero material line to the tuyere center line, and based on the target separation unit volume, the corresponding material line, radial length, and accommodated volume after compression are calculated; Based on the second data set, each batch of material data is decomposed into coke and ore to form two pieces of data, which are cross-filled into the shaft simulation model until the blast furnace working volume condition is met, and the number of batches existing in the furnace at the current time is calculated; Based on the accommodated batch number, the first half of the data in the batch table Batch arranged in reverse order of time is read, and the ore and coke are separated and appended to the data table MirrorData to form the calculated blast furnace shaft simulation data set at the current time.

5. The smart blast furnace data set preparation method according to claim 1, characterized in that, Based on the dynamic matching of the blast furnace ironmaking theory and the furnace heat hysteresis time, the reference data bar is determined and the average coke ratio of the adjacent area is calculated, the real-time coal ratio is combined to realize process load connection, and the latest state and operation data are fused to build a smart blast furnace data set, which includes: Calculate the blast furnace heat hysteresis time; Based on the blast furnace heat hysteresis time, the corresponding data bar of the blast furnace heat hysteresis time is inversely calculated; Based on the reference data bar, the average coke ratio of the data bar within the fluctuation range before and after the time node is considered as the current coke ratio, and the current coal ratio is connected to realize load processing; Based on the data bar that realizes load connection, as the raw material related data at the current time, the latest state and operation data are taken to form a smart blast furnace full-chain data set based on the shaft simulation model, covering raw materials, states, operations, and tests.

6. The smart blast furnace data set preparation method according to claim 5, characterized in that, The corresponding data bar of the blast furnace heat hysteresis time based on the blast furnace heat hysteresis time includes: By downward compatibility and selecting data bars in the preset charging time range.

7. A smart blast furnace data set preparation system, characterized by, It includes: A first construction module configured to construct a first data set based on the type of charging material and the batch number of charging material; A second construction module configured to establish a furnace material analysis moving database based on the frequency analysis result of the furnace material detection; A third construction module configured to calculate the charge composition data based on the first data set and the furnace material analysis moving database, and to construct a second data set based on the first data set and the charge composition data; A fourth construction module configured to decompose the batch data into coke and ore units for cross-filling based on the second data set, to calculate the current batch number in the furnace, and to generate a blast furnace shaft simulation data set; A fifth construction module is configured to dynamically match the furnace thermal lag time based on the blast furnace ironmaking theory, determine the reference data bar and calculate the average coke ratio of the adjacent area, realize the process load connection combined with the real-time coal ratio, and construct the intelligent blast furnace dataset by fusing the latest state and operation data; The furnace burden analysis and movement database is established based on the analysis result of the furnace burden detection frequency. The time node position of the furnace burden composition detection in the process procedure and the time consumed by the belt conveying into the top of the furnace are analyzed. Based on the analysis result, the furnace burden object of the time lag experiment is determined. Based on the test data of the furnace burden object of the time lag experiment, the material movement rule standard is established, and the movement batch quantity is selected, wherein the material includes one or more of the following: sinter, pellet, lump ore, flux, and coke. Based on the analysis and judgment result of the furnace burden movement, the furnace burden composition movement rule is formulated, and the furnace burden analysis and movement database is established.

8. A computing device, comprising: It comprises: a memory and a processor; The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions, which realize the steps of the intelligent blast furnace dataset preparation method in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, It stores computer executable instructions, which realize the steps of the intelligent blast furnace dataset preparation method in any one of claims 1 to 6 when executed by the processor.

Images