Blast furnace quantitative knowledge determination method, system, device and storage medium

Abstract

The present application provides a method, system, equipment and storage medium for determining quantitative knowledge of a blast furnace, the method comprising: obtaining the production data of the blast furnace, the production data comprising a variety of blast furnace data divided according to the quantitative objects in the blast furnace production process; slicing the various blast furnace data respectively to obtain multiple production segments of each blast furnace data, the production segments comprising blast furnace data of a preset first duration; calculating the statistical indicators of the blast furnace data in each production segment, and discretizing the statistical indicators to determine the discrete variables of the statistical indicators; splicing the discrete variables corresponding to the production segments with the same slicing end time to form multiple production records; quantitatively analyzing the correlation between each discrete variable in each production record, determining the association rules, so as to complete the determination of quantitative knowledge of the blast furnace. In this way, the correlation between multi-dimensional parameters in blast furnace production can be automatically mined, and the rapid and comprehensive extraction and quantification of blast furnace production knowledge can be achieved.

Description

Technical Field

[0001] The present application relates to the technical field of blast furnaces, and in particular to a method, system, device and storage medium for determining quantitative knowledge of blast furnaces. Background Art

[0002] As the core link in steel production, the complexity and high coupling of blast furnace have a decisive influence on the efficiency and quality of steel production. The physical and chemical reactions inside the blast furnace involve multiple phases, such as the interaction between gas, liquid and solid. These reactions are not only accompanied by the transformation of substances, but also accompanied by complex energy flow and transformation, resulting in high coupling and large time lag characteristics in blast furnace production. Among them, high coupling is reflected in the raw material composition, furnace temperature control, airflow distribution and other aspects. These factors are intertwined and complicated. The large time lag characteristics are reflected in the fact that changes in a certain operation or parameter often take a long time to be reflected in the output of production, which further increases the difficulty of production control. In addition, the mutual influence mechanism between raw materials, operation and state parameters in the blast furnace production process is complex. Therefore, it is difficult to comprehensively and accurately characterize blast furnace production through simple process models. In related technologies, the knowledge of the mutual influence of various factors in blast furnace production mainly relies on process experts to gradually summarize some basic laws in blast furnace production based on years of practical experience.

[0003] However, methods that rely on manual summarization have obvious limitations. On the one hand, due to the complexity and nonlinearity of blast furnace production, it is difficult to fully reveal the intrinsic connections between multi-dimensional parameters based on experience alone, and the discovery of laws is incomplete and inefficient. On the other hand, there may be differences in experience between different experts, which makes it difficult to uniformly quantify and standardize the summarized laws. Summary of the invention

[0004] In order to provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. The summary is not an extensive review, nor is it intended to identify key / critical components or delineate the scope of protection of these embodiments, but rather serves as a prelude to the detailed description that follows.

[0005] In view of the shortcomings of the prior art mentioned above, the present application discloses a method, system, equipment and storage medium for determining quantitative knowledge of a blast furnace to solve the technical problem of how to improve the efficiency and comprehensiveness of law extraction and quantification between multi-dimensional parameters in blast furnace production.

[0006] In a first aspect, the present application provides a method for determining quantitative knowledge of a blast furnace, the method comprising: obtaining production data of a blast furnace, the production data comprising a plurality of blast furnace data divided according to quantitative objects in a blast furnace production process; slicing the plurality of blast furnace data respectively to obtain a plurality of production segments of each of the blast furnace data, the production segments comprising the blast furnace data of a preset first time length; calculating statistical indicators of the blast furnace data in each of the production segments, and discretizing the statistical indicators to determine discrete variables of the statistical indicators; splicing the discrete variables corresponding to the production segments with the same slicing end time to form a plurality of production records, the production records being a collection of the discrete variables associated with each of the blast furnace data at the same slicing end time; quantitatively analyzing the correlation between the discrete variables in each of the production records to determine association rules to complete the determination of the quantitative knowledge of the blast furnace.

[0007] In one embodiment of the present application, the multiple blast furnace data are sliced ​​separately to obtain multiple production segments of each blast furnace data, including: using the preset first time length as the window width of the sliding window, and using the preset second time length as the step length of the sliding window, the preset second time length is smaller than the preset first time length; based on the sliding window, slicing the sequence formed over time for each blast furnace data to obtain multiple production segments corresponding to each blast furnace data.

[0008] In one embodiment of the present application, the statistical indicators of the blast furnace data in each of the production segments are calculated, and the statistical indicators are discretized to determine the discrete variables of the statistical indicators, including: calculating according to the blast furnace data of the preset first time length in each of the production segments to determine the statistical indicators corresponding to each of the production segments, the statistical indicators including statistical characteristics and linear regression slopes; discretizing the different types of statistical indicators corresponding to each of the production segments to determine the discrete variables corresponding to each of the production segments.

[0009] In one embodiment of the present application, the statistical indicators are discretized to determine the discrete variables of the statistical indicators, including: performing equal-frequency binning on the statistical indicators corresponding to each of the production segments to divide the numerical range of each of the statistical indicators into a preset number of equal-frequency intervals; allocating the statistical indicators corresponding to each of the production segments to the corresponding equal-frequency intervals to determine the discrete variables of the statistical indicators corresponding to each of the production segments.

[0010] In one embodiment of the present application, the association relationship between each discrete variable in each production record is quantitatively analyzed to determine the association rules, including: taking each production record as an item set, and each discrete variable in the production record as an item; calculating the support of each item, and defining the minimum support of the item set; iteratively screening the items whose support is greater than or equal to the minimum support to obtain multiple frequent item sets, wherein the frequent item set is a set of at least one target item, and the support of the target item is greater than or equal to the minimum support; and generating multiple association rules based on each frequent item set.

[0011] In one embodiment of the present application, after determining the association rules, it also includes: calculating the confidence of each of the association rules, and defining the minimum confidence of the association rules; screening the association rules whose confidence is greater than or equal to the minimum confidence, and determining the final association rules.

[0012] In one embodiment of the present application, after determining the association rules, it also includes: visually displaying the association rules, wherein the visual display method includes at least a network diagram, a heat map and a table; filtering the displayed association rules, and storing the filtered association rules in a preset knowledge base.

[0013] In the second aspect, the present application provides a blast furnace quantitative knowledge determination system, the system comprising: an acquisition module, used to acquire the production data of the blast furnace, the production data comprising a plurality of blast furnace data divided according to the quantitative objects in the blast furnace production process; a slicing module, used to slice the plurality of blast furnace data respectively to obtain a plurality of production segments of each of the blast furnace data, the production segments comprising the blast furnace data of a preset first time length; a calculation module, used to calculate the statistical indicators of the blast furnace data in each of the production segments, and discretize the statistical indicators to determine the discrete variables of the statistical indicators; a splicing module, used to splice the discrete variables corresponding to the production segments with the same slicing end time to form a plurality of production records, the production records being a collection of the discrete variables associated with each of the blast furnace data at the same slicing end time; an analysis module, used to quantitatively analyze the association relationship between each of the discrete variables in each of the production records, determine the association rules, so as to complete the blast furnace quantitative knowledge determination.

[0014] In the third aspect, the present application also provides an electronic device, comprising: a processor, a memory and a communication bus; the communication bus is used to connect the processor and the memory; the processor is used to execute a computer program stored in the memory to implement the method for determining blast furnace quantitative knowledge as described in the above embodiment.

[0015] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor of a computer, the computer executes the method described in the above embodiments.

[0016] Beneficial effects of the present application: The present application proposes a method, system, equipment and storage medium for determining quantitative knowledge of a blast furnace. By acquiring the production data of the blast furnace, the production data includes a variety of blast furnace data divided according to the quantitative objects in the blast furnace production process, and the blast furnace data is sliced ​​according to different types to obtain multiple production segments of each blast furnace data, and the blast furnace data is refined, which is helpful to capture subtle changes in the blast furnace production process in subsequent quantitative analysis and improve the accuracy of quantitative analysis; then, the statistical indicators of the blast furnace data in each production segment are calculated, and the statistical indicators are discretized to determine the discrete variables of the statistical indicators, which reduces the complexity of the statistical indicators and is conducive to improving the efficiency of subsequent quantitative analysis; then, the discrete variables corresponding to the production segments with the same slicing end time are spliced ​​to form multiple production records, and the production records are a collection of discrete variables associated with each blast furnace data at the same slicing end time, which helps to fully reflect the production status of the blast furnace at different time points; finally, the correlation between each discrete variable in each production record is quantitatively analyzed, and the association rules are determined to represent knowledge with the association rules. In this way, the correlation between multi-dimensional parameters in blast furnace production can be automatically mined, which effectively realizes the rapid and comprehensive extraction and quantification of knowledge, avoiding the problems of inconsistent standards and low quantification caused by the use of artificial experience to summarize the rules. The automatic mining and further verification of the correlation between the dimensional parameters of the blast furnace are realized, which can effectively realize the extraction and quantification of knowledge, avoiding the problems of inconsistent standards and low quantification caused by the use of artificial experience to summarize the rules.

[0017] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings herein are incorporated into the specification and constitute a part of the specification, showing embodiments consistent with the present application, and together with the specification, are used to explain the principles of the present application. Obviously, the drawings described below are only some embodiments of the present application, and for those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0019] Figure 1 is a flow chart of a method for determining blast furnace quantitative knowledge shown in an exemplary embodiment of the present application;

[0020] Figure 2 is a schematic diagram of the overall process of knowledge determination shown in an exemplary embodiment of the present application;

[0021] Figure 3 This is a schematic diagram of an overall knowledge determination framework shown in an exemplary embodiment of the present application.

[0022] Figure 4 is a block diagram of a blast furnace quantitative knowledge determination system shown in an exemplary embodiment of the present application;

[0023] Figure 5 It is a structural diagram of a computer system suitable for implementing the electronic device of the present application, shown as an exemplary embodiment of the present application. DETAILED DESCRIPTION

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

[0025] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present application, and thus the drawings only show components related to the present application rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the form, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0026] In the following description, a large number of details are discussed to provide a more thorough explanation of the embodiments of the present application. However, it is obvious to those skilled in the art that the embodiments of the present application can be implemented without these specific details. In other embodiments, well-known structures and devices are shown in the form of block diagrams rather than in detail to avoid making the embodiments of the present application difficult to understand.

[0027] See also Figure 1 , is a flowchart of a method for determining blast furnace quantitative knowledge according to an exemplary embodiment of the present application. The method for determining blast furnace quantitative knowledge can be executed by a client, such as Figure 1 As shown, in an exemplary embodiment, the method for determining blast furnace quantitative knowledge includes at least steps S110 to S140, which are described in detail as follows:

[0028] Step S110, obtaining production data of a blast furnace, where the production data includes a variety of blast furnace data divided according to quantitative objects in a blast furnace production process.

[0029] In one embodiment of the present application, production data is recorded over time, and the blast furnace data divided according to the quantitative object can be summarized as at least five types of raw material data, fuel data, furnace condition data, operation data and index data in the blast furnace production process. Among them, if the quantitative object is further subdivided, the raw material data mainly reflects the information of various raw materials used in the blast furnace production process, including but not limited to the blast furnace data of the composition and performance of sintered ore, pelletized ore and lump ore respectively; the fuel data mainly reflects the information of the fuel used in the blast furnace production process, including but not limited to the blast furnace data of the composition and performance of coke and coal powder respectively; the furnace condition data mainly reflects the various state information in the blast furnace smelting process, including but not limited to the real-time monitoring parameters of coal gas flow, furnace body, molten iron slag and cooling water respectively; the operation data mainly refers to the operation records and adjustment parameters in the blast furnace production process, including but not limited to the blast furnace data of the types of air volume, wind temperature, wind pressure, top pressure, top temperature, material distribution angle, charging method, iron tapping time and iron tapping amount; the index data mainly reflects the various economic and technical indicators in the blast furnace smelting process, including but not limited to the two types of blast furnace data of output and fuel ratio. In this way, the subsequent analysis of the patterns in the blast furnace production data involves multi-dimensional data, which improves the accuracy and comprehensiveness of the determination of association rules.

[0030] In one embodiment of the present application, in order to improve the subsequent processing efficiency of various blast furnace data, the real-time acquired production data can be input into the message queue, that is, each type of blast furnace data is assigned to a different message queue, so that the blast furnace data in each queue can be processed independently without interfering with other types of blast furnace data, so that each blast furnace data can be processed in parallel, improving the processing efficiency of the production data. For example, if the index data includes output and fuel ratio, then the output and fuel ratio are assigned to two different queues.

[0031] Step S120, slicing the various blast furnace data respectively to obtain multiple production segments of each blast furnace data, wherein the production segment includes blast furnace data of a preset first time length.

[0032] Specifically, the preset first duration is used as the window width of the sliding window, and the preset second duration is used as the step length of the sliding window, and the preset second duration is smaller than the preset first duration; based on the sliding window, the sequence formed over time of each blast furnace data is sliced ​​to obtain multiple production segments corresponding to each blast furnace data. In this way, segmentation helps to more accurately capture the detailed changes in the blast furnace production process, providing a basis for subsequent quantitative analysis. In addition, through slicing processing, multiple blast furnace data can be analyzed independently or combined as needed. This flexibility helps to more effectively mine data value.

[0033] In one embodiment of the present application, in the process of high-speed rail production, the smelting cycle is one of the important indicators that affect the production of blast furnaces. It is the residence time of the charge in the blast furnace during the blast furnace ironmaking process, an indicator that characterizes the material discharge speed, and an important operating parameter of blast furnace smelting. The shorter the smelting cycle, the shorter the residence time of the charge in the blast furnace, and the greater the blast furnace output. Therefore, in order to improve the accuracy of the association rule determination, the preset first time length is set to be greater than the smelting cycle of blast furnace production, so that the preset first time length includes at least one smelting cycle.

[0034] In one embodiment of the present application, each type of blast furnace data is arranged in chronological order to form a sequence, and the blast furnace data is sliced ​​according to type. Taking the first duration as 8 hours and the second duration as 1 hour as an example, starting from the starting point of the sequence formed by any (type) blast furnace data, the first 8 hours of blast furnace data in the sequence are intercepted to obtain the first production segment corresponding to the blast furnace data, and then the sliding window is slid forward in the sequence for 1 hour, and 8 hours of blast furnace data are intercepted again as the second production segment, and the above truck is repeated until the sliding window slides to the end of the sequence, and the sequence formed by the blast furnace data is completely sliced.

[0035] Step S130, calculating the statistical indicators of the blast furnace data in each production segment, and discretizing the statistical indicators to determine the discrete variables of the statistical indicators.

[0036] Specifically, calculations are performed based on the blast furnace data of the preset first time length in each production segment to determine the statistical indicators corresponding to each production segment, and the statistical indicators include statistical characteristics and linear regression slopes; different types of statistical indicators corresponding to each production segment are discretized to determine the discrete variables corresponding to each production segment.

[0037] In one embodiment of the present application, each type of blast furnace data is divided into multiple production segments, and the statistical indicators of each production segment are calculated, so as to realize the refined analysis of the blast furnace production process. Among them, the statistical characteristics include at least the mean and the standard deviation, which can generally describe the distribution of the blast furnace data in each production segment, and help to identify abnormal points, trend changes and potential problem points in the production process; the linear regression slope is associated with time, and the linear relationship of the blast furnace data in different production segments can be analyzed, and the change of the slope can reflect the change trend of the blast furnace data over time.

[0038] In one embodiment of the present application, the statistical indicators are discretized and converted from continuous numerical data into discrete classification labels to describe the characteristics of the blast furnace data in the corresponding production segment, which helps to simplify the subsequent quantitative analysis process, reduce the amount of calculation, improve the efficiency of quantitative analysis, and make the analysis results more intuitive and easy to understand.

[0039] In one embodiment of the present application, the statistical indicators corresponding to each production segment are respectively divided into equal-frequency bins to divide the numerical range of each statistical indicator into a preset number of equal-frequency intervals; the corresponding statistical indicators in each production segment are allocated to the corresponding equal-frequency intervals to determine the discrete variables of the statistical indicators corresponding to each production segment.

[0040] In one embodiment of the present application, the blast furnace data in a production segment is the Si (silicon) content in molten iron. The statistical indicators corresponding to the production segment include mean, standard deviation and linear regression slope. The preset number is set to 3 as an example. For the three statistical indicators in the production segment, each statistical indicator is subjected to equal-frequency binning, and the numerical range of each statistical indicator is divided into 3 equal-frequency intervals, that is, for the production segment, the number of statistical indicators is 3, and the number of equal-frequency intervals is 9. Among them, if the three intervals [a, b), [b, c) and [c, d) are used to represent the three equal-frequency intervals corresponding to each statistical indicator, then it is necessary to determine to which of the corresponding equal-frequency intervals [a, b), [b, c) and [c, d) the mean value of the Si content corresponding to the production fragment belongs, to which of the corresponding equal-frequency intervals [a, b), [b, c) and [c, d) the standard deviation of the Si content belongs, and to which of the corresponding equal-frequency intervals [a, b), [b, c) and [c, d) the linear regression slope of the Si content belongs. If the statistical indicator belongs to any equal-frequency interval, 1 is used to represent the categorical variable of the statistical indicator in the equal-frequency interval to which it belongs. If the statistical indicator does not belong to any equal-frequency interval, 0 is used to represent the categorical variable corresponding to the equal-frequency interval to which the statistical indicator does not belong. That is to say, the statistical indicator corresponding to a production segment, whose discrete variable is a categorical variable of 0-1 (that is, the target variable in a binary classification problem, or called a label, response variable), can be represented by one-hot encoding (a method of converting categorical variables into numerical variables), and the number of discrete variables converted by each statistical indicator is a preset number.

[0041] In one embodiment of the present application, the equal-frequency binning is processed by discretization, and can also be achieved by setting a threshold, using a clustering algorithm, a decision tree, and other methods.

[0042] Step S140, concatenate the discrete variables corresponding to the production segments with the same slicing end time to form multiple production records, where the production record is a collection of discrete variables associated with each blast furnace data at the same slicing end time.

[0043] In one embodiment of the present application, the slicing end time refers to the time point when the production segment is finished during the slicing process, that is, the moment when the production segment is terminated during slicing.

[0044] In one embodiment of the present application, the slicing end time is used as the unique identifier of the production record, and each production record is stored in a database to facilitate subsequent reading and analysis.

[0045] Step S150, quantitatively analyzing the association relationship between each discrete variable in each production record, determining the association rules, and completing the blast furnace quantitative knowledge determination.

[0046] Specifically, each production record is regarded as an item set, and each discrete variable in the production record is regarded as an item; the support of each item is calculated, and the minimum support of the item set is defined; the items whose support is greater than or equal to the minimum support are iteratively screened to obtain multiple frequent item sets, where the frequent item set is a set of at least one target item, and the support of the target item is greater than or equal to the minimum support; and multiple association rules are generated based on each frequent item set.

[0047] In one embodiment of the present application, the items with support greater than or equal to the minimum support are iteratively screened, including: screening the items with support greater than or equal to the minimum support once to obtain a frequent 1-item set, where the frequent 1-item set is a set of target items; generating a candidate 2-item set based on the frequent 1-item set, that is, a combination of two target items; calculating the support of the candidate 2-item set, and screening the candidate 2-item set with support greater than or equal to the minimum support twice as a frequent 2-item set; by continuously iterating this process until no new frequent item sets are generated, that is, until there is no candidate N+1 item set with support greater than or equal to the minimum support, the screened candidate N-item set that meets the minimum support is used as a frequent N-item set, and the final frequent item set is determined, where N is greater than or equal to 1. Among them, the candidate N-item set is a combination of N target items, the support represents the frequency of a certain item or item set in the item set, and only the item set with support greater than or equal to the minimum support is considered frequent.

[0048] In one embodiment of the present application, during the iterative screening process, the Apriori algorithm (i.e., the association rule algorithm) is used to prune frequent item sets, wherein, if an item set (a set of target items) is frequent (i.e., its support is greater than or equal to the minimum support), then all its subsets should also be frequent; conversely, if an item set is infrequent, then all its supersets (i.e., the larger item set containing the item set) are also infrequent. Based on this, for each screening, if a candidate item set contains an infrequent subset, the candidate item set can be directly deleted because it cannot be frequent, which can significantly reduce the size of the candidate item set, thereby reducing the amount of calculation required for the subsequent support calculation; finally, the pruned candidate item set is scanned, the support of each candidate item set is calculated, and the candidate item sets with a support greater than or equal to the minimum support are retained as frequent item sets, so that frequent item sets in the item set can be found more efficiently and association rules can be generated faster.

[0049] In one embodiment of the present application, the confidence of each association rule is calculated, and the minimum confidence of the association rule is defined; the association rules with confidence greater than or equal to the minimum confidence are screened to determine the final association rule.

[0050] In one embodiment of the present application, confidence is an indicator for measuring the reliability of association rules. Therefore, association rules with confidence greater than or equal to the minimum confidence are considered valid, which reveals the potential correlation between different discrete variables in the production records, that is, it mines the correlation between various blast furnace data.

[0051] In one embodiment of the present application, after determining the association rules, it also includes: visually displaying the association rules, and the visual display methods include at least network diagrams, heat maps and tables, which help to intuitively understand the relationship between multi-dimensional blast furnace data and improve the efficiency of regularity analysis; the displayed association rules can be further reviewed and screened to delete association rules that do not conform to the process logic, and the screened association rules are stored in a preset knowledge base, which can facilitate subsequent use and analysis of these rules.

[0052] See also Figure 2 , is a schematic diagram of the overall process of knowledge determination shown in an exemplary embodiment of the present application. Figure 2 As shown, the overall process of knowledge determination includes: step S1, collecting blast furnace production related data, which is equivalent to executing the above step S110; step S2, processing the blast furnace production data to obtain production records, that is, executing the above steps S120 to S140; step S3, blast furnace data storage, that is, storing the production records obtained after processing; step S4, establishing a knowledge capture discovery model, that is, executing the above step S150, determining association rules; step S5, rule storage and verification, that is, storing the association rules, and verifying whether the association rules are the actual process logic of blast furnace production. Among them, the overall process of knowledge determination has been described in detail in the above embodiments, and will not be repeated here.

[0053] See also Figure 3 , which is a schematic diagram of the overall knowledge determination framework shown in an exemplary embodiment of the present application. The framework shown in 3 includes a data acquisition module, a data processing module, a data storage module, a knowledge capture module and a knowledge filtering module, wherein the data acquisition model is used to implement Figure 2 The function performed by step S1 shown in FIG. 1 is to realize the data processing module Figure 2 The function performed in step S2 is shown, and the data storage module is used to implement Figure 2 The function performed by step S3 shown in the figure, the knowledge capture module and the knowledge filtering module are used to implement the functions performed by steps S4 and S5 respectively, which will not be described in detail here.

[0054] The method for determining blast furnace quantitative knowledge provided by the present application has the following advantages: it can automatically mine the correlation between multi-dimensional parameters in blast furnace production, effectively realize the rapid and comprehensive extraction and quantification of knowledge, and avoid the problems of inconsistent standards and low quantification degree caused by the way of summarizing laws by artificial experience. The automatic mining and further verification of the correlation between parameters of each dimension of the blast furnace are realized, which can effectively realize the extraction and quantification of knowledge, and avoid the problems of inconsistent standards and low quantification degree caused by the way of summarizing laws by artificial experience.

[0055] See also Figure 4 , is a block diagram of a blast furnace quantitative knowledge determination system shown in an exemplary embodiment of the present application. Figure 4 As shown, in an exemplary embodiment, the blast furnace quantitative knowledge determination system includes at least an acquisition module 410, a slicing module 420, a calculation module 430, a splicing module 440 and an analysis module 450, which are described in detail as follows:

[0056] An acquisition module 410 is used to acquire production data of a blast furnace, where the production data includes a variety of blast furnace data divided according to quantitative objects in a blast furnace production process;

[0057] A slicing module 420, for slicing the multiple blast furnace data respectively to obtain multiple production segments of each blast furnace data, wherein the production segment includes blast furnace data of a preset first time length;

[0058] A calculation module 430 is used to calculate the statistical indicators of the blast furnace data in each production segment, and discretize the statistical indicators to determine the discrete variables of the statistical indicators;

[0059] A splicing module 440 is used to splice the discrete variables corresponding to the production segments with the same slice end time to form multiple production records. The production record is a collection of discrete variables associated with each blast furnace data at the same slice end time;

[0060] The analysis module 450 is used to perform quantitative analysis on the association relationship between each discrete variable in each production record and determine the association rules to complete the blast furnace quantitative knowledge determination.

[0061] In one embodiment of the present application, the function of the acquisition module 410 is equivalent to Figure 3 The functions of the data acquisition module, the slicing module 420, the calculation module 430 and the splicing module 440 are equivalent to Figure 3 The data processing module shown in the figure, the function implemented by the analysis module 450 is equivalent to Figure 3 The knowledge capture module shown.

[0062] It should be noted that the blast furnace quantitative knowledge determination system provided in the above embodiment and the blast furnace quantitative knowledge determination method provided in the above embodiment belong to the same concept, and the contents of the operations performed by each module have been described in detail in the method embodiment and will not be repeated here.

[0063] The present application also provides an electronic device, including: a processor, a memory and a communication bus; the communication bus is used to connect the processor and the memory; the processor is used to execute a computer program stored in the memory to implement the blast furnace quantitative knowledge determination method as in the above embodiment.

[0064] See also Figure 5 , shows a schematic diagram of the structure of a computer system suitable for implementing an electronic device of an embodiment of the present application. It should be noted that, Figure 5 The computer system 500 of the electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0065] like Figure 5 As shown, the computer system 500 includes a central processing unit (CPU) 501, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 502 or the program loaded from the storage part 508 to the random access memory (RAM) 503, such as executing the method in the above embodiment. In the RAM 503, various programs and data required for system operation are also stored. The CPU 501, the ROM 502 and the RAM 503 are connected to each other through the bus 504. The input / output (I / O) interface 505 is also connected to the bus 504.

[0066] The following components are connected to the I / O interface 505: an input section 506 including a keyboard, a mouse, etc.; an output section 507 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to the I / O interface 509 as needed. A removable medium 511, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 510 as needed so that a computer program read therefrom is installed into the storage section 508 as needed.

[0067] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication section 509, and / or installed from a removable medium 511. When the computer program is executed by a central processing unit (CPU) 501, various functions defined in the system of the present application are executed.

[0068] The present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor of a computer, the computer executes the rule engine configuration method for early warning as described above. The computer-readable storage medium may be included in the electronic device described in the above embodiment, or may exist independently without being assembled into the electronic device.

[0069] It should be noted that the computer-readable medium shown in the embodiment of the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, an electrical, magnetic, optical, electromagnetic, infrared or semiconductor system, system or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, wherein a computer-readable computer program is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, system or device. A computer program contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0070] The flowchart and block diagram in the accompanying drawings illustrate the possible architecture, functions and operations of the system, method and computer program product according to various embodiments of the present application. Wherein, each box in the flowchart or block diagram can represent a module, a program segment, or a part of the code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0071] The units involved in the embodiments described in this application may be implemented by software or hardware, and the units described may also be set in a processor. The names of these units do not, in some cases, constitute limitations on the units themselves.

[0072] The above embodiments are merely illustrative of the principles and effects of the present application, and are not intended to limit the present application. Anyone familiar with the technology may modify or change the above embodiments without violating the spirit and scope of the present application. Therefore, all equivalent modifications or changes made by a person of ordinary skill in the art without departing from the spirit and technical ideas disclosed in the present application shall still be covered by the claims of the present application.

Claims

1. A method for determining blast furnace quantitative knowledge, characterized in that: The method comprises: Acquire production data of a blast furnace, wherein the production data includes a plurality of blast furnace data divided according to quantitative objects in a blast furnace production process; Slicing the multiple blast furnace data respectively to obtain multiple production segments of each blast furnace data, wherein the production segment includes the blast furnace data of a preset first time length; Calculating statistical indicators of the blast furnace data in each of the production segments, and discretizing the statistical indicators to determine discrete variables of the statistical indicators; The discrete variables corresponding to the production segments with the same slicing end time are spliced ​​to form a plurality of production records, wherein the production record is a set of the discrete variables associated with each blast furnace data at the same slicing end time; The correlation relationship between the discrete variables in the production records is quantitatively analyzed to determine the association rules so as to complete the quantitative knowledge determination of the blast furnace.

2. The method for determining blast furnace quantitative knowledge according to claim 1, characterized in that: The multiple blast furnace data are sliced ​​separately to obtain multiple production segments of each blast furnace data, including: Using the preset first duration as the window width of the sliding window, and using the preset second duration as the step length of the sliding window, wherein the preset second duration is smaller than the preset first duration; Based on the sliding window, each sequence of the blast furnace data formed over time is sliced ​​to obtain a plurality of production segments corresponding to each blast furnace data.

3. The method for determining blast furnace quantitative knowledge according to claim 1, characterized in that: The calculating of the statistical index of the blast furnace data in each of the production segments, and discretizing the statistical index to determine the discrete variables of the statistical index, includes: Calculate according to the blast furnace data of the preset first time length in each of the production segments to determine the statistical indicators corresponding to each of the production segments, wherein the statistical indicators include statistical characteristics and linear regression slopes; Discretization processing is performed on the different types of statistical indicators corresponding to each of the production segments to determine the discrete variables corresponding to each of the production segments.

4. The method for determining blast furnace quantitative knowledge according to claim 3, characterized in that: The discretization processing of the statistical indicator to determine the discrete variables of the statistical indicator includes: Performing equal-frequency binning on the statistical indicators corresponding to each of the production segments, so as to divide the value range of each of the statistical indicators into a preset number of equal-frequency intervals; The statistical indicator corresponding to each of the production segments is allocated to the corresponding equal-frequency interval, and the discrete variable corresponding to the statistical indicator of each of the production segments is determined.

5. The method for determining blast furnace quantitative knowledge according to any one of claims 1 to 4, characterized in that: The quantitative analysis of the association relationship between the discrete variables in the production records to determine the association rules includes: Taking each of the production records as an item set, each of the discrete variables in the production record as an item; Calculate the support of each item and define the minimum support of the item set; Iteratively screening the items whose support is greater than or equal to the minimum support to obtain a plurality of frequent item sets, wherein the frequent item set is a set of at least one target item, and the support of the target item is greater than or equal to the minimum support; A plurality of association rules are generated based on each of the frequent item sets.

6. The method for determining blast furnace quantitative knowledge according to claim 5, characterized in that: After determining the association rule, the method further includes: Calculating the confidence of each of the association rules, and defining the minimum confidence of the association rules; The association rules whose confidence is greater than or equal to the minimum confidence are screened to determine the final association rules.

7. The method for determining blast furnace quantitative knowledge according to any one of claims 1 to 4, characterized in that: After determining the association rule, the method further includes: Visually display the association rules, wherein the visual display method includes at least a network diagram, a heat map and a table; The displayed association rules are filtered, and the filtered association rules are stored in a preset knowledge base.

8. A blast furnace quantitative knowledge determination system, characterized in that: The system comprises: An acquisition module, used for acquiring production data of a blast furnace, wherein the production data includes a plurality of blast furnace data divided according to quantitative objects in a blast furnace production process; A slicing module, used for slicing the multiple blast furnace data respectively to obtain multiple production segments of each blast furnace data, wherein the production segment includes the blast furnace data of a preset first time length; A calculation module, used for calculating the statistical index of the blast furnace data in each of the production segments, and discretizing the statistical index to determine the discrete variables of the statistical index; A splicing module, used for splicing the discrete variables corresponding to the production segments with the same slicing end time to form a plurality of production records, wherein the production record is a set of the discrete variables associated with each blast furnace data at the same slicing end time; The analysis module is used to perform quantitative analysis on the association relationship between the discrete variables in the production records and determine the association rules to complete the quantitative knowledge determination of the blast furnace.

9. An electronic device, characterized in that: include: processor, memory, and communication bus; The communication bus is used to connect the processor and the memory; The processor is configured to execute the computer program stored in the memory to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and the computer program is used to make a computer execute the method according to any one of claims 1 to 7.

Images