Soft melting zone root monitoring model construction method and soft melting zone root monitoring method

Abstract

The invention relates to the technical field of blast furnace ironmaking intelligent application, and discloses a soft melting zone root monitoring model construction method and a soft melting zone root monitoring method.The method comprises the steps that real-time blast furnace cooling wall temperature data and real-time static pressure difference data are collected; utilizing the soft melting zone root monitoring model to generate soft melting zone root working conditions corresponding to the real-time blast furnace cooling wall temperature data and the real-time static pressure difference data based on the real-time blast furnace cooling wall temperature data and the real-time static pressure difference data; and adjusting the feedback relation model based on a pre-trained operation system, and generating an adjustment suggestion for the blast furnace in combination with the working condition of the root of the soft melting zone. The method can effectively reflect the change condition of the root position of the soft melting zone in the blast furnace production process, provides corresponding operation improvement suggestions according to the change condition of the root position of the soft melting zone so as to prevent furnace condition fluctuation caused by the change of the root position of the soft melting zone, has the advantages of being convenient to operate, comprehensive, visual and remarkable in effect, and has wide application prospects. And an instructive basis is provided for actual production.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent application of blast furnace ironmaking, and in particular to a method for constructing a soft melting zone root monitoring model and a method for monitoring the soft melting zone root. Background Art

[0002] The soft melting zone of a blast furnace plays a key role in the distribution of coal gas flow in the furnace and in the stable operation process. Its shape determines the distribution of the middle and lower parts of the blast furnace gas and the distribution of the temperature field in the blast furnace. Its shape and position have a significant impact on the smelting process of the blast furnace, such as the pre-reduction of ore, the silicon content of pig iron, the utilization of coal gas, the temperature and activity of the furnace, and the maintenance of the furnace lining. The shape and position of the soft melting zone of a blast furnace are a comprehensive reflection of the means of adjusting the upper and lower parts of the blast furnace, and are the guarantee for the blast furnace to achieve excellent economic and technical indicators and achieve high quality, high yield and low consumption. Therefore, it is necessary to obtain a reasonable root position of the soft melting zone through operational adjustment. Since the blast furnace itself is a "black box" and its internal state cannot be directly observed, it is particularly important to develop online monitoring technology that can reflect the changes in the root position of the blast furnace soft melting zone, and give corresponding adjustment suggestions in real time based on the judgment of the root position of the soft melting zone.

[0003] In the related art, in the current blast furnace production, the blast furnace operator usually judges the change of the root position of the soft melting zone according to the change of the pressure difference on the upper part of the blast furnace based on the production experience. For example, when the root position of the soft melting zone moves upward, the pressure difference on the upper part of the blast furnace increases, but the specific position of the soft melting zone cannot be determined. The judgment of the degree of movement of the root position of the soft melting zone also varies due to the experience differences of the operators, which lacks guidance. At the same time, the existing data analysis methods cannot achieve the visual and precise positioning of the root position of the soft melting zone, and all stop at the analysis and judgment of the root position or temperature field of the blast furnace soft melting zone. On this basis, no in-depth guidance and suggestions are given to the blast furnace operation, so the application has limitations. These situations cause the control of the blast furnace condition to be often in a passive state, which is not conducive to the long-term stable and smooth operation of the blast furnace. Summary of the invention

[0004] In view of this, the present invention provides a method for constructing a soft melting zone root monitoring model and a soft melting zone root monitoring method to solve the problem that it is difficult to monitor the root of the blast furnace soft melting zone due to the production experience of production personnel.

[0005] In a first aspect, the present invention provides a method for constructing a soft melting zone root monitoring model, the method comprising:

[0006] Collect sample blast furnace cooling wall temperature data and sample static pressure difference data;

[0007] The cooling wall surface of the blast furnace is unfolded in the circumferential direction and projected onto a two-dimensional plane, and the sample blast furnace cooling wall temperature data is filled into the corresponding position of the two-dimensional plane to obtain a visualization grid, wherein the ordinate of the visualization grid is used to represent the elevation of the blast furnace, and the abscissa of the visualization grid is used to represent the circumferential angle of the blast furnace;

[0008] Using the interpolation algorithm, the visualized grid is filled and interpolated to obtain a virtual grid, which covers all areas of the blast furnace cooling wall.

[0009] Using the contour line search algorithm, the grids with the same temperature of the blast furnace cooling wall in the virtual grid are linked to draw a two-dimensional plane model of the root position of the blast furnace soft melting zone;

[0010] The two-dimensional plane model is optimized using the sample static pressure difference data to construct a soft melting zone root monitoring model, wherein the soft melting zone root monitoring model is used to determine the soft melting zone root position.

[0011] In the present invention, by collecting rich and detailed sample blast furnace production data, fully obtaining representative data sources, and using sample blast furnace cooling wall temperature data and sample static pressure difference data to build a soft melting zone root monitoring model, in which the blast furnace soft melting zone root position can be visualized. Through the soft melting zone root monitoring model, it is possible to provide real-time blast furnace operation adjustment suggestions for changes in the soft melting zone root position, and to close the loop of blast furnace soft melting zone root position judgment and operation adjustment suggestions, providing constructive guidance for driving blast furnace operation adjustment based on the soft melting zone root position.

[0012] In an optional implementation, the sample blast furnace cooling wall temperature data is filled into the corresponding position of the two-dimensional plane to obtain a visualization grid, including:

[0013] Based on the sensor position of the data source of the sample blast furnace cooling stave temperature data, fill the sample blast furnace cooling stave temperature data into the position corresponding to the sensor position in the two-dimensional plane;

[0014] According to the data volume and accuracy requirements of the sample blast furnace cooling wall temperature data, the size of the visualization grid is determined, and the visualization grid is obtained by arranging the sample blast furnace cooling wall temperature data.

[0015] In this method, the data measured by each sensor are plotted on a two-dimensional plane at a position precisely corresponding to the position of the sensor from which the data originated. The size of the visualization grid is determined according to the data volume and accuracy requirements of the blast furnace cooling wall temperature field data, and the grid is arranged according to the plane of the blast furnace wall to obtain an offline two-dimensional visualization temperature field without interpolation filling.

[0016] In an optional implementation, using an isoline search algorithm, grids with the same blast furnace cooling wall temperature in a virtual grid are linked to draw a two-dimensional plane model of the root position of the blast furnace soft melting zone, including:

[0017] Establish a mapping table between different blast furnace cooling wall temperature ranges and different colors;

[0018] Using the mapping table and the sample blast furnace cooling wall temperature data, the temperature normal distribution diagram corresponding to the sample blast furnace cooling wall temperature data of each section of the blast furnace cooling wall with a production and a fuel ratio within a preset range is screened, and the division interval of each section temperature is determined;

[0019] Based on the divided intervals, the grids with the same temperature of the blast furnace cooling wall in the virtual grid are linked to obtain a two-dimensional plane model of the root position of the blast furnace soft melting zone.

[0020] In this method, a virtual grid reflecting the required spatial resolution is drawn to cover the plane area where no sensors are used to collect blast furnace cooling wall temperature data and static pressure difference data. Contour lines are fitted to the isovalues ​​and the results are displayed on a computer screen, allowing users to more intuitively determine the specific location of the root of the soft melting zone.

[0021] In a second aspect, the present invention provides a method for monitoring the root of a soft melting zone, the method comprising:

[0022] Collect real-time blast furnace cooling wall temperature data and real-time static pressure difference data;

[0023] Using the soft melting zone root monitoring model, based on the real-time blast furnace cooling wall temperature data and the real-time static pressure difference data, the soft melting zone root working conditions corresponding to the real-time blast furnace cooling wall temperature data and the real-time static pressure difference data are generated, wherein the soft melting zone root monitoring model is constructed using the soft melting zone root monitoring model construction method of any one of the first aspects;

[0024] Based on the pre-trained operating system adjustment feedback relationship model and combined with the working conditions at the root of the soft melting zone, adjustment suggestions for the blast furnace are generated.

[0025] In the present invention, the real-time production data of the blast furnace is input into the constructed soft melting zone root monitoring model to generate real-time blast furnace soft melting zone root conditions, which can effectively reflect the changes in the soft melting zone root position during the blast furnace production process, and put forward corresponding operation improvement suggestions based on the changes in the soft melting zone root position to prevent furnace condition fluctuations caused by changes in the soft melting zone root position. It has the advantages of convenient operation, comprehensive and intuitive, and significant effects, and provides a guiding basis for actual production.

[0026] In an optional implementation, the working conditions of the root of the soft melting zone include upward movement, stability and downward movement of the root of the soft melting zone, and the operation system adjustment feedback relationship model is trained in the following way:

[0027] Obtain historical operation cases corresponding to the working conditions at the root of each soft melting zone;

[0028] The feedback relationship model is trained using the root working conditions of each soft melting zone and historical operation cases to obtain the trained operation system adjustment feedback relationship model.

[0029] In this method, an actual production case database is used to provide real-time operational adjustment suggestions for changes in the root position of the soft melting zone. Through the continuous updating and application of the case database, a key channel is opened for the control of the blast furnace soft melting zone, facilitating real-time adjustment of the blast furnace condition.

[0030] In a third aspect, the present invention provides a device for constructing a soft melting zone root monitoring model, the device comprising:

[0031] The first data acquisition module is used to collect sample blast furnace cooling wall temperature data and sample static pressure difference data;

[0032] A visualization grid construction module is used to expand the cooling wall surface of the blast furnace in the circumferential direction and project it onto a two-dimensional plane, and fill the sample blast furnace cooling wall temperature data into the corresponding position of the two-dimensional plane to obtain a visualization grid, wherein the ordinate of the visualization grid is used to represent the elevation of the blast furnace, and the abscissa of the visualization grid is used to represent the circumferential angle of the blast furnace;

[0033] The numerical filling interpolation module is used to fill and interpolate the visual grid using the interpolation algorithm to obtain a virtual grid, which covers all areas of the blast furnace cooling wall;

[0034] The isoline search module is used to link the grids with the same temperature of the blast furnace cooling wall in the virtual grid by using the isoline search algorithm, and draw a two-dimensional plane model of the root position of the blast furnace soft melting zone;

[0035] The model building module is used to optimize the two-dimensional plane model using the sample static pressure difference data and build a soft melting zone root monitoring model, wherein the soft melting zone root monitoring model is used to determine the soft melting zone root position.

[0036] In a fourth aspect, the present invention provides a soft melting belt root monitoring device, the device comprising:

[0037] The second data acquisition module is used to collect real-time blast furnace cooling wall temperature data and real-time static pressure difference data;

[0038] A soft melting zone root condition generation module, which is used to generate the soft melting zone root condition corresponding to the real-time blast furnace cooling wall temperature data and the real-time static pressure difference data by using the soft melting zone root monitoring model, based on the real-time blast furnace cooling wall temperature data and the real-time static pressure difference data, wherein the soft melting zone root monitoring model is constructed by using the soft melting zone root monitoring model construction device of the third aspect;

[0039] The adjustment suggestion generation module is used to generate adjustment suggestions for the blast furnace based on the pre-trained operation system adjustment feedback relationship model and the working conditions at the root of the soft melting zone.

[0040] In a fifth aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the soft melting zone root monitoring model construction method of the above-mentioned first aspect or any corresponding embodiment thereof, or executes the soft melting zone root monitoring method of the above-mentioned second aspect or any corresponding embodiment thereof by executing the computer instructions.

[0041] In a sixth 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 constructing a soft melting zone root monitoring model according to the first aspect or any corresponding embodiment thereof, or to execute the method for monitoring the soft melting zone root according to the second aspect or any corresponding embodiment thereof.

[0042] In the seventh aspect, the present invention provides a computer program product, comprising computer instructions, which are used to enable a computer to execute the method for constructing a soft melting zone root monitoring model according to the first aspect or any corresponding embodiment thereof, or to execute the method for monitoring the soft melting zone root according to the second aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] 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.

[0044] Figure 1 It is a flow chart of a method for constructing a soft melting zone root monitoring model according to an embodiment of the present invention.

[0045] Figure 2 It is a flow chart of the application of an intelligent control system for a blast furnace driven by the position of the root of a soft melting zone according to an embodiment of the present invention.

[0046] Figure 3 It is a flow chart of another method for constructing a soft melting zone root monitoring model according to an embodiment of the present invention.

[0047] Figure 4 The figure is a flow chart of a method for monitoring the root of a soft melting zone according to an embodiment of the present invention.

[0048] Figure 5 It is a schematic diagram of temperature field interpolation of an online monitoring visualization model for the root position of a blast furnace soft melting zone according to an embodiment of the present invention.

[0049] Figure 6 It is a schematic diagram of display results obtained by an online monitoring visualization model of the root position of a blast furnace soft melting zone according to an embodiment of the present invention.

[0050] Figure 7 It is a schematic diagram of the data collection process of a blast furnace intelligent control system driven by the root position of a soft melting zone according to an embodiment of the present invention.

[0051] Figure 8 It is a comparative schematic diagram before and after the application of a blast furnace intelligent control system driven by the root position of a soft melting zone according to an embodiment of the present invention.

[0052] Fig. 9 4 is a structural block diagram of a device for constructing a soft melting zone root monitoring model according to an embodiment of the present invention.

[0053] Fig.10 4 is a structural block diagram of a soft melting zone root monitoring device according to an embodiment of the present invention.

[0054] Fig.11 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0055] 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.

[0056] In the related art, in the current blast furnace production, the blast furnace operator usually judges the change of the root position of the soft melting zone according to the change of the pressure difference on the upper part of the blast furnace based on the production experience. For example, when the root position of the soft melting zone moves upward, the pressure difference on the upper part of the blast furnace increases, but the specific position of the soft melting zone cannot be determined. The judgment of the degree of movement of the root position of the soft melting zone also varies due to the experience differences of the operators, which lacks guidance. At the same time, the existing data analysis methods cannot achieve the visual and precise positioning of the root position of the soft melting zone, and all stop at the analysis and judgment of the root position or temperature field of the blast furnace soft melting zone. On this basis, no in-depth guidance and suggestions are given to the blast furnace operation, so the application has limitations. These situations cause the control of the blast furnace condition to be often in a passive state, which is not conducive to the long-term stable and smooth operation of the blast furnace.

[0057] The invention patent (application number CN 202210982214.8) discloses a method, device and storage medium for calculating the root height of the soft melting zone of a blast furnace. The temperature data of each temperature measuring point on the cooling wall of the blast furnace is periodically obtained and preprocessed, and the temperature change amplitude and temperature repetition number of the obtained temperature data are statistically calculated. The position of the root of the soft melting zone is determined according to the change in the number of temperature repetitions of each temperature measuring point to calculate the specific height value. This method provides good data support for the shape calculation of the blast furnace soft melting zone, but the degree of visualization is low. The invention patent (application number CN 202110137263.7) discloses a method and system for visualizing the temperature field data of the soft melting zone of a blast furnace. By preprocessing the offline temperature field data of the soft melting zone of a blast furnace, a three-dimensional texture object for organizing the temperature field data of the soft melting zone of a blast furnace is created, and the pixels in the three-dimensional texture object are filled and interpolated, and the three-dimensional texture object after filling and interpolation is sampled to obtain color values, and the color values ​​are displayed on the screen image. The temperature field data of the soft melting zone of a blast furnace is displayed more comprehensively and intuitively, and three-dimensional visualization of the temperature field distribution of the soft melting zone of a blast furnace is realized. However, due to the offline analysis method, this method cannot achieve online monitoring.

[0058] In order to solve the above problems, a method for monitoring the root of a soft melting belt is provided in an embodiment of the present invention, which is used in a computer device. It should be noted that its execution subject can be a soft melting belt root monitoring device, which can be implemented as part or all of the computer device through software, hardware, or a combination of software and hardware. The computer device can be a terminal, a client, or a server. The server can be a single server or a server cluster composed of multiple servers. The terminal in the embodiment of the present application can be a smart phone, a personal computer, a tablet computer, or other intelligent hardware devices. In the following method embodiments, the execution subject is taken as an example of a computer device for explanation.

[0059] The computer equipment in this embodiment is suitable for use scenarios in which the changes in the root position of the soft melting zone are monitored during the blast furnace production process. The present invention provides a soft melting zone root monitoring method, inputs the real-time production data of the blast furnace into the constructed soft melting zone root monitoring model, generates real-time blast furnace soft melting zone root conditions, and can effectively reflect the changes in the root position of the soft melting zone during the blast furnace production process, and proposes corresponding operation improvement suggestions based on the changes in the root position of the soft melting zone to prevent furnace condition fluctuations caused by changes in the root position of the soft melting zone. It has the advantages of convenient operation, comprehensive and intuitive, and significant effects, and provides a guiding basis for actual production.

[0060] According to an embodiment of the present invention, an embodiment of a method for constructing a soft melt zone root monitoring model 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.

[0061] In this embodiment, a method for constructing a soft melting zone root monitoring model is provided, which can be used in the above-mentioned computer device. Figure 1 is a flow chart of a method for constructing a soft melting zone root monitoring model according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0062] Step S101, collecting sample blast furnace cooling wall temperature data and sample static pressure difference data.

[0063] In one example, the temperature and static pressure difference data of the blast furnace cooling wall are collected, and the data are preprocessed to make their values ​​fall within a reasonable range. The preprocessing is to standardize the data, select the blast furnace cooling wall data that meets the root position of the soft melting zone, and detect it when selecting the data. If the data exceeds the upper limit of the indicator or is lower than the lower limit, it is detected as an abnormal value and removed. The missing data that is removed is filled with possible values.

[0064] Step S102, unfold the blast furnace cooling wall surface in a circumferential direction and project it onto a two-dimensional plane, fill the sample blast furnace cooling wall temperature data into the corresponding position of the two-dimensional plane, and obtain a visualization grid.

[0065] In the embodiment of the present invention, the ordinate of the visualization grid is used to represent the elevation of the blast furnace, and the abscissa of the visualization grid is used to represent the circumferential angle of the blast furnace.

[0066] In one example, the cooling wall surface of a blast furnace is unfolded in a circular direction and projected onto a two-dimensional plane, where the ordinate and abscissa represent the elevation and circumferential angle of the blast furnace, respectively. The measurement data of each sensor is plotted on a two-dimensional plane at a position that precisely corresponds to the position of the sensor from which the data comes. The size of the visualization grid should be determined based on the data volume and accuracy requirements of the temperature field data of the blast furnace cooling wall. Among them, the arrangement of sensors is based on the shape of the furnace body. The blast furnace body includes several parts, such as the furnace body, furnace waist, furnace belly, and furnace hearth. The shape of each part is different. The furnace waist and furnace hearth are cylinders, and the furnace waist and furnace belly are frustums. The number and size of cooling walls are different. Therefore, the number and position of thermocouples installed on the cooling wall are not equidistant and equal in number.

[0067] Step S103, using an interpolation algorithm, fills and interpolates the visualized grid to obtain a virtual grid, where the virtual grid covers all areas of the blast furnace cooling wall.

[0068] In one example, a software development tool was used to write a high-speed interpolation and contour search algorithm that draws a virtual grid reflecting the desired spatial resolution, covering the flat area without sensors. The visualization grid is filled and interpolated based on the Kriging interpolation algorithm.

[0069] Step S104, using an isoline search algorithm, linking grids with the same blast furnace cooling wall temperature in the virtual grid to draw a two-dimensional plane model of the root position of the blast furnace soft melting zone.

[0070] In one example, a curve vector diagram is generated, which links the positions of the measured data items with the same value, and a two-dimensional plane model of the root position of the blast furnace soft melting zone is drawn. The temperature values ​​in the processed cooling wall temperature field are mapped to the HSV color space and then converted to the RGB color space, and the isovalued color blocks are fitted with isovalue lines, and the results are displayed on the computer screen.

[0071] Step S105, optimizing the two-dimensional plane model using the sample static pressure difference data to construct a soft melting zone root monitoring model.

[0072] In the embodiment of the present invention, the soft melting zone root monitoring model is used to determine the soft melting zone root position.

[0073] In one implementation scenario, Figure 2 : is a schematic diagram of the application of a blast furnace intelligent control system driven by the root position of a soft melting zone according to an embodiment of the present invention, such as Figure 2 As shown, the application of the blast furnace intelligent control system driven by the root position of the soft melting zone includes: obtaining the blast furnace cooling wall temperature and static pressure difference data during the blast furnace smelting process; preprocessing the cooling wall temperature data to build a blast furnace soft melting zone position algorithm model; using static pressure difference data to verify the accuracy of the algorithm model, and releasing the verified model online; using the algorithm model to judge the direction and degree of movement of the soft melting zone position, whether the soft melting zone position moves upward or downward; querying the operation adjustment suggestions from the soft melting zone position movement case library, and adopting the upper system or lower system accordingly; providing the operation adjustment suggestions to the computer PC / mobile APP for reference by the blast furnace operator.

[0074] The method for constructing the soft melting zone root monitoring model provided in this embodiment fully obtains representative data sources by collecting rich and detailed sample blast furnace production data, and uses sample blast furnace cooling wall temperature data and sample static pressure difference data to build a soft melting zone root monitoring model, in which the root position of the blast furnace soft melting zone can be visualized. Through the soft melting zone root monitoring model, it is possible to give real-time blast furnace operation adjustment suggestions based on the changes in the root position of the soft melting zone, and the blast furnace soft melting zone root position judgment and operation adjustment suggestions are closed-looped, providing constructive guidance for driving blast furnace operation adjustments based on the root position of the soft melting zone.

[0075] In this embodiment, a method for constructing a soft melting zone root monitoring model is provided, which can be used in the above-mentioned computer device. Figure 3 FIG. 4 is a flowchart of another method for constructing a soft melting zone root monitoring model according to an embodiment of the present invention. Figure 3 As shown, the process includes the following steps:

[0076] Step S301, collect sample blast furnace cooling wall temperature data and sample static pressure difference data. Figure 1 Step S101 of the illustrated embodiment will not be described in detail here.

[0077] Step S302, unfold the blast furnace cooling wall surface in a circumferential direction and project it onto a two-dimensional plane, fill the sample blast furnace cooling wall temperature data into the corresponding position of the two-dimensional plane, and obtain a visualization grid.

[0078] Specifically, the above step S302 includes:

[0079] Step S3021, based on the sensor position of the data source of the sample blast furnace cooling stave temperature data, fill the sample blast furnace cooling stave temperature data into the position corresponding to the sensor position in the two-dimensional plane.

[0080] Step S3022, determining the size of the visualization grid according to the data volume and accuracy requirements of the sample blast furnace cooling stave temperature data, and arranging the visualization grid in combination with the sample blast furnace cooling stave temperature data.

[0081] In one example, the measurement data of each sensor is plotted on a two-dimensional plane at a position exactly corresponding to the position of the sensor from which the data originated. The size of the visualization grid should be determined based on the data volume and accuracy requirements of the blast furnace cooling wall temperature field data.

[0082] In this method, the data measured by each sensor are plotted on a two-dimensional plane at a position precisely corresponding to the position of the sensor from which the data originated. The size of the visualization grid is determined according to the data volume and accuracy requirements of the blast furnace cooling wall temperature field data, and the grid is arranged according to the plane of the blast furnace wall to obtain an offline two-dimensional visualization temperature field without interpolation filling.

[0083] Step S303, using an interpolation algorithm, fills and interpolates the visualized grid to obtain a virtual grid, which covers all areas of the blast furnace cooling wall. Figure 1 Step S103 of the illustrated embodiment will not be described in detail here.

[0084] Step S304, using an isoline search algorithm, linking grids with the same blast furnace cooling wall temperature in the virtual grid to draw a two-dimensional plane model of the root position of the blast furnace soft melting zone.

[0085] Specifically, the above step S304 includes:

[0086] Step S3041, establishing a mapping table between different blast furnace cooling wall temperature ranges and different colors.

[0087] Step S3042, using the mapping table and the sample blast furnace cooling wall temperature data, screen the temperature normal distribution diagram corresponding to the sample blast furnace cooling wall temperature data of each section of the blast furnace cooling wall with output and fuel ratio within the preset range, and determine the division interval of each temperature section.

[0088] Step S3043, based on the divided intervals, the grids with the same blast furnace cooling wall temperature in the virtual grid are linked to draw a two-dimensional plane model of the root position of the blast furnace soft melting zone.

[0089] In one example, the visualization grid is filled and interpolated based on the Kriging interpolation algorithm. The temperature values ​​in the processed cooling wall temperature field are mapped to the HSV color space and then converted to the RGB color space, and the isovalued color blocks are fitted with isovalue lines, and the results are displayed on the computer screen.

[0090] Specifically, the possible values ​​are obtained by using the adjacent grid average interpolation algorithm: The calculation of the possible values ​​may include: using the interpolation method, for example, if there is no thermocouple inserted in the T0 position, but the adjacent positions T1, T2, T3, T4, T5, T6, T7, T8 have thermocouples installed, then the distances between T0 and T1, T2, T3...T8 are calculated, which are s1, s2, s3...s8 respectively, and the influence coefficients of T1 to T8 on T0 are respectively

[0091] 1 / s1 / (1 / s1+1 / s2+1 / s3+1 / s4+1 / s5+1 / s6+1 / s7+1 / s8),

[0092] 1 / s2 / (1 / s1+1 / s2+1 / s3+1 / s4+1 / s5+1 / s6+1 / s7+1 / s8),

[0093] 1 / s3 / (1 / s1+1 / s2+1 / s3+1 / s4+1 / s5+1 / s6+1 / s7+1 / s8) ...

[0095] 1 / s8 / ((1 / s1+1 / s2+1 / s3+1 / s4+1 / s5+1 / s6+1 / s7+1 / s8))

[0096] First, determine the grid location distribution of the missing values, and then average the data around the grid to obtain the missing value data.

[0097] The temperature and static pressure data of each cooling wall are divided into different ranges and corresponded to different colors to form a mapping table. Taking the cooling wall temperature as an example, the temperature range of each cooling wall is different. According to historical data, the normal distribution diagram of the temperature of all thermocouples in each cooling wall with a reasonable output and fuel ratio is selected. According to the distribution diagram, the division interval of each temperature section is determined.

[0098] In this method, a virtual grid reflecting the required spatial resolution is drawn to cover the plane area where no sensors are used to collect blast furnace cooling wall temperature data and static pressure difference data. Contour lines are fitted to the isovalues ​​and the results are displayed on a computer screen, allowing users to more intuitively determine the specific location of the root of the soft melting zone.

[0099] Step S305, optimize the two-dimensional plane model using the sample static pressure difference data to construct a monitoring model for the root of the soft melting zone. Figure 1 Step S105 of the illustrated embodiment will not be described in detail here.

[0100] The method for constructing a monitoring model for the root of the soft melting zone provided in this embodiment is to plot the data measured by each sensor on a two-dimensional plane at a position exactly corresponding to the position of the sensor from which the data comes, determine the size of the visualization grid according to the data volume and accuracy requirements of the blast furnace cooling stave temperature field data, and arrange it according to the plane expansion of the blast furnace wall to obtain an offline two-dimensional visualization temperature field without interpolation filling. By drawing a virtual grid reflecting the required spatial resolution, covering the plane area where no sensor collects the blast furnace cooling stave temperature data and static pressure difference data, performing contour line fitting on the equal values, and displaying the results on the computer screen, it is convenient for users to more intuitively determine the specific position of the root of the soft melting zone.

[0101] In this embodiment, a method for monitoring the root of a soft melting strip is provided, which can be used in the above-mentioned computer device. Figure 4 is a flow chart of a method for monitoring the root of a soft melting zone according to an embodiment of the present invention. Figure 4 As shown, the process includes the following steps:

[0102] Step S401, collecting real-time blast furnace cooling wall temperature data and real-time static pressure difference data.

[0103] In one example, online blast furnace cooling wall temperature and static pressure difference data are collected, and the data are preprocessed so that their values ​​fall within a reasonable range.

[0104] Step S402, using the soft melting zone root monitoring model, based on the real-time blast furnace cooling wall temperature data and the real-time static pressure difference data, generates the soft melting zone root working conditions corresponding to the real-time blast furnace cooling wall temperature data and the real-time static pressure difference data.

[0105] In the embodiment of the present invention, the soft melting zone root monitoring model is constructed by using the above-mentioned soft melting zone root monitoring model construction method.

[0106] In one example, the online blast furnace cooling wall temperature, static pressure difference data collection and the soft melting zone root monitoring model algorithm constructed in the above steps are packaged and deployed to a Linux system server. The application service is started and configured through the system service manager on the server side so that it can run continuously in the background, thereby realizing the two-dimensional plane online visualization of the root position of the blast furnace soft melting zone.

[0107] Specifically, the two-dimensional plane of the root position of the furnace soft melting zone is visualized online, and the tested application system is packaged into an executable JAR or WAR package, which is uploaded to the Linux server through a secure file transfer protocol. On the server side, the application service is started and configured through the system service manager so that it can run continuously in the background. A load balancer is introduced to distribute network traffic, improve the availability, reliability and scalability of the system, and use Nginx to listen to HTTP requests from the client, and then transparently forward these requests to the backend according to preset rules.

[0108] Step S403, based on the pre-trained operation system adjustment feedback relationship model and combined with the working conditions at the root of the soft melting zone, generate adjustment suggestions for the blast furnace.

[0109] In an optional embodiment, the root operating conditions of the soft melting zone include upward movement, stability and downward movement of the root of the soft melting zone, and the operating system adjustment feedback relationship model is trained in the following manner: obtaining historical operating cases corresponding to each soft melting zone root operating condition; using each soft melting zone root operating condition and historical operating cases to train the feedback relationship model to obtain the trained operating system adjustment feedback relationship model.

[0110] In one example, based on the above online system, the system interface is optimized, the system prompt function is added, and a feedback relationship is established between the soft melting zone root position movement and the operation system adjustment, so as to obtain a blast furnace intelligent control system driven by the soft melting zone root position. The established feedback relationship between the soft melting zone root position movement and the operation system adjustment includes three working conditions: upward, stable, and downward movement of the soft melting zone root. The feedback relationship model is trained based on the historical data of each working condition, and the training data of each working condition is no less than 10 groups.

[0111] For example, when the soft melting zone root position driving blast furnace intelligent control system is applied to the blast furnace system, it is connected to the blast furnace monitoring system, data acquisition system, user interaction system, and injection coal quantity adjustment system to realize the blast furnace soft melting zone root position online driving blast furnace intelligent control. The application in the blast furnace system is an intelligent application throughout, and the specific application process includes the following steps:

[0112] SS1. The data acquisition system automatically collects, pre-processes and stores the blast furnace cooling wall parameter measurement data, which are input into the server from the blast furnace cooling wall sensor in the form of digital data.

[0113] SS2. Process the measured data into visual information, and use algorithms on the computer to perform secondary processing on the visual information. The measured data is presented in the form of two-dimensional graphic contour lines.

[0114] SS3, the database system and the computer are connected to the server via a network to achieve online data analysis, and the system can also extract any part of the accumulated digital data from the database system as needed for offline analysis.

[0115] SS4. After the online data analysis is completed, the system gives the judgment result and pops up a window prompt, and also gives corresponding operation adjustment suggestions.

[0116] SS5. After the adjustment suggestion is adopted and executed, it continues to affect the changing trend of the root position of the soft melting zone. Repeat steps SS1 to SS5 to drive the intelligent operation of the blast furnace based on the root position of the soft melting zone.

[0117] In one implementation scenario, a 2680m 3 A blast furnace is an example. Since the blast furnace was started, the furnace condition has frequently fluctuated due to the change of the root position of the soft melting zone, which has a great negative effect on the stable and smooth operation of the blast furnace.

[0118] 1. Develop an intelligent blast furnace control system driven by the root position of the soft melting zone based on the production data of the blast furnace. The specific steps are as follows:

[0119] S1. Collect offline blast furnace cooling wall temperature and static pressure difference data, standardize the data, convert the data format into the matrix form required by the system, select the blast furnace cooling wall data that meets the root position of the soft melting zone, and select the copper cooling wall data from the furnace belly to the lower part of the furnace body (16.6m~25.5m). When selecting data, detect it. If the data exceeds the upper limit (70℃) or is lower than the lower limit (30℃), it is detected as an abnormal value. The abnormal value is removed to make the remaining values ​​fall into a reasonable range. For the missing data that are removed, possible values ​​are used to fill in, and the possible values ​​are obtained by the average interpolation algorithm of adjacent grids: first determine the grid position distribution of the missing value, and then average the data around the grid to obtain the missing value data.

[0120] S2, the cooling wall surface of the blast furnace is unfolded in the circumferential direction and projected onto a two-dimensional plane, where the ordinate and abscissa represent the elevation and circumferential angle of the blast furnace respectively. The measurement data of each sensor is plotted on the two-dimensional plane at the position exactly corresponding to the position of the sensor from which the data comes. The size of the visualization grid is determined according to the data volume and accuracy requirements of the blast furnace cooling wall temperature field data. As shown in S1, the cooling wall temperature data obtained by the blast furnace in this embodiment each time is 368. Each data is marked as X according to the elevation (H), angle (R), and temperature value (T). ij =(H i , R ij , T ij ), X ij 0≤i≤8, 0≤j≤46, where H i Indicates the elevation of each floor, i indicates the elevation, R ij represents the circular angle at each layer elevation, j represents each circular angle, T ij Represents each thermocouple at each elevation, and j represents the jth thermocouple. The selected 368 cooling wall temperature data include 8 elevations, 46 circumferential angles, and the basic pixel size is 8×46. Figure 5 : is a schematic diagram of temperature field interpolation of an online monitoring visualization model of the root position of a blast furnace soft melting zone according to an embodiment of the present invention, according to which the pixel size of the three interpolation data between every two data is reserved as follows: Figure 5 As shown, X ij The offline two-dimensional visualized temperature field without interpolation filling is obtained by unfolding the blast furnace wall plane.

[0121] S3, based on the Kriging interpolation algorithm, the temperature field of step S2 is interpolated and optimized, and the variogram is used as the basic tool to make linear unbiased and optimal estimates of unknown sample points, and modeling is carried out on this basis. Use Python software to write high-speed interpolation and contour search algorithms to fill and interpolate the visual grid.

[0122] (, h) = 1 / 2 {[() - (+h)]2}

[0123] Among them, (), (, h) are points X ij , X ij +h observation value, h is the step size, {[()-(+h)] 2 Variance

[0124] The algorithm is used to draw a virtual grid that reflects the required spatial resolution. The number of virtual grids matches the reserved pixels of S1, covering the plane area without sensors. The temperature values ​​in the processed cooling wall temperature field are mapped to the HSV color space and then converted to the RGB color space, and the isovalue blocks are fitted with contour lines, and the results are displayed on the computer screen. Based on the above content, contour lines and vector diagrams including curves linking the positions of the measured data items with the same value are generated to complete the two-dimensional plane offline visualization of the root position of the blast furnace soft melting zone. Because the soft melting zone is usually in the part with the largest airflow fluctuation, the pressure change gradient in the height direction of this part is the fastest. Therefore, the position of the soft melting zone can be verified by the change value of the static pressure difference per unit height. Figure 6 is a schematic diagram of the display result obtained by an online monitoring visualization model of the root position of the blast furnace soft melting zone according to an embodiment of the present invention, and the selected cooling wall temperature data is checked with the corresponding blast furnace static pressure difference data, such as Figure 6 As shown, the verification results of the two show that the root position of the soft melting zone established according to the cooling wall temperature field is consistent with the pressure difference trend result. In this embodiment, the root position of the soft melting zone is between 20.6m and 23.7m.

[0125] S4, package the tested data collection in step S1 and the algorithm application system in step S3 to obtain an executable JAR or WAR package, Figure 7 Schematic diagram of the data acquisition process of a blast furnace intelligent control system driven by the root position of a soft melting zone according to an embodiment of the present invention, which is uploaded to a Linux server via a secure file transfer protocol. Figure 7 As shown. On the server side, the application service is started and configured through the system service manager so that it can run continuously in the background. A load balancer is introduced to distribute network traffic to improve the availability, reliability and scalability of the system. Nginx is used to listen to HTTP requests from the client and then transparently forward these requests to the backend according to preset rules. On the server side, the application service is started and configured through the system service manager so that it can run continuously in the background, realizing the two-dimensional plane online visualization of the root position of the blast furnace soft melting zone.

[0126] S5, based on the online system in S4, optimize the system interface and add system prompt functions such as Figure 6As shown. According to the three working conditions of the soft melting zone root moving up, stable and downward, relevant operation adjustment historical cases are selected to establish the operation system adjustment feedback relationship model. The feedback relationship model is trained based on the historical data of each working condition. The training data of each working condition is no less than 10 groups, and the blast furnace intelligent control system driven by the soft melting zone root position is obtained.

[0127] Adjustments to the operating system include the adjustment of the distribution system, air supply system, and slag making system. Different distribution systems can form different gas flow distributions, and further form different soft melting zones. Factors affecting the distribution system are reflected in coke batches, ore batches, and distribution matrices. The air supply system is mainly reflected in the size of the blast kinetic energy, which directly acts on the combustion zone. The length of the combustion zone affects the root position of the soft melting zone, and the factors that determine the air supply system include air volume, air temperature, and tuyere area. The slag making system directly affects the position and permeability of the soft melting zone, which is mainly reflected in the control of slag basicity. High basicity leads to late initial slag formation, increased viscosity, poor permeability, and downward movement of the soft melting zone. Conversely, the soft melting zone moves upward.

[0128] Based on the actual production indicators of the blast furnace and according to the movement of the root position of the soft melting zone, the system automatically feeds back the operation adjustment suggestions in the following table. Table 1 is the feedback relationship table of the movement of the root position of the soft melting zone and the adjustment of the operation system. Table 1 is shown below.

[0129] Table 1

[0130]

[0131]

[0132] S6. After the application of S5 system, the root position of the soft melting zone is effectively directional controlled. Figure 8 : is a schematic diagram of comparison before and after the application of a blast furnace intelligent control system driven by the root position of a soft melting zone according to an embodiment of the present invention, such as Figure 8 shown.

[0133] In June 2023, the kinetic energy of the blast was too large, reaching 12574 J / s, which caused the combustion zone to be too long, resulting in "overblowing" in the center, causing the root of the soft melting zone to move down too much, and edge accumulation. According to the S5 adjustment plan, the measures taken include reducing the coke batch by 0.3t, the ore batch by 3t, moving the distribution matrix inward by 0.5°, and reducing the air volume by 50Nm 3 / h, the air outlet area is expanded by 0.0236m 3 , the wind temperature is reduced by 5℃, the slag basicity is reduced by 0.03, the center development edge airflow is appropriately suppressed, and the root position of the soft melting zone is gradually moved upward.

[0134] In August 2023, the center was over-pressed, the edge was over-developed, and the Z / W value of the blast furnace continued to decline from 17.5 to 8.59, which increased the root position of the soft melting zone by 1.0m, reduced the gas utilization rate by 2%, and increased the heat load of the cooling wall by 30MJ / h. According to the S5 adjustment plan, the measures taken include increasing the proportion of central coke by 5%, expanding the coke batch by 0.5t, expanding the ore batch by 3t, and increasing the air volume by 100Nm 3 / h, the slag basicity is increased by 0.05, the center and edge airflows are properly developed, and the shape of the soft melting zone develops from "V" → "W" → "Λ", which is conducive to loosening the center material column, and the root position of the soft melting zone gradually moves downward.

[0135] In November 2023, the kinetic energy of the blast was too small, which caused the center to accumulate and the edge airflow to develop excessively, causing the soft melting zone to develop in a "V" shape, and the root of the soft melting zone moved upward, disrupting the smooth operation of the blast furnace. According to the S5 adjustment plan, the measures taken include expanding the coke batch by 0.3t, moving the distribution matrix outward by 1°, and increasing the air volume by 100Nm 3 / h, the wind temperature is increased by 10℃, and the central airflow is guided to achieve the effect of gradually moving the soft melting zone downward and recovering.

[0136] The soft melting zone root monitoring method provided in this embodiment inputs the real-time production data of the blast furnace into the constructed soft melting zone root monitoring model to generate real-time blast furnace soft melting zone root working conditions, which can effectively reflect the changes in the soft melting zone root position during the blast furnace production process, and propose corresponding operation improvement suggestions based on the changes in the soft melting zone root position to prevent furnace condition fluctuations caused by changes in the soft melting zone root position. It has the advantages of convenient operation, comprehensive and intuitive, and significant effects, and provides a guiding basis for actual production. The actual production case database is used to provide real-time operation adjustment suggestions for changes in the soft melting zone root position. Through the continuous updating and application of the case database, a key channel is opened for the blast furnace soft melting zone control, which is convenient for real-time adjustment of the blast furnace condition.

[0137] In this embodiment, a soft melting zone root monitoring model construction 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 device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0138] This embodiment provides a device for constructing a monitoring model for the root of a soft melting zone. Fig. 9 As shown, including:

[0139] The first data acquisition module 901 is used to collect sample blast furnace cooling wall temperature data and sample static pressure difference data. Figure 1Step S101 of the illustrated embodiment will not be described in detail here.

[0140] The visualization grid construction module 902 is used to expand the blast furnace cooling wall surface in the circumferential direction and project it onto a two-dimensional plane, fill the sample blast furnace cooling wall temperature data into the corresponding position of the two-dimensional plane, and obtain a visualization grid, wherein the ordinate of the visualization grid is used to represent the elevation of the blast furnace, and the abscissa of the visualization grid is used to represent the circumferential angle of the blast furnace. For details, please refer to Figure 1 Step S102 of the illustrated embodiment will not be described in detail here.

[0141] The numerical filling interpolation module 903 is used to fill and interpolate the visual grid using the interpolation algorithm to obtain a virtual grid, which covers all areas of the blast furnace cooling wall. Figure 1 Step S103 of the illustrated embodiment will not be described in detail here.

[0142] The contour search module 904 is used to link the grids with the same blast furnace cooling wall temperature in the virtual grid using the contour search algorithm to draw a two-dimensional plane model of the root position of the blast furnace soft melting zone. Figure 1 Step S104 of the illustrated embodiment will not be described in detail here.

[0143] The model building module 905 is used to optimize the two-dimensional plane model using the sample static pressure difference data to build a soft melting zone root monitoring model, wherein the soft melting zone root monitoring model is used to determine the soft melting zone root position. Figure 1 Step S105 of the illustrated embodiment will not be described in detail here.

[0144] In some optional implementations, the visual grid construction module 902 includes:

[0145] The data filling unit is used to fill the sample blast furnace cooling wall temperature data into the position corresponding to the sensor position in the two-dimensional plane based on the sensor position of the data source of the sample blast furnace cooling wall temperature data.

[0146] The data arrangement unit is used to determine the size of the visualization grid according to the data volume and accuracy requirements of the sample blast furnace cooling wall temperature data, and to arrange the visualization grid in combination with the sample blast furnace cooling wall temperature data.

[0147] In some optional implementations, the contour line search module 904 includes:

[0148] The mapping table establishing unit is used to establish a mapping table between different blast furnace cooling wall temperature ranges and different colors.

[0149] The division interval determination unit is used to use the mapping table and the sample blast furnace cooling wall temperature data to screen the temperature normal distribution diagram corresponding to the sample blast furnace cooling wall temperature data of each section of the blast furnace cooling wall with output and fuel ratio within a preset range, and determine the division interval of each temperature section.

[0150] The two-dimensional plane model drawing unit is used to link the grids with the same temperature of the blast furnace cooling wall in the virtual grid based on the divided interval, and draw a two-dimensional plane model of the root position of the blast furnace soft melting zone.

[0151] 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.

[0152] The soft melt belt root monitoring model building 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.

[0153] In this embodiment, a soft melting belt root monitoring device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, 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 of 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 conceivable.

[0154] This embodiment provides a soft melting belt root monitoring device, such as Fig.10 As shown, including:

[0155] The numerical filling interpolation module 1001 is used to fill and interpolate the visual grid using the interpolation algorithm to obtain a virtual grid, which covers all areas of the blast furnace cooling wall. Figure 4 Step S401 of the illustrated embodiment will not be described in detail here.

[0156] The contour search module 1002 is used to link the grids with the same blast furnace cooling wall temperature in the virtual grid using the contour search algorithm to draw a two-dimensional plane model of the root position of the blast furnace soft melting zone. Figure 4 Step S402 of the illustrated embodiment will not be described in detail here.

[0157] The model building module 1003 is used to optimize the two-dimensional plane model using the sample static pressure difference data to build a soft melting zone root monitoring model, wherein the soft melting zone root monitoring model is used to determine the soft melting zone root position. Figure 4Step S403 of the illustrated embodiment will not be described in detail here.

[0158] In some optional embodiments, the working conditions of the root of the soft melting zone include upward movement, stability and downward movement of the root of the soft melting zone, and the root monitoring device of the soft melting zone also includes:

[0159] The case acquisition unit is used to obtain historical operation cases corresponding to the working conditions at the root of each soft melting zone.

[0160] The model training unit is used to train the feedback relationship model using the root working conditions of each soft melting zone and historical operation cases to obtain the trained operation system adjustment feedback relationship model.

[0161] 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.

[0162] The soft melt belt root monitoring 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.

[0163] The embodiment of the present invention also provides a computer device having the above Fig. 9 The soft melting zone root monitoring model construction device shown in Fig.10 The soft melting zone root monitoring device shown.

[0164] See also Fig.11 , Fig.11 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Fig.11 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). Fig.11 A processor 10 is taken as an example.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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. Fig.11 The example of connecting through bus is taken in the following.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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 constructing a soft melting zone root monitoring model, characterized in that: The method comprises: Collect sample blast furnace cooling wall temperature data and sample static pressure difference data; The cooling wall surface of the blast furnace is unfolded in a circumferential direction and projected onto a two-dimensional plane, and the sample blast furnace cooling wall temperature data is filled into the corresponding position of the two-dimensional plane to obtain a visualization grid, wherein the ordinate of the visualization grid is used to represent the elevation of the blast furnace, and the abscissa of the visualization grid is used to represent the circumferential angle of the blast furnace; Using an interpolation algorithm, the visual grid is filled and interpolated to obtain a virtual grid, where the virtual grid covers all areas of the blast furnace cooling wall surface; Using an isoline search algorithm, grids with the same temperature of the blast furnace cooling wall in the virtual grid are linked to draw a two-dimensional plane model of the root position of the blast furnace soft melting zone; The two-dimensional plane model is optimized using the sample static pressure difference data to construct a soft melting zone root monitoring model, wherein the soft melting zone root monitoring model is used to determine the soft melting zone root position.

2. The method according to claim 1, characterized in that: The step of filling the sample blast furnace cooling wall temperature data into the corresponding position of the two-dimensional plane to obtain a visualization grid includes: Based on the sensor position of the data source of the sample blast furnace cooling stave temperature data, fill the sample blast furnace cooling stave temperature data into the position corresponding to the sensor position in the two-dimensional plane; The size of the visualization grid is determined according to the data volume and accuracy requirements of the sample blast furnace cooling stave temperature data, and the visualization grid is obtained by arranging the sample blast furnace cooling stave temperature data.

3. The method according to claim 1, characterized in that The method uses an isoline search algorithm to link grids with the same temperature of the blast furnace cooling wall in the virtual grid to draw a two-dimensional plane model of the root position of the blast furnace soft melting zone, including: Establish a mapping table between different blast furnace cooling wall temperature ranges and different colors; Using the mapping table and the sample blast furnace cooling stave temperature data, a temperature normal distribution diagram corresponding to the sample blast furnace cooling stave temperature data of each section of the blast furnace cooling stave with a production output and a fuel ratio within a preset range is screened to determine a division interval for each section of the temperature; Based on the divided intervals, grids with the same temperature of the blast furnace cooling wall in the virtual grid are linked to draw a two-dimensional plane model of the root position of the blast furnace soft melting zone.

4. A method for monitoring the root of a soft melting zone, characterized in that: The method comprises: Collect real-time blast furnace cooling wall temperature data and real-time static pressure difference data; Using the soft melting zone root monitoring model, based on the real-time blast furnace cooling wall temperature data and the real-time static pressure difference data, the soft melting zone root working conditions corresponding to the real-time blast furnace cooling wall temperature data and the real-time static pressure difference data are generated, wherein the soft melting zone root monitoring model is constructed using the soft melting zone root monitoring model construction method according to any one of claims 1 to 3; Based on the pre-trained operating system adjustment feedback relationship model and combined with the soft melting zone root working conditions, adjustment suggestions for the blast furnace are generated.

5. The method according to claim 4, characterized in that The working conditions of the root of the soft melting zone include upward movement, stability and downward movement of the root of the soft melting zone. The operation system adjustment feedback relationship model is trained in the following way: Obtaining historical operation cases corresponding to the working conditions at the root of each soft melting zone; The feedback relationship model is trained using the root conditions of the soft melting zone and the historical operation cases to obtain a trained operation system adjustment feedback relationship model.

6. A device for constructing a soft melting zone root monitoring model, characterized in that: The device comprises: The first data acquisition module is used to collect sample blast furnace cooling wall temperature data and sample static pressure difference data; A visualization grid construction module is used to expand the cooling wall surface of the blast furnace in a circumferential direction and project it onto a two-dimensional plane, fill the sample blast furnace cooling wall temperature data into the corresponding position of the two-dimensional plane, and obtain a visualization grid, wherein the ordinate of the visualization grid is used to represent the elevation of the blast furnace, and the abscissa of the visualization grid is used to represent the circumferential angle of the blast furnace; A numerical filling and interpolation module is used to fill and interpolate the visual grid using an interpolation algorithm to obtain a virtual grid, wherein the virtual grid covers all areas of the blast furnace cooling wall surface; The isoline search module is used to link the grids with the same temperature of the blast furnace cooling wall in the virtual grid by using the isoline search algorithm to draw a two-dimensional plane model of the root position of the blast furnace soft melting zone; The model building module is used to optimize the two-dimensional plane model using the sample static pressure difference data to build a soft melting zone root monitoring model, wherein the soft melting zone root monitoring model is used to determine the soft melting zone root position.

7. A soft melting belt root monitoring device, characterized in that: The device comprises: The second data acquisition module is used to collect real-time blast furnace cooling wall temperature data and real-time static pressure difference data; A soft melting zone root condition generation module, which is used to generate the soft melting zone root condition corresponding to the real-time blast furnace cooling wall temperature data and the real-time static pressure difference data using the soft melting zone root monitoring model based on the real-time blast furnace cooling wall temperature data and the real-time static pressure difference data, wherein the soft melting zone root monitoring model is constructed using the soft melting zone root monitoring model construction device according to claim 6; The adjustment suggestion generation module is used to generate adjustment suggestions for the blast furnace based on the pre-trained operation system adjustment feedback relationship model and the soft melting zone root working conditions.

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 constructing a soft melting zone root monitoring model according to any one of claims 1 to 3 or the method for monitoring the soft melting zone root according to any one of claims 4 to 5 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 constructing a soft melting zone root monitoring model according to any one of claims 1 to 3 or the method for monitoring the soft melting zone root according to any one of claims 4 to 5.

10. A computer program product, characterized in that The method comprises computer instructions, wherein the computer instructions are used to enable a computer to execute the method for constructing a soft melting zone root monitoring model according to any one of claims 1 to 3 or the method for monitoring the soft melting zone root according to any one of claims 4 to 5.

Images