Blast furnace raw material abnormity coping method and device, computer equipment and storage medium

Abstract

The invention relates to the technical field of blast furnace raw material anomaly monitoring, and discloses a blast furnace raw material anomaly coping method and device, computer equipment and a storage medium, and the method comprises the steps that a pre-constructed case library is imported, and the case library comprises historical case data and raw material anomaly standards; collecting raw material quality data at the current moment; judging whether the raw material quality data at the current moment is abnormal or not according to the raw material abnormal standard; when the raw material quality data at the current moment is abnormal, retrieving the case library to obtain an approximate case most similar to the raw material quality data; and reusing or modifying the approximate case to generate a corresponding measure corresponding to the raw material quality data. According to the method, the specific conditions of the blast furnace raw material abnormity are rapidly analyzed and classified, corresponding response operation suggestions are proposed in combination with previous response experience, the working efficiency of a blast furnace raw material abnormity processing site is greatly improved, and finally, the whole-process closed-loop processing of raw material abnormity monitoring, response and summarization and induction is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of blast furnace raw material abnormality monitoring, and in particular to a blast furnace raw material abnormality response method, device, computer equipment and storage medium. Background Art

[0002] Ironmaking raw materials are the basis of blast furnace production, and the quality and properties of raw materials will directly affect the blast furnace production indicators. The so-called "70% raw materials, 30% operation" or "40% raw materials, 30% equipment, 30% operation" all illustrate the importance of raw material quality in blast furnace smelting. While the charge is participating in the reaction in the furnace, it will be significantly squeezed, mechanically worn and chemically eroded. Too low sintered ore and coke quality will seriously affect the permeability and stability of the material column inside the blast furnace. Therefore, ensuring the stability of raw material quality is one of the prerequisites for ensuring the stable and smooth operation of the blast furnace. However, in the daily production process, various raw material abnormalities will inevitably occur due to various reasons, which will have a serious impact on the normal production of the blast furnace. Therefore, it is of great significance to carry out research on the detection and intelligent fault handling methods of blast furnace raw material abnormalities to improve the efficiency and safety of steel production.

[0003] In the related art, CN117493900A is a method for evaluating the stability of blast furnace conditions based on fluctuations in the quality of blast furnace raw materials. The method predicts the condition of the blast furnace based on the relevant data of the blast furnace, including the standard deviation of the cooling wall temperature, the core temperature, the blast furnace output, the heat load fluctuation and the abnormal fluctuation of the raw material quality. The invention includes the monitoring of the fluctuation of the raw material quality and the prediction of the blast furnace condition, but there is no related technology for dealing with the blast furnace condition. At present, the monitoring and processing of the abnormality of blast furnace raw materials still remain in a relatively primary stage, that is, when the raw material quality fluctuates, the corresponding countermeasures are made based on the experience of the on-site operators. This leads to obvious subjectivity and hysteresis in the process of handling the abnormality, and it is also possible to ignore some subtle abnormalities. Summary of the invention

[0004] In view of this, the present invention provides a method, device, computer equipment and storage medium for dealing with blast furnace raw material abnormalities, so as to solve the problem that the handling of blast furnace raw material abnormalities depends on the experience of operators and the handling is delayed.

[0005] In a first aspect, the present invention provides a method for dealing with abnormalities in blast furnace raw materials, the method comprising:

[0006] Import pre-built case libraries containing historical case data and raw material anomaly standards;

[0007] Collect raw material quality data at the current moment;

[0008] Use the raw material abnormality standard to determine whether the raw material quality data at the current moment is abnormal;

[0009] When the raw material quality data at the current moment is abnormal, the case library is searched to obtain the approximate case that is most similar to the raw material quality data;

[0010] Reuse or modify similar cases to generate corresponding countermeasures for raw material quality data;

[0011] Based on the countermeasures, new cases are generated and stored in the case library.

[0012] In the present invention, by using historical raw material abnormality case source data based on a big data platform to form a multivariate case library, real-time monitoring of current raw material quality fluctuations and case retrieval of current samples to obtain the case closest to the raw material and furnace condition, reuse or modify the historical best response measures of the current case, and realize rapid analysis and classification of the specific situation of blast furnace raw material abnormality, and propose corresponding response operation suggestions based on previous response experience, which greatly improves the work efficiency of blast furnace raw material abnormality on-site. After the response is completed, the corresponding response method will be summarized as a historical case and included in the case library, which is convenient for subsequent use of this response data for abnormal processing, and finally realizes the full process closed-loop processing of raw material abnormality monitoring, response, and summary.

[0013] In an optional implementation, the historical case data includes raw material quality parameters, blast furnace condition parameters and corresponding countermeasures when the raw material abnormality occurs. The case library is constructed by the following steps:

[0014] Sort the historical case data based on date to obtain sorted historical case data;

[0015] For historical case data in different time intervals, determine the raw material abnormality standards in each time interval;

[0016] Based on the raw material abnormality standards in each time interval, the raw material quality parameters, blast furnace condition parameters and countermeasures are screened and standardized to obtain the processed raw material quality parameters, blast furnace condition parameters and countermeasures;

[0017] Based on the processed raw material quality parameters, blast furnace condition parameters and countermeasures, historical cases are generated and stored in the case library.

[0018] In this method, historical case data is sorted based on date, the corresponding raw material abnormality standards in each time interval are determined, the historical case data is screened and standardized, and a multi-case library is constructed to facilitate the subsequent use of the case library to monitor the raw material quality data in real time.

[0019] In an optional embodiment, raw material quality parameters, blast furnace condition parameters and countermeasures are screened and standardized to obtain processed raw material quality parameters, blast furnace condition parameters and countermeasures, including:

[0020] Screening the raw material quality parameters and the blast furnace condition parameters, excluding singular values ​​and null values ​​in the raw material quality parameters and the blast furnace condition parameters, and obtaining screened raw material quality parameters and the blast furnace condition parameters;

[0021] Scaling the screened raw material quality parameters and blast furnace condition parameters to obtain processed raw material quality parameters and blast furnace condition parameters;

[0022] The text operations in the countermeasures are converted into numerical data to obtain the processed countermeasures.

[0023] In this method, the redundant data in the case library is reduced by screening out the singular values ​​and null values ​​in the raw material quality parameters and blast furnace condition parameters. The differences between the features are reduced by standardizing the screened data, and the countermeasures are converted into numerical data, which makes it easier for computer equipment to use numerical data for unified analysis.

[0024] In an optional implementation, the case library is constructed by the following formula:

[0025] C=(X 1 ,X 2 ,...,X i ,Y 1 ,Y 2 ,...,Y j ,Z 1 ,Z 2 ,...,Z k )

[0026] Among them, C is the case library, X 1 ~X i is the raw material quality parameter, i is the number of raw material quality parameters, Y 1 ~Y j is the blast furnace condition parameter, j is the number of blast furnace condition parameters, Z 1 ~Z k is the response magnitude of the response measure, and k is the number of response directions of the response measure.

[0027] In this method, a multi-case library is formed by merging and sorting out the raw material quality parameters, blast furnace condition parameters and corresponding countermeasures when raw material abnormalities occur. In the process of continuous enrichment of the case library, the number k of countermeasure directions will also change with the emergence of new operating directions.

[0028] In an optional implementation, when the raw material quality data at the current moment is abnormal, the case library is searched to obtain the approximate case that is most similar to the raw material quality data, including:

[0029] Calculate the distance between the raw material quality parameters and blast furnace condition parameters at the current moment and the raw material quality parameters and blast furnace condition parameters of all historical case data in the case library;

[0030] The distances are sorted to identify the approximate cases that are most similar to the raw material quality data.

[0031] In this method, by calculating the distance between the historical case data in the case library and the raw material quality data at the current moment, the distance is sorted to determine the approximate case that is most similar to the raw material quality data at the current moment, so as to facilitate the use of the approximate case to generate the corresponding countermeasures at the current moment.

[0032] In an optional implementation, the similar case is reused or modified to generate corresponding countermeasures for the raw material quality data, including:

[0033] When the number of approximate cases is 1, the countermeasures corresponding to the approximate cases are determined to be the countermeasures corresponding to the raw material quality data;

[0034] When the number of approximate cases is greater than 1, the average value of the same response direction in the approximate cases is taken as the recommended solution, and the recommended solutions of each response direction are integrated to generate the response measures corresponding to the raw material quality data.

[0035] In this method, when the number of approximate cases is 1, the countermeasures corresponding to the approximate cases are determined to be the countermeasures corresponding to the raw material quality data. When the number of approximate cases is greater than 1, the suggested solutions of each response direction are integrated to generate the countermeasures corresponding to the raw material quality data, thereby realizing the generation of countermeasures and assisting on-site staff in formulating solutions.

[0036] In a second aspect, the present invention provides a device for dealing with abnormalities in blast furnace raw materials, the device comprising:

[0037] Case library import module, used to import pre-built case libraries, which contain historical case data and raw material anomaly standards;

[0038] Data collection module, used to collect raw material quality data at the current moment;

[0039] The abnormality judgment module is used to judge whether the raw material quality data at the current moment is abnormal by using the raw material abnormality standard;

[0040] A case library retrieval module is used to search the case library when there is an abnormality in the raw material quality data at the current moment, and obtain an approximate case that is most similar to the raw material quality data;

[0041] The countermeasure generation module is used to reuse or modify similar cases and generate countermeasures corresponding to raw material quality data.

[0042] The case generation and storage module is used to generate new cases based on the response measures and store the new cases in the case library.

[0043] In a third aspect, the present invention provides a computer device comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the method for dealing with blast furnace raw material abnormalities according to the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0044] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the method for dealing with blast furnace raw material abnormalities according to the first aspect or any corresponding embodiment thereof.

[0045] In a fifth aspect, the present invention provides a computer program product, comprising computer instructions for causing a computer to execute the method for dealing with blast furnace raw material abnormalities according to the first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0047] Figure 1 It is a flow chart of a method for dealing with abnormalities in blast furnace raw materials according to an embodiment of the present invention.

[0048] Figure 2 It is a schematic diagram of the main structure of a blast furnace raw material abnormality response system based on artificial intelligence according to an embodiment of the present invention.

[0049] Figure 3 It is a schematic diagram of the principle of a case-based reasoning algorithm according to an embodiment of the present invention.

[0050] Figure 4 It is a flow chart of another method for dealing with abnormality of blast furnace raw materials according to an embodiment of the present invention.

[0051] Figure 5 It is a flow chart of another method for dealing with blast furnace raw material abnormality according to an embodiment of the present invention.

[0052] Figure 6 It is a structural block diagram of a device for dealing with abnormalities in blast furnace raw materials according to an embodiment of the present invention.

[0053] Figure 7 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0055] In the related art, CN117493900A is a method for evaluating the stability of blast furnace conditions based on fluctuations in the quality of blast furnace raw materials. The method predicts the condition of the blast furnace based on the relevant data of the blast furnace, including the standard deviation of the cooling wall temperature, the core temperature, the blast furnace output, the heat load fluctuation and the abnormal fluctuation of the raw material quality. The invention includes the monitoring of the fluctuation of the raw material quality and the prediction of the blast furnace condition, but there is no related technology for dealing with the blast furnace condition. At present, the monitoring and processing of the abnormality of blast furnace raw materials still remain in a relatively primary stage, that is, when the raw material quality fluctuates, the corresponding countermeasures are made based on the experience of the on-site operators. This leads to obvious subjectivity and hysteresis in the process of handling the abnormality, and it is also possible to ignore some subtle abnormalities.

[0056] To solve the above problems, a method for dealing with abnormalities of blast furnace raw materials is provided in an embodiment of the present invention, which is used in a computer device. It should be noted that the execution subject may be a device for dealing with abnormalities of blast furnace raw materials, which may be implemented as part or all of a computer device through software, hardware, or a combination of software and hardware, wherein the computer device may be a terminal, a client, or a server, and the server may be a single server or a server cluster composed of multiple servers. The terminal in the embodiment of the present application may be a smart phone, a personal computer, a tablet computer, or other intelligent hardware devices. In the following method embodiments, the execution subject is a computer device as an example for explanation.

[0057] The computer equipment in this embodiment is suitable for the use scenario of real-time monitoring of the quality of blast furnace raw materials. The present invention provides a method for dealing with abnormalities in blast furnace raw materials. By using historical raw material abnormality case source data based on a big data platform to form a multivariate case library, the current raw material quality fluctuations are monitored in real time and case retrieval is performed on the current sample to obtain the case closest to the raw material and furnace condition, and the historical best response measures for the current case are reused or modified, so as to achieve rapid analysis and classification of the specific situation of blast furnace raw material abnormalities, and propose corresponding response operation suggestions in combination with previous response experience, which greatly improves the work efficiency of the blast furnace raw material abnormality handling site. After the response is completed, the corresponding response method will be summarized as a historical case and included in the case library, so as to facilitate the subsequent use of the response data for abnormal handling, and finally realize the full process closed-loop processing of raw material abnormality monitoring, response, and summary.

[0058] According to an embodiment of the present invention, an embodiment of a method for dealing with abnormalities in blast furnace raw materials is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0059] In this embodiment, a method for dealing with abnormalities in blast furnace raw materials is provided, which can be used in the above-mentioned computer equipment. Figure 1 is a flow chart of a method for dealing with abnormalities of blast furnace raw materials according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0060] Step S101, importing a pre-built case library.

[0061] In an embodiment of the present invention, the case library includes historical case data and raw material abnormality standards.

[0062] In one example, historical case sample data is exported and current data is monitored in real time by connecting to an SQL database. The collected case data set is screened and processed to remove extreme and missing data. Historical cases are integrated to form a case library. The historical raw material abnormality cases only include cases when the raw material quality is abnormal and are sorted by time. The interval is all raw material abnormality cases since the blast furnace was opened. The selection criteria for historical raw material abnormality cases are the raw material quality requirements at that time point, that is, the selection criteria for abnormal cases in different time intervals are different.

[0063] Step S102, collecting raw material quality data at the current moment.

[0064] Step S103, using the raw material abnormality standard, determining whether the raw material quality data at the current moment is abnormal.

[0065] In one example, the current raw material quality is monitored, and the monitoring of the raw material quality is performed based on the quality standard at the current time as a threshold.

[0066] Step S104: when there is an abnormality in the raw material quality data at the current moment, the case library is searched to obtain an approximate case that is most similar to the raw material quality data.

[0067] In one example, when the quality is below the standard, an abnormal warning is issued and the current quality information is exported for retrieval. When the quality is abnormal, a case search is performed on the current sample to find the most similar historical case.

[0068] Step S105, reusing or modifying the similar cases to generate corresponding countermeasures for the raw material quality data.

[0069] In one example, the search results are analyzed, and the cases are reused or modified to find the most suitable response measures for this abnormal sample. The response measures should be specific to specific values ​​or value ranges. For example, if it is recommended to reduce the batch size, it should be specific to the specific weight range of the reduction.

[0070] Step S106: Generate a new case based on the countermeasures and store the new case in the case library.

[0071] For example, after the abnormal problem is solved, the current case is evaluated and stored to enrich the case library. Case storage should select samples with practical application effects for storage. If the solution implemented under the current sample fails to play an effective response effect, the storage of the sample will be abandoned.

[0072] In one implementation scenario, Figure 2 is a schematic diagram of the main structure of a blast furnace raw material abnormality response system based on artificial intelligence according to an embodiment of the present invention. Figure 2 As shown in the figure, the logical structure of the artificial intelligence-based blast furnace raw material abnormality response system is mainly composed of data collection, data processing, establishment of historical case library, case retrieval, case reuse and case storage, which are used to perform the following steps:

[0073] S1: Export historical case sample data and monitor current data in real time by connecting to the SQL database.

[0074] S2: Screen and process the collected case data set to remove extreme and missing data.

[0075] S3: Integrate historical cases to form a case library.

[0076] S4: Monitor the quality of current raw materials. When the quality is abnormal, perform case retrieval on the current sample to find the most similar historical case.

[0077] S5: Analyze the search results, reuse or modify the cases to find the most suitable response measures for this abnormal sample.

[0078] S6: The analysis results are exported to the user machine to guide on-site response. If the solution implemented under the current sample successfully plays an effective role in response, the sample will be stored as a case and eventually included in the case library. Figure 3 is a schematic diagram of the principle of a case-based reasoning algorithm according to an embodiment of the present invention, such as Figure 3 As shown, the details of result export and case storage include: the suggested solution of the current abnormal sample obtained according to the analysis of step S5 is exported to the user machine to assist the on-site staff in formulating a solution; after the final solution is formulated and implemented, the relevant raw material information, furnace condition information and solution of this sample are integrated to form a case; if the response to the raw material abnormality achieves the expected effect, the case is included in the case library; if the response to the raw material abnormality does not achieve the desired result, the case is abandoned for further storage.

[0079] The method for dealing with abnormal blast furnace raw materials provided in this embodiment forms a multivariate case library by using historical raw material abnormality case source data based on a big data platform, monitors the current raw material quality fluctuations in real time, and performs case retrieval on the current sample to obtain the case that is closest to the raw material and furnace condition, reuses or modifies the historical best response measures for the current case, and realizes rapid analysis and classification of the specific situation of blast furnace raw material abnormalities. Combined with previous response experience, corresponding response operation suggestions are proposed, which greatly improves the work efficiency of blast furnace raw material abnormality handling on site. After the response is completed, the corresponding response method will be summarized as a historical case and included in the case library, which is convenient for subsequent use of the response data for abnormal handling, and finally realizes the full process closed-loop processing of raw material abnormality monitoring, response, and summary.

[0080] In this embodiment, a method for dealing with abnormalities in blast furnace raw materials is provided, which can be used in the above-mentioned computer equipment. Figure 4 is a flow chart of another method for dealing with abnormal blast furnace raw materials according to an embodiment of the present invention. Figure 4 As shown, the process includes the following steps:

[0081] Step S401, importing a pre-built case library.

[0082] Specifically, the historical case data includes raw material quality parameters, blast furnace condition parameters and corresponding countermeasures when the raw material abnormality occurs. The above step S401 includes:

[0083] Step S4011, sort the historical case data based on date to obtain sorted historical case data.

[0084] Step S4012, for historical case data in different time intervals, determine the raw material abnormality standard in each time interval.

[0085] In one example, historical case data is selected and sorted based on date. The data are raw material quality parameters, blast furnace condition parameters and corresponding countermeasures when raw material abnormalities occur in the history of blast furnaces. Here, the standard for raw material abnormalities will change with time, that is, the standards for different time intervals are different, so the raw material abnormality standard is the standard in the time interval where the case is located. At the same time, there are corresponding standards for furnace condition parameters that change with time, which are mainly used to classify furnace conditions and are not used as standards for data screening. Among them, the raw material quality parameters are various parameters related to blast furnace raw materials, such as coke CSR, coke M40, sinter drum coefficient, sinter basicity, etc. Blast furnace condition parameters include various parameters related to blast furnace conditions, such as gas utilization rate, pressure difference, furnace temperature, heat load, etc., which will be added or replaced according to specific needs, such as sinter FeO, coke moisture, etc., which can be replaced or increased or decreased according to different concerns of different blast furnaces. Other parameters may also include air volume, output, etc.; countermeasures include changing ore batches, changing coke batches, changing coal injection volume, adjusting air volume, and other parameters in blast furnace operation. Here, the raw material quality parameters and blast furnace condition parameters can be added or deleted according to specific needs. The countermeasures are the measures taken in history. When new measures appear in new cases, they will be automatically added. Here, the types of raw material quality parameters and blast furnace condition parameters should be as detailed as possible, and the types of raw material quality parameters and blast furnace condition parameters are not limited in the present invention.

[0086] Step S4013, based on the raw material abnormality standard in each time interval, the raw material quality parameters, blast furnace condition parameters and countermeasures are screened and standardized to obtain processed raw material quality parameters, blast furnace condition parameters and countermeasures.

[0087] In some optional implementations, the above step S4013 includes:

[0088] Step a1, screening the raw material quality parameters and blast furnace condition parameters, excluding singular values ​​and null values ​​in the raw material quality parameters and blast furnace condition parameters, and obtaining screened raw material quality parameters and blast furnace condition parameters.

[0089] Step a2, scaling the screened raw material quality parameters and blast furnace condition parameters to obtain processed raw material quality parameters and blast furnace condition parameters.

[0090] Step a3, converting the text operations in the countermeasures into numerical data to obtain the processed countermeasures.

[0091] In one example, during the data screening process, each parameter has a corresponding value range, and different parameters have different requirements. For raw material quality parameters, when a singular value or null value appears in a certain data at a certain time point, it will be considered that the data at that time point has no reference value, that is, the group of data will be deleted. For each raw material quality parameter, there is a corresponding normal value range. A value exceeding this range is a singular value, and a null value means that there is no value of the parameter at that time point in the database, which is displayed as None. When a singular value or null value appears in a certain data at a certain time point, it will be considered that the data at that time point has no reference value. This situation is generally considered to be an abnormality in data detection.

[0092] For blast furnace condition data, when a singular value or null value appears in a data at a certain time point, this parameter in the data group will be marked, and the distance calculation for this parameter in the subsequent case retrieval will be skipped. Each furnace condition parameter also has its normal range. When a singular value or null value appears in a data at a certain time point, it is judged that the corresponding detection equipment is faulty, so the parameter will not be used as the retrieval basis.

[0093] In data processing, the filtered data also needs to be standardized, that is, based on the Z-Score standardization method, the raw material quality and blast furnace condition parameter characteristics are scaled to a range of mean 0 and standard deviation 1, which helps to eliminate the differences between the characteristics. For countermeasures, it is necessary to convert textual operations into numerical data for analysis, such as 5 for increasing the ore batch by 5t, and 5 for reducing the air volume by 200m 3 / min is -200.

[0094] In this method, the redundant data in the case library is reduced by screening out the singular values ​​and null values ​​in the raw material quality parameters and blast furnace condition parameters. The differences between the features are reduced by standardizing the screened data, and the countermeasures are converted into numerical data, which makes it easier for computer equipment to use numerical data for unified analysis.

[0095] Step S4014, based on the processed raw material quality parameters, blast furnace condition parameters and countermeasures, generate historical cases and store the historical cases in the case library.

[0096] In some optional implementations, the above step S4013 includes:

[0097] Step b1, construct the case library through the following formula:

[0098] C=(X 1 ,X 2 ,...,X i ,Y 1 ,Y 2 ,...,Y j ,Z1 ,Z 2 ,...,Z k )

[0099] Among them, C is the case library, X 1 ~X i is the raw material quality parameter, i is the number of raw material quality parameters, Y 1 ~Y j is the blast furnace condition parameter, j is the number of blast furnace condition parameters, Z 1 ~Z k is the response magnitude of the response measure, and k is the number of response directions of the response measure.

[0100] In one example, the details for establishing a historical case library are as follows:

[0101] The above data are combined and sorted to form a multi-case library C = (X 1 ,X 2 …,X i ,Y 1 ,Y 2 …,Y j ,Z 1 ,Z 2 …,Z k ), where X 1 ~X i is the raw material quality parameter, a total of i parameters have been added; Y 1 ~Y j is the corresponding blast furnace condition parameter, a total of j parameters have been added; Z 1 ~Z k is the k response directions of the response measures in the historical cases, and its value is the response range of the direction. In the process of continuous enrichment of the case library, the k value will also change with the emergence of new operation directions. Here, the case library has m rows and n columns, m = i + j + k, n is the total number of cases in the case library, and m is the sum of raw material parameters, furnace condition parameters, and response measures.

[0102] In this method, historical case data is sorted based on date, the corresponding raw material abnormality standard in each time interval is determined, historical case data is screened and standardized, and a multivariate case library is constructed to facilitate the subsequent use of the case library for real-time monitoring of raw material quality data. The raw material quality parameters, blast furnace condition parameters and corresponding countermeasures at the time of raw material abnormality are combined and sorted to form a multivariate case library. In the process of continuous enrichment of the case library, the number of response directions k of the countermeasures will also change with the emergence of new operation directions.

[0103] Step S402, collect the raw material quality data at the current moment. Figure 1 Step S102 of the illustrated embodiment will not be described in detail here.

[0104] Step S403: Use the raw material abnormality standard to determine whether the raw material quality data at the current moment is abnormal. Figure 1 Step S103 of the illustrated embodiment will not be described in detail here.

[0105] Step S404: When the raw material quality data at the current moment is abnormal, the case library is searched to obtain the approximate case that is most similar to the raw material quality data. Figure 1 Step S104 of the illustrated embodiment will not be described in detail here.

[0106] Step S405: Reuse or modify the similar cases to generate corresponding countermeasures for the raw material quality data. Figure 1 Step S105 of the illustrated embodiment will not be described in detail here.

[0107] Step S406: Generate a new case based on the response measures and store the new case in the case library. Figure 1 Step S106 of the illustrated embodiment will not be described in detail here.

[0108] The blast furnace raw material abnormality coping method provided in the present embodiment, by sorting the historical case data based on the date, determining the corresponding raw material abnormality standard in each time interval, screening and standardizing the historical case data, constructing a multivariate case library, and facilitating the subsequent use of the case library to monitor the raw material quality data in real time. By screening out the singular values ​​and null values ​​in the raw material quality parameters and the blast furnace condition parameters, the redundant data in the case library is reduced, and by standardizing the screened data, the difference between the features is reduced, and the countermeasures are converted into numerical data, so that the computer equipment can use numerical data for unified analysis. By merging and combing the raw material quality parameters, blast furnace condition parameters and corresponding countermeasures at the time of raw material abnormality, a multivariate case library is formed, and in the process of the continuous enrichment of the case library, the countermeasures of the countermeasures The number of k values ​​will also change with the emergence of new operating directions.

[0109] In this embodiment, a method for dealing with abnormalities in blast furnace raw materials is provided, which can be used in the above-mentioned computer equipment. Figure 5 is a flow chart of another method for dealing with abnormal blast furnace raw materials according to an embodiment of the present invention, such as Figure 5 As shown, the process includes the following steps:

[0110] Step S501: Import the pre-built case library. Figure 4 Step S401 of the illustrated embodiment will not be described in detail here.

[0111] Step S502, collect the raw material quality data at the current moment. Figure 4Step S402 of the illustrated embodiment will not be described in detail here.

[0112] Step S503: Use the raw material abnormality standard to determine whether the raw material quality data at the current moment is abnormal. Figure 4 Step S403 of the illustrated embodiment will not be described in detail here.

[0113] Step S504: when there is an abnormality in the raw material quality data at the current moment, the case library is searched to obtain an approximate case that is most similar to the raw material quality data.

[0114] Specifically, the above step S504 includes:

[0115] Step S5041, calculating the distance between the raw material quality parameters and blast furnace condition parameters at the current moment and the raw material quality parameters and blast furnace condition parameters of all historical case data in the case library.

[0116] Step S5042, sorting the distances to determine the approximate case that is most similar to the raw material quality data.

[0117] In one example, the quality of raw materials is monitored using the quality standard at the current time as a threshold. When the quality is lower than the standard, an abnormal warning is issued and the current quality information is exported for retrieval.

[0118] Case retrieval is based on the K-Nearest Neighbor (KNN) classification algorithm. The idea of ​​this method is: in the feature space, if most of the K nearest samples (i.e., the closest samples in the feature space) near a sample belong to a certain category, then the sample also belongs to this category. The KNN algorithm itself is simple and effective. It is a lazy-learning algorithm. The classifier does not need to be trained using a training set. The training time complexity is 0, and its computational complexity is only related to the number of samples in the training set.

[0119] For the KNN algorithm, the distance calculation needs to be defined. Here, the Euclidean distance is used to calculate the distance D between samples:

[0120] D=ω 1 (ω 11 (xx 1 ) 2 +ω 12 (xx 2 ) 2 +…+ω 1i (xx i ) 2 )+ω 2 (ω 21 (yy 2 ) 2 +ω22 (yy 2 ) 2 +…+ω 2j (yy j ) 2 )

[0121] where ω 1 ,ω 2 The value is 0 or 1. When calculating the distance of raw material mass, ω 1 =1,ω 2 =0, when calculating furnace distance ω 1 =0,ω 2 =1;ω 11 ~ω 1i is the weight of each parameter of raw material quality; ω 21 ~ω 2j is the weight of each furnace condition parameter. Here ω 11 ~ω 1i The default value is 0.5, and it will also be adjusted according to the type of raw material abnormality and actual situation. For example, when a certain quality of coke is abnormal, the weight of the coke parameter is adjusted to 1, and the others remain at 0.5; when it is considered that the impact of the fluctuation of a certain quality parameter on the blast furnace can be ignored, its weight can be adjusted to 0.1 or 0. 21 ~ω 2j The default value is 0.5. When one or some furnace condition data exceeds the standard range, the parameter weight is adjusted to 1 for calculation.

[0122] Case retrieval has two retrieval modes for case libraries of different sizes. When the number of cases in the case library is limited, hierarchical retrieval is performed: first, the distance between the raw material quality between the current sample and all samples in the case library is calculated based on the K nearest neighbor classification algorithm and sorted, and K1 cases with similar raw material quality to the current sample are screened out; secondly, the furnace condition distance between the current sample and K1 samples with similar raw materials is calculated and sorted, and K2 cases with similar raw material quality and furnace conditions to the current sample are obtained for subsequent analysis, where K2≤K1. After each distance calculation is completed, it needs to be standardized to scale the distance feature to between 0 and 1 to obtain the similarity S=1-Dstandard. The standardization calculation formula is as follows:

[0123]

[0124] Among them, d i is the distance between the current case and all historical cases, d max is the maximum value among all distances, d min is the minimum value of all distances, that is, the values ​​calculated by D above. Here, i ranges from 0 to the number of all historical cases, that is, 0-n.

[0125] When the number of cases in the case library is rich enough, perform accurate retrieval: first classify the case library C according to the furnace condition information to obtain multiple case libraries C 0 ~C j =(X 1 ,X 2 …,X i ,Z 1 ,Z 2 …,Z k ). Where C 0 This is the case when the furnace conditions are normal. 1 ~C j are case libraries under j kinds of abnormal furnace conditions. Here, since multiple furnace condition parameters exceed the standard at one time point, C 1 ~C j When the raw material quality is abnormal, first determine the current furnace condition information to match the case library. When the furnace condition is normal, use C 0 The case library is searched. When a parameter of the furnace condition is abnormal, the case library matching it is selected for retrieval. When multiple furnace condition parameters are abnormal, multiple corresponding case libraries are selected for combined retrieval. The case retrieval principle is consistent with the hierarchical retrieval, and finally K3 cases matching the current sample are obtained. Among them, the determination of K1, K2 and K3 values ​​is controlled by adjusting the similarity threshold. Generally, the threshold is 0.05.

[0126] In this method, by calculating the distance between the historical case data in the case library and the raw material quality data at the current moment, the distance is sorted to determine the approximate case that is most similar to the raw material quality data at the current moment, so as to facilitate the use of the approximate case to generate the corresponding countermeasures at the current moment.

[0127] Step S505: reuse or modify the similar cases to generate corresponding countermeasures for the raw material quality data.

[0128] Specifically, the above step S505 includes:

[0129] Step S5051, when the number of approximate cases is 1, determining the countermeasures corresponding to the approximate cases as the countermeasures corresponding to the raw material quality data.

[0130] Step S5052, when the number of approximate cases is greater than 1, the average value of the same response direction in the approximate cases is used as a suggested solution, and the suggested solutions of each response direction are integrated to generate response measures corresponding to the raw material quality data.

[0131] In one example, whether it is hierarchical retrieval or precise retrieval, one or more cases and their countermeasures that are very close to the current sample can be obtained in the end. When the number of approximate cases is 1, its countermeasures are directly taken as the recommended solution for the current sample; when the number of approximate cases is greater than 1, its countermeasures are integrated, and when there are multiple non-zero recommended solutions for the same response direction, the average value is taken as the final recommended solution, and finally the integrated recommended solution for multiple directions of the current sample is obtained. For example, if two historical case recommended solutions for the current sample are obtained (z 1 =5,z 2 =10,z 3 =0), (z 1 =8,z 2 =0,z 3 =0), then the proposed solution after integration is (z 1 =6.5,z 2 =5,z 3 =0).

[0132] Step S506: Generate a new case based on the countermeasures and store the new case in the case library. Figure 4 Step S406 of the illustrated embodiment will not be described in detail here.

[0133] The method for dealing with abnormalities in blast furnace raw materials provided in this embodiment calculates the distance between the historical case data in the case library and the raw material quality data at the current moment, sorts the distances to determine the approximate cases that are most similar to the raw material quality data at the current moment, and facilitates the use of the approximate cases to generate the corresponding countermeasures at the current moment. When the number of approximate cases is 1, the countermeasures corresponding to the approximate cases are determined to be the countermeasures corresponding to the raw material quality data. When the number of approximate cases is greater than 1, the recommended solutions of each response direction are integrated to generate the countermeasures corresponding to the raw material quality data, thereby realizing the generation of countermeasures and assisting on-site staff in formulating solutions.

[0134] In this embodiment, a blast furnace raw material abnormality response device is also provided, which is used to implement the above-mentioned embodiments and preferred embodiments, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware for a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived.

[0135] This embodiment provides a blast furnace raw material abnormality response device, such as Figure 6 As shown, including:

[0136] The case library import module 601 is used to import a pre-built case library, which contains historical case data and raw material abnormality standards. Figure 1Step S101 of the illustrated embodiment will not be described in detail here.

[0137] The data collection module 602 is used to collect the raw material quality data at the current moment. Figure 1 Step S102 of the illustrated embodiment will not be described in detail here.

[0138] The abnormality judgment module 603 is used to judge whether the raw material quality data at the current moment is abnormal by using the raw material abnormality standard. Figure 1 Step S103 of the illustrated embodiment will not be described in detail here.

[0139] The case library search module 604 is used to search the case library when the raw material quality data at the current moment is abnormal, and obtain the approximate case that is most similar to the raw material quality data. Figure 1 Step S104 of the illustrated embodiment will not be described in detail here.

[0140] The countermeasure generation module 605 is used to reuse or modify similar cases to generate countermeasures corresponding to the raw material quality data. Figure 1 Step S105 of the illustrated embodiment will not be described in detail here.

[0141] The case generation and storage module 606 is used to generate new cases based on the response measures and store the new cases in the case library. Figure 1 Step S106 of the illustrated embodiment will not be described in detail here.

[0142] In some optional implementations, the historical case data includes raw material quality parameters, blast furnace condition parameters and corresponding countermeasures when the raw material abnormality occurs, and the case library import module 601 includes:

[0143] The data sorting unit is used to sort the historical case data based on the date to obtain sorted historical case data.

[0144] The abnormality standard determination unit is used to determine the raw material abnormality standard in each time interval for historical case data in different time intervals.

[0145] The data screening and standardization unit is used to screen and standardize the raw material quality parameters, blast furnace condition parameters and countermeasures based on the raw material abnormality standards in each time interval, and obtain the processed raw material quality parameters, blast furnace condition parameters and countermeasures.

[0146] The case storage unit is used to generate and store historical cases based on processed raw material quality parameters, blast furnace condition parameters and countermeasures.

[0147] In some optional implementations, the data screening and standardization unit includes:

[0148] The data screening subunit is used to screen the raw material quality parameters and blast furnace condition parameters, exclude singular values ​​and null values ​​in the raw material quality parameters and blast furnace condition parameters, and obtain the screened raw material quality parameters and blast furnace condition parameters.

[0149] The data scaling subunit is used to scale the screened raw material quality parameters and blast furnace condition parameters to obtain processed raw material quality parameters and blast furnace condition parameters.

[0150] The text conversion subunit is used to convert the text operations in the countermeasures into numerical data to obtain the processed countermeasures.

[0151] In some optional implementations, the case library is constructed by the following formula:

[0152] C=(X 1 ,X 2 ,...,X i ,Y 1 ,Y 2 ,...,Y j ,Z 1 ,Z 2 ,...,Z k )

[0153] Among them, C is the case library, X 1 ~X i is the raw material quality parameter, i is the number of raw material quality parameters, Y 1 ~Y j is the blast furnace condition parameter, j is the number of blast furnace condition parameters, Z 1 ~Z k is the response magnitude of the response measure, and k is the number of response directions of the response measure.

[0154] In some optional implementations, the case library retrieval module 604 includes:

[0155] The distance calculation unit is used to calculate the distance between the raw material quality parameters and blast furnace condition parameters at the current moment and the raw material quality parameters and blast furnace condition parameters of all historical case data in the case library.

[0156] The distance sorting unit is used to sort the distances and determine the approximate case that is most similar to the raw material quality data.

[0157] In some optional implementations, the countermeasure generation module 605 includes:

[0158] The first countermeasure generating unit is used to determine, when the number of the approximate cases is 1, that the countermeasure corresponding to the approximate case is the countermeasure corresponding to the raw material quality data.

[0159] The second countermeasure generation unit is used to, when the number of approximate cases is greater than 1, take the average value of the same countermeasure direction in the approximate cases as a suggested solution, integrate the suggested solutions of each countermeasure direction, and generate countermeasures corresponding to the raw material quality data.

[0160] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0161] The blast furnace raw material abnormality response device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0162] The embodiment of the present invention also provides a computer device having the above Figure 6 The device shown is for dealing with abnormalities in blast furnace raw materials.

[0163] See also Figure 7 , Figure 7 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 7 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 7 A processor 10 is taken as an example.

[0164] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0165] The memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0166] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0167] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0168] The computer device also includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30 and the output device 40 may be connected via a bus or other means. Figure 7 The example of connecting through bus is taken in the following.

[0169] The input device 30 can receive input digital or character information, and generate key signal input related to the user settings and function control of the computer device, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator bar, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The above-mentioned display device includes but is not limited to a liquid crystal display, a light emitting diode, a display and a plasma display. In some optional embodiments, the display device can be a touch screen.

[0170] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0171] A part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the existence of the computer program instruction in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc., and accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium accessible to the computer.

[0172] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A method for dealing with abnormalities in blast furnace raw materials, characterized in that: The method comprises: Importing a pre-built case library containing historical case data and raw material anomaly standards; Collect raw material quality data at the current moment; Using the raw material abnormality standard, determining whether the raw material quality data at the current moment is abnormal; When the raw material quality data at the current moment is abnormal, searching the case library to obtain an approximate case that is most similar to the raw material quality data; Reusing or modifying the approximate case to generate corresponding countermeasures for the raw material quality data; Based on the countermeasures, a new case is generated and stored in a case library.

2. The method according to claim 1, characterized in that The historical case data includes raw material quality parameters, blast furnace condition parameters and corresponding countermeasures when raw material abnormalities occur. The case library is constructed through the following steps: Sorting the historical case data based on date to obtain sorted historical case data; For historical case data in different time intervals, determine the raw material abnormality standards in each time interval; Based on the raw material abnormality standards in each time interval, the raw material quality parameters, blast furnace condition parameters and countermeasures are screened and standardized to obtain processed raw material quality parameters, blast furnace condition parameters and countermeasures; Based on the processed raw material quality parameters, blast furnace condition parameters and countermeasures, historical cases are generated and stored in the case library.

3. The method according to claim 2, characterized in that The raw material quality parameters, blast furnace condition parameters and countermeasures are screened and standardized to obtain the processed raw material quality parameters, blast furnace condition parameters and countermeasures, including: Screening the raw material quality parameters and blast furnace condition parameters, excluding singular values ​​and null values ​​in the raw material quality parameters and blast furnace condition parameters, and obtaining screened raw material quality parameters and blast furnace condition parameters; Scaling the screened raw material quality parameters and blast furnace condition parameters to obtain the processed raw material quality parameters and blast furnace condition parameters; The text operations in the countermeasures are converted into numerical data to obtain the processed countermeasures.

4. The method according to claim 2, characterized in that: The case library is constructed by the following formula: C=(X1,X2,…,X i ,Y1,Y2,…,Y j ,Z1,Z2,…,Z k ) Among them, C is the case library, X1~X i is the raw material quality parameter, i is the number of the raw material quality parameters, Y1~Y j is the blast furnace condition parameter, j is the number of the blast furnace condition parameters, Z1~Z k is the response amplitude of the response measure, and k is the number of response directions of the response measure.

5. The method according to claim 2, characterized in that: When the raw material quality data at the current moment is abnormal, searching the case library to obtain the approximate case that is most similar to the raw material quality data includes: Calculate the distance between the raw material quality parameters and blast furnace condition parameters at the current moment and the raw material quality parameters and blast furnace condition parameters of all historical case data in the case library; The distances are sorted to determine the approximate case that is most similar to the raw material quality data.

6. The method according to claim 1, characterized in that The reusing or modifying the approximate case to generate the corresponding countermeasures for the raw material quality data includes: When the number of the approximate cases is 1, determining the countermeasure corresponding to the approximate case as the countermeasure corresponding to the raw material quality data; When the number of the approximate cases is greater than 1, the average value of the same response direction in the approximate cases is taken as a suggested solution, and the suggested solutions of each response direction are integrated to generate response measures corresponding to the raw material quality data.

7. A device for dealing with abnormalities in blast furnace raw materials, characterized in that: The device comprises: A case library import module, used to import a pre-built case library, the case library containing historical case data and raw material anomaly standards; Data collection module, used to collect raw material quality data at the current moment; An abnormality judgment module, used to judge whether the raw material quality data at the current moment is abnormal by using the raw material abnormality standard; A case library retrieval module, used to search the case library when the raw material quality data at the current moment is abnormal, and obtain an approximate case that is most similar to the raw material quality data; A countermeasure generation module, used for reusing or modifying the approximate case to generate countermeasures corresponding to the raw material quality data; The case generation and storage module is used to generate new cases based on the countermeasures and store the new cases in a case library.

8. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method for dealing with blast furnace raw material abnormalities according to any one of claims 1 to 6 by executing the computer instructions.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the method for dealing with blast furnace raw material abnormalities according to any one of claims 1 to 6.

10. A computer program product, characterized in that The method comprises computer instructions for causing a computer to execute the method for dealing with abnormality of blast furnace raw materials according to any one of claims 1 to 6.

Images