A query analysis method and system for metallurgical electric appliance data

Abstract

The application relates to the technical field of blast furnace ironmaking control, in particular to a metallurgical electric appliance data-oriented query analysis method and system. Silicon content in molten iron, slag byproduct alkalinity multiple and coal gas conveying capacity of key nodes are collected in real time through sensors. When any parameter exceeds a preset threshold value, it is determined that there is high-emission tail gas abnormality. Based on real-time data and historical records, corresponding device node sets are determined respectively. Sample data sets are constructed by using monitoring records in the high-emission abnormal state. A similarity calculation model is trained to convergence, and a deep learning model is generated. The three device node sets are input into the model, and potential leakage nodes are output. Visual warning information of target nodes is generated. The application integrates three-dimensional data, improves the high-emission determination accuracy, realizes accurate leakage point tracing by combining the device node space topological relationship and the graph neural network, identifies CO2 high-emission risk by the alkalinity change duration, and establishes a hierarchical warning system.

Description

Technical Field

[0001] This application relates to the field of blast furnace ironmaking control technology, and in particular to a query and analysis method and system for metallurgical electrical data. Background Technology

[0002] In urban water supply systems, blast furnace metallurgical equipment systems are equipped with data acquisition systems. These systems can monitor data such as the Si content of molten iron and the basicity multiple of slag by-products at key nodes of the blast furnace metallurgical equipment, and transmit the data back to the central server. This allows management personnel to collect data such as the Si content of molten iron and the basicity multiple of slag by-products at key nodes of the blast furnace metallurgical equipment through the central server terminal for high-emission exhaust gas analysis.

[0003] However, in querying high-emission tail gas in blast furnace metallurgical equipment, it is often necessary to manually analyze the Si content of molten iron, the basicity multiple of slag by-products, and the gas supply volume associated with each key node to determine the location of high-emission tail gas. The query and analysis efficiency for metallurgical electrical data is low. Summary of the Invention

[0004] To achieve the above objectives, this application provides the following technical solution:

[0005] According to a first aspect of the present invention, the present invention claims protection for a query and analysis method for metallurgical electrical data, characterized in that it includes:

[0006] S1. Real-time acquisition of monitoring parameters of key nodes of blast furnace metallurgical equipment, including silicon content of molten iron, basicity multiple of slag by-products and gas delivery rate;

[0007] S2. Based on the silicon content of the molten iron, the basicity multiple of the slag by-products, and the gas transmission rate, determine whether the blast furnace metallurgical equipment has abnormal high-emission tail gas.

[0008] S3. When there is an abnormality in high exhaust emissions:

[0009] Based on real-time silicon content in molten iron and historical data, the first set of associated equipment nodes is determined; based on real-time basicity multiples of slag by-products and historical data, the second set of associated equipment nodes is determined; and based on real-time gas transmission volume and historical data, the third set of associated equipment nodes is determined.

[0010] S4. Construct a sample dataset, which includes: records of silicon content in molten iron, basicity multiples of slag by-products, and gas transmission volume collected from key nodes under abnormal conditions of high-emission exhaust gas.

[0011] S5. Train a similarity calculation model using the sample dataset. When the model cost function converges, a deep learning model is obtained.

[0012] S6. Input the first, second, and third device node sets into the deep learning model and output potential high-emission exhaust gas nodes. If the number of intersection nodes of the three node sets is 2, then the downstream node between the two nodes is taken as the high-emission exhaust gas node. If the number of intersection nodes is ≥3, then connect all intersection nodes and take the end node of the topology as the high-emission exhaust gas node.

[0013] Further, S2 includes:

[0014] Determine whether the silicon content of the molten iron exceeds a preset range, whether the basicity multiple of the slag by-products exceeds a preset range, or whether the gas delivery volume exceeds a preset threshold.

[0015] If any parameter exceeds the corresponding range, it is determined that there is an abnormality in high-emission exhaust gas.

[0016] Furthermore, determining the high-emission exhaust gas node in S6 includes:

[0017] Obtain the spatial location information of the first, second, and third device node sets;

[0018] Perform topology connection operations based on the spatial location information to determine the end node.

[0019] Furthermore, following S6, it also includes:

[0020] Based on the records of the alkalinity multiples of slag by-products in the second set of equipment nodes, the high-emission tail gas level is determined.

[0021] Furthermore, determining the high-emission exhaust gas level includes:

[0022] Calculate the time interval between the most recent historical moment when the basicity multiple of the slag by-product is equal to 1 and the current moment;

[0023] If the interval exceeds the preset period, it is determined to be a high level of CO2 emissions.

[0024] Furthermore, it also includes:

[0025] Based on the high CO2 emission level, early warning information for the high emission exhaust gas node is generated.

[0026] According to a second aspect of the present invention, the present invention claims protection for a query and analysis system for metallurgical electrical data, comprising a memory, a processor, and a computer program stored in the memory;

[0027] When the processor executes the computer program, it implements the steps of the query and analysis method for metallurgical electrical data.

[0028] This application relates to the field of blast furnace ironmaking control technology, and particularly to a method and system for querying and analyzing metallurgical electrical data. It uses sensors to collect real-time data on key nodes, including the silicon content of molten iron, the basicity multiple of slag by-products, and the gas delivery rate. When any parameter exceeds a preset threshold, a high-emission tail gas anomaly is identified. Based on the correlation between real-time data and historical records, corresponding equipment node sets are determined. A sample dataset is constructed using monitoring records under high-emission anomaly conditions. A similarity calculation model is trained until convergence to generate a deep learning model. The three equipment node sets are input into the model, and potential leakage nodes are output. Visualized early warning information for target nodes is generated. This invention integrates three-dimensional data to improve the accuracy of high-emission detection; combines the spatial topological relationship of equipment nodes with graph neural networks to achieve precise source tracing of leakage points; and identifies high CO2 emission risks by the duration of basicity changes, establishing a tiered early warning system. Attached Figure Description

[0029] Figure 1 A flowchart illustrating the workflow of a query and analysis method for metallurgical electrical data as claimed in an embodiment of this application;

[0030] Figure 2 This is a structural block diagram of a query and analysis system for metallurgical electrical data, which is claimed in an embodiment of this application. Detailed Implementation

[0031] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0032] The terms "first," "second," and "third" in this application are for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Therefore, a feature defined as "first," "second," or "third" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified. All directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of this application are only used to explain the relative positional relationships and movements between components in a specific orientation (as shown in the figures). If the specific orientation changes, the directional indications also change accordingly. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices.

[0033] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The presence of this phrase in various locations throughout the specification does not necessarily refer to the same embodiment, nor is it a mutually exclusive, independent, or alternative embodiment. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0034] The main solution of this invention is as follows: A query and analysis system for metallurgical electrical data queries the Si content state of molten iron, the basicity multiple of slag by-products, and the gas supply volume of key nodes in blast furnace metallurgical equipment; based on the Si content state of molten iron, the basicity multiple of slag by-products, and the gas supply volume, it determines whether the blast furnace metallurgical equipment has high-emission tail gas; when the blast furnace metallurgical equipment has high-emission tail gas, based on the Si content state of molten iron and historical Si content state data, it determines a first query record associated with the Si content state of molten iron, a second query record associated with the basicity multiple of slag by-products based on historical slag by-products, and a third query record associated with the gas supply volume based on historical gas supply volume; and it collects the high-emission tail gas nodes associated with the first query record, the second query record, and the third query record.

[0035] Because the query and analysis system for metallurgical electrical data uses the Si content of molten iron, the basicity multiple of slag by-products, and the gas supply volume as initial conditions for high-emission tail gas, and generates query records by combining known historical data, and then uses the location of the high-emission tail gas in the blast furnace metallurgical equipment that is commonly associated with each record as the location of the high-emission tail gas, it can improve the query and analysis efficiency of metallurgical electrical data compared to manually analyzing numerous numerical levels of data in the blast furnace metallurgical equipment.

[0036] To better understand the above technical solutions, the following will provide a detailed explanation of the technical solutions in conjunction with the accompanying drawings and specific implementation methods.

[0037] Reference Figure 1 , Figure 1 This is the first embodiment of the query and analysis method for metallurgical electrical data of the present invention. The method includes the following steps:

[0038] S1. Real-time acquisition of monitoring parameters of key nodes of blast furnace metallurgical equipment, including silicon content of molten iron, basicity multiple of slag by-products and gas delivery rate;

[0039] S2. Based on the silicon content of the molten iron, the basicity multiple of the slag by-products, and the gas transmission rate, determine whether the blast furnace metallurgical equipment has abnormal high-emission tail gas.

[0040] S3. When there is an abnormality in high-emission exhaust gas: Based on real-time silicon content of molten iron and historical data, determine the first set of associated equipment nodes; based on real-time basicity multiple of slag by-products and historical data, determine the second set of associated equipment nodes; based on real-time gas transmission volume and historical data, determine the third set of associated equipment nodes.

[0041] S4. Construct a sample dataset, which includes: records of silicon content in molten iron, basicity multiples of slag by-products, and gas transmission volume collected from key nodes under abnormal conditions of high-emission exhaust gas.

[0042] S5. Train a similarity calculation model using the sample dataset. When the model cost function converges, a deep learning model is obtained.

[0043] S6. Input the first, second, and third device node sets into the deep learning model and output potential high-emission exhaust gas nodes. If the number of intersection nodes of the three node sets is 2, then the downstream node between the two nodes is taken as the high-emission exhaust gas node. If the number of intersection nodes is ≥3, then connect all intersection nodes and take the end node of the topology as the high-emission exhaust gas node.

[0044] In this embodiment, the scenario is set as follows: a steel plant with a capacity of 3200m². 3 Key components of a blast furnace include: the furnace throat, tuyeres, hot blast stove inlet, and gas purification station.

[0045] S1 Real-time Monitoring:

[0046] Silicon content in molten iron: Real-time detection value from furnace throat sensor is 0.45% (normal range 0.3%-0.8%);

[0047] Basicity ratio of slag by-products: 1.8 (normal range 1.0-1.5) as detected by the slag treatment system;

[0048] Gas delivery volume: Flow meter reading at the purification station: 380,000 m³ 3 / h(threshold 350,000m) 3 / h);

[0049] S2 Anomaly Detection:

[0050] Alkalinity ratio 1.8 > 1.5 (exceeding the limit) → triggers abnormal high-emission exhaust gas;

[0051] S3 historical node location:

[0052] First equipment node set: Query records with silicon content of molten iron ≈ 0.45% in the past 30 days → associate nodes {furnace throat sensor A, molten iron conveyor belt B};

[0053] Second equipment node set: Query records with alkalinity multiple ≈ 1.8 → associated nodes {slag treatment controller C, cooling water valve D};

[0054] Third equipment node set: Query gas volume > 350,000 m³ 3 / h record → associated node {gas purification station E, booster fan F};

[0055] S4 Sample Construction:

[0056] Retrieve monitoring data from the same nodes during 10 historical high emission anomalies to construct a sample set (e.g., [Silicon content 0.42%, alkalinity 1.75, gas volume 375,000] → tag "purification station leakage");

[0057] S5 model training:

[0058] Training a similarity calculation model using a graph convolutional neural network (GCN).

[0059] Input sample set, optimize node association features → save model after cost function (cross-entropy) convergence: S6 node localization:

[0060] Input node set: {A,B},{C,D},{E,F}

[0061] Number of intersection nodes = 0 → Model output topology end nodes:

[0062] Further, S2 includes:

[0063] Determine whether the silicon content of the molten iron exceeds a preset range, whether the basicity multiple of the slag by-products exceeds a preset range, or whether the gas delivery volume exceeds a preset threshold.

[0064] If any parameter exceeds the corresponding range, it is determined that there is an abnormality in high-emission exhaust gas.

[0065] In this embodiment, the preset range is:

[0066] Silicon content in molten iron: 0.3%-0.8%;

[0067] Slag basicity ratio: 1.0-1.5;

[0068] Gas delivery threshold: 350,000 m³ 3 / h;

[0069] Decision logic:

[0070] An alkalinity factor of 1.8 > 1.5 indicates that an abnormality is triggered when a single parameter exceeds its limit.

[0071] Furthermore, determining the high-emission exhaust gas node in S6 includes:

[0072] Obtain the spatial location information of the first, second, and third device node sets;

[0073] Perform topology connection operations based on the spatial location information to determine the end node.

[0074] In this embodiment, spatial location information is obtained as follows:

[0075] Extracting node coordinates from the blast furnace BIM model:

[0076] Furnace throat A (10,20,5), conveyor belt B (15,25,5);

[0077] Controller C (30,40,0), cooling valve D (35,45,0);

[0078] Purification station E(50,60,0), fan F(45,55,0);

[0079] Topology operations:

[0080] Connect the node according to the pipeline flow direction → end coordinates (50, 60, 0) to the corresponding purification station E.

[0081] Furthermore, following S6, it also includes:

[0082] Based on the records of the alkalinity multiples of slag by-products in the second set of equipment nodes, the high-emission tail gas level is determined.

[0083] Furthermore, determining the high-emission exhaust gas level includes:

[0084] Calculate the time interval between the most recent historical moment when the basicity multiple of the slag by-product is equal to 1 and the current moment;

[0085] If the interval exceeds the preset period, it is determined to be a high level of CO2 emissions.

[0086] Furthermore, it also includes:

[0087] Based on the high CO2 emission level, early warning information for the high emission exhaust gas node is generated.

[0088] In this embodiment, a new step is added after S4:

[0089] Query the alkalinity records of the second node set {C,D}: >1.5 for 72 consecutive hours.

[0090] Level determination:

[0091] The last time the alkalinity was 1.0 was at 08:00 on May 1, 2023.

[0092] Current time: 2023-05-04 09:00;

[0093] Interval duration 73 hours > preset cycle (72 hours) → determine high CO2 emission level;

[0094] Early warning generation (claim 6):

[0095] Send the message to the control center: "Gas purification station E has experienced high CO2 emissions, exceeding the standard for 73 consecutive hours."

[0096] According to a second embodiment of the present invention, referring to Figure 2 This invention claims protection for a query and analysis system for metallurgical electrical data, comprising a memory, a processor, and a computer program stored in the memory;

[0097] When the processor executes the computer program, it implements the steps of the query and analysis method for metallurgical electrical data.

[0098] To achieve the above objectives, embodiments of the present invention also provide a query and analysis system for metallurgical electrical data. The query and analysis system for metallurgical electrical data includes: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the various steps of the query and analysis method for metallurgical electrical data as described above.

[0099] In the several embodiments provided in this application, it should be understood that the disclosed systems, methods, and approaches can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between systems or units may be electrical, mechanical, or other forms.

[0100] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated units described above can be implemented in hardware or as software functional units. The above are merely embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made based on the description and drawings of this application, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

[0101] The specific embodiments of the invention have been described in detail above, but they are only examples, and this application is not limited to the specific embodiments described above. For those skilled in the art, any equivalent modifications or substitutions to the invention are also within the scope of this application. Therefore, all equivalent changes, modifications, and improvements made without departing from the spirit and principles of this application should be covered within the scope of this application.

Claims

1. A query and analysis method for metallurgical electrical data, characterized in that, include: S1. Real-time acquisition of monitoring parameters of key nodes of blast furnace metallurgical equipment, including silicon content of molten iron, basicity multiple of slag by-products and gas delivery rate; S2. Based on the silicon content of the molten iron, the basicity multiple of the slag by-products, and the gas transmission rate, determine whether the blast furnace metallurgical equipment has abnormal high-emission tail gas. S3. When there is an abnormality in high exhaust emissions: Based on real-time silicon content in molten iron and historical data, the first set of associated equipment nodes is determined; based on real-time basicity multiples of slag by-products and historical data, the second set of associated equipment nodes is determined; and based on real-time gas transmission volume and historical data, the third set of associated equipment nodes is determined. S4. Construct a sample dataset, which includes: records of silicon content in molten iron, basicity multiples of slag by-products, and gas transmission volume collected from key nodes under abnormal conditions of high-emission exhaust gas. S5. Train a similarity calculation model using the sample dataset. When the model cost function converges, a deep learning model is obtained. S6. Input the first, second, and third device node sets into the deep learning model and output potential high-emission exhaust gas nodes. If the number of intersection nodes of the three node sets is 2, then the downstream node between the two nodes is taken as the high-emission exhaust gas node. If the number of intersection nodes is ≥3, then connect all intersection nodes and take the end node of the topology as the high-emission exhaust gas node.

2. The query and analysis method for metallurgical electrical data according to claim 1, characterized in that, S2 includes: Determine whether the silicon content of the molten iron exceeds a preset range, whether the basicity multiple of the slag by-products exceeds a preset range, or whether the gas delivery volume exceeds a preset threshold. If any parameter exceeds the corresponding range, it is determined that there is an abnormality in high-emission exhaust gas.

3. The query and analysis method for metallurgical electrical data according to claim 1, characterized in that, The high-emission exhaust gas nodes identified in S6 include: Obtain the spatial location information of the first, second, and third device node sets; Perform topology connection operations based on the spatial location information to determine the end node.

4. The query and analysis method for metallurgical electrical data according to claim 1, characterized in that, Following S6, it also includes: Based on the records of the alkalinity multiples of slag by-products in the second set of equipment nodes, the high-emission tail gas level is determined.

5. The query and analysis method for metallurgical electrical data according to claim 4, characterized in that, The determination of high-emission exhaust gas levels includes: Calculate the time interval between the most recent historical moment when the basicity multiple of the slag by-product is equal to 1 and the current moment; If the interval exceeds the preset period, it is determined to be a high level of CO2 emissions.

6. The query and analysis method for metallurgical electrical data according to claim 5, characterized in that, Also includes: Based on the high CO2 emission level, early warning information for the high emission exhaust gas node is generated.

7. A query and analysis system for metallurgical electrical data, characterized in that, Includes a memory, a processor, and a computer program stored in the memory; When the processor executes the computer program, it implements the steps of the query and analysis method for metallurgical electrical data as described in any one of claims 1-6.

Images