Method and system for scoring blast furnace conditions

Abstract

The application discloses a method and system for scoring a blast furnace condition, the method comprising: using a normalized interval analysis method to analyze data of key parameters and important technical parameters of the blast furnace to obtain a normalized linear equation; determining a scoring weight of the corresponding key parameters on the blast furnace condition according to an absolute value of a dependent variable coefficient in the normalized linear equation; and further quantitatively evaluating the blast furnace condition, which comprises: dividing a value grade of each key parameter according to a degree of a total score of the key parameter deviating from a reasonable range of the key parameter; setting a grade score; and summing up scores of all key parameters in a time period to obtain a score of the blast furnace condition in the time period. Determining the reasonable range of a key parameter specifically comprises: using an interval analysis method to analyze data of the key parameter and related parameters of the key parameter to obtain a linear regression relationship; and combining one or more known target indicators of the related parameters to obtain the reasonable range of the key parameter.

Description

Technical Field

[0001] This invention relates to the field of blast furnace ironmaking technology, and in particular to a method and system for scoring blast furnace conditions. Background Technology

[0002] Whether the blast furnace is operating smoothly is crucial for stable production and reduced energy consumption. Therefore, it is necessary to assess and predict the blast furnace condition and control and adjust the blast furnace based on the prediction results.

[0003] Existing systems for evaluating or predicting blast furnace performance, such as blast furnace scoring systems or blast furnace data analysis systems, suffer from varying degrees of problems, including a lack of scientific basis and timeliness in their evaluation standards. For instance, the determination of optimal control ranges and standards for blast furnace raw materials and operating indicators relies solely on experience in setting the weights of various parameters, lacking data support and scientific evidence. Such evaluation or prediction systems can lead to invalid or misjudged blast furnace big data analysis or furnace condition scoring results, and even cause directional errors in blast furnace response measures.

[0004] Therefore, how to scientifically and accurately evaluate the condition of a blast furnace has always been a difficult problem to overcome. Summary of the Invention

[0005] The purpose of this invention is to provide a method and system for scoring blast furnace conditions.

[0006] To achieve one of the above-mentioned objectives, one embodiment of the present invention provides a method for scoring blast furnace conditions, the method comprising:

[0007] The normalized interval analysis method was used to analyze the data of key parameters and important technical and economic parameters of the blast furnace, and normalized linear equations with the key parameters as independent variables and the important technical and economic parameters as dependent variables were obtained respectively.

[0008] Based on the magnitude of the absolute value of the dependent variable coefficient in the normalized linear equation, the scoring weight of the corresponding key parameters on the blast furnace condition is determined.

[0009] The blast furnace condition is quantitatively evaluated based on the scoring weights of all key parameters and the value levels of each key parameter. This includes: calculating the total score for each key parameter based on its scoring weights; determining the reasonable range for each key parameter; classifying each key parameter into value levels based on the degree to which its value deviates from the reasonable range; setting a grade score for each value level of each key parameter based on its total score and the value level classification; acquiring data for all key parameters over a given time period; scoring the data for each key parameter; and summing the scores for all key parameters to obtain the score for the blast furnace condition during that time period.

[0010] Specifically, determining the reasonable range of a key parameter includes: obtaining data on a key parameter and related parameters that are correlated with the key parameter; using interval analysis to analyze the data on the key parameter and related parameters to obtain the linear regression relationship between the key parameter and each related parameter; and based on the linear regression relationship, combined with one or more known target indicators of the related parameters, obtaining the reasonable range of the parameter.

[0011] As a further improvement to one embodiment of the present invention, the normalized interval analysis method includes:

[0012] Obtain sample data of multiple parameters at different time points, and divide the fluctuation range of the sample data of the first parameter into intervals;

[0013] Based on the time correspondence between other parameters and the first parameter, the sample data of all other parameters are divided into the same intervals.

[0014] Calculate the average value of each parameter in each interval, and use a normalization formula to obtain the normalized average value t of each parameter's average value T, wherein the normalization formula is: The min and max Find the minimum and maximum values ​​for each parameter across all intervals;

[0015] Using the normalized average values ​​of the first parameter and other parameters in each interval as the coordinate values ​​of the two coordinate axes, the normalized linear equations with other parameters as independent variables and the first parameter as the dependent variable are calculated respectively.

[0016] As a further improvement to one embodiment of the present invention, the interval analysis method includes:

[0017] Obtain sample data of multiple parameters at different time points, and divide the fluctuation range of the sample data of the first parameter into intervals;

[0018] Based on the time correspondence between other parameters and the first parameter, the sample data of all other parameters are divided into the same intervals, and the average value of each parameter in each interval is calculated.

[0019] Using the average values ​​of the first parameter and other parameters in each interval as the coordinate values ​​of the two axes, the linear regression relationship between the first parameter and other parameters is calculated.

[0020] As a further improvement to one embodiment of the present invention, the key technical parameters include blast furnace output and fuel ratio, and the determination of the scoring weight of the corresponding key parameters on the blast furnace condition based on the absolute value of the dependent variable coefficient in the normalized linear equation includes:

[0021] The weight of the influence of output on blast furnace condition is determined as c, and the weight of the influence of fuel ratio on blast furnace condition is determined as d.

[0022] Calculate the weight e of the impact of each key parameter on output and the weight f of the impact of each key parameter on fuel ratio;

[0023] The weight of each key parameter in the blast furnace condition score is calculated as c*e + d*f.

[0024] As a further improvement to one embodiment of the present invention, the method further includes:

[0025] Different scoring ranges are set for the blast furnace condition, and different response plans are developed for different scoring ranges.

[0026] As a further improvement to one embodiment of the present invention, the method further includes:

[0027] When a key parameter loses points, the impact of the key parameter on the important technical and economic parameters is calculated through the linear regression relationship between the key parameter and the important technical and economic parameters.

[0028] As a further improvement to one embodiment of the present invention, the key parameters include key operational process parameters, and the method further includes:

[0029] Calculate the score for each critical operation process parameter in each shift, obtain the highest score for each critical operation process parameter across all shifts, and select the operation corresponding to the highest score as the standard operation.

[0030] As a further improvement to one embodiment of the present invention, the method further includes:

[0031] Calculate the score for each shift in the blast furnace within a time period to obtain the overall score for each shift during that time period, and manage the workers corresponding to each shift based on the overall score.

[0032] As a further improvement to one embodiment of the present invention, the key parameters include some input parameters and some process parameters, and the important technical and economic parameters include some output parameters. The specific data for obtaining the key parameters and important technical and economic parameters of the blast furnace includes:

[0033] Establish the time correspondence between the input parameters and the process and output parameters;

[0034] Based on the time correspondence, a blast furnace database will be established using the collected data of relevant blast furnace parameters;

[0035] Data on the key parameters and important technical and economic parameters are obtained from the blast furnace database.

[0036] As a further improvement to one embodiment of the present invention, the input parameters include coke M40, coke M10, sinter drum strength, ferrous content of sinter, and overall furnace feed grade.

[0037] The process parameters include blast kinetic energy, air volume, top pressure, air temperature, theoretical combustion temperature, furnace bottom center temperature, cooling wall temperature, and cooling wall temperature uniformity.

[0038] As a further improvement to one embodiment of the present invention, the establishment of the time correspondence between the input parameters, process parameters, and output parameters specifically includes:

[0039] By dynamically monitoring the raw material testing data, arrival time, arrival quantity, finished product warehouse location changes, belt conveyor speed and transfer volume from the finished product warehouse to the blast furnace raw material warehouse, blast furnace raw material warehouse location, transfer speed and transfer volume after blast furnace raw material charging, and the smelting cycle of blast furnace raw materials in the blast furnace, the time correspondence between the blast furnace input parameters, process parameters, and output parameters can be calculated or obtained through tracer experiments.

[0040] As a further improvement to one embodiment of the present invention, the step of establishing a blast furnace database from the collected blast furnace-related parameter data specifically includes:

[0041] Data cleaning, data mining, and data fusion are performed on the data in the blast furnace database. The fused data in the blast furnace database is then used for data analysis, monitoring, and early warning. Specifically, data cleaning refers to removing outliers from the collected data; data mining refers to calculating indirect parameters based on the collected data using existing formulas; and data fusion refers to unifying the data frequency or data period of all parameters to obtain periodic data.

[0042] To achieve one of the above-mentioned objectives, one embodiment of the present invention provides a blast furnace condition scoring system, the system comprising:

[0043] The data processing module is used to analyze the data of key parameters and important technical and economic parameters of the blast furnace using normalized interval analysis, and to obtain normalized linear equations with the key parameter as the independent variable and the important technical and economic parameters as the dependent variable. The data processing module is also used to determine a reasonable range for a key parameter, which includes: acquiring data of a key parameter and related parameters; using interval analysis to analyze the data of the key parameter and related parameters to obtain the linear regression relationship between the key parameter and each related parameter; and based on the linear regression relationship, combined with one or more known target indicators of the related parameters, to obtain the reasonable range of the parameter.

[0044] The scoring preprocessing module is used to determine the scoring weight of the corresponding key parameters on the blast furnace condition based on the magnitude of the absolute value of the coefficient of the dependent variable in the normalized linear equation.

[0045] The scoring module is used to quantitatively evaluate the blast furnace condition based on the scoring weights of all key parameters and the value levels of each key parameter. The scoring module is also used to: calculate the total score for each key parameter based on its scoring weights; determine the reasonable range for each key parameter and classify each key parameter into value levels based on the degree to which its value deviates from the reasonable range; set a level score corresponding to each value level of each key parameter based on its total score and value level classification; acquire data for all key parameters over a given time period; score the data for each key parameter; and the sum of the scores for all key parameters is the score of the blast furnace condition during that time period.

[0046] As a further improvement to one embodiment of the present invention, the data processing module is further configured to:

[0047] Obtain sample data of multiple parameters at different time points, and divide the fluctuation range of the sample data of the first parameter into intervals;

[0048] Based on the time correspondence between other parameters and the first parameter, the sample data of all other parameters are divided into the same intervals.

[0049] Calculate the average value of each parameter in each interval, and use a normalization formula to obtain the normalized average value t of each parameter's average value T, wherein the normalization formula is: The min and max Find the minimum and maximum values ​​for each parameter across all intervals;

[0050] Using the normalized average values ​​of the first parameter and other parameters in each interval as the coordinate values ​​of the two coordinate axes, the normalized linear equations with other parameters as independent variables and the first parameter as the dependent variable are calculated respectively.

[0051] As a further improvement to one embodiment of the present invention, the data processing module is further configured to:

[0052] Obtain sample data of multiple parameters at different time points, and divide the fluctuation range of the sample data of the first parameter into intervals;

[0053] Based on the time correspondence between other parameters and the first parameter, the sample data of all other parameters are divided into the same intervals, and the average value of each parameter in each interval is calculated.

[0054] Using the average values ​​of the first parameter and other parameters in each interval as the coordinate values ​​of the two axes, the linear regression relationship between the first parameter and other parameters is calculated.

[0055] As a further improvement to one embodiment of the present invention, the key technical parameters include blast furnace output and fuel ratio, and the scoring preprocessing module is further used for:

[0056] The weight of the influence of output on blast furnace condition is determined as c, and the weight of the influence of fuel ratio on blast furnace condition is determined as d.

[0057] Calculate the weight e of the impact of each key parameter on output and the weight f of the impact of each key parameter on fuel ratio;

[0058] The weight of each key parameter in the blast furnace condition score is calculated as c*e + d*f.

[0059] As a further improvement of one embodiment of the present invention, the system further includes a management module, the management module being used for:

[0060] Different scoring ranges are set for the blast furnace condition, and different response plans are developed for different scoring ranges.

[0061] As a further improvement of one embodiment of the present invention, the system further includes a management module, the management module being used for:

[0062] When a key parameter loses points, the impact of the key parameter on the important technical and economic parameters is calculated through the linear regression relationship between the key parameter and the important technical and economic parameters.

[0063] As a further improvement of one embodiment of the present invention, the key parameters include key operating process parameters, and the system further includes a management module, which is used for:

[0064] Calculate the score for each critical operation process parameter in each shift, obtain the highest score for each critical operation process parameter across all shifts, and select the operation corresponding to the highest score as the standard operation.

[0065] As a further improvement of one embodiment of the present invention, the system further includes a management module, the management module being used for:

[0066] Calculate the score for each shift in the blast furnace within a time period to obtain the overall score for each shift during that time period, and manage the workers corresponding to each shift based on the overall score.

[0067] As a further improvement to one embodiment of the present invention, the key parameters include some input parameters and some process parameters, the important technical parameters include some output parameters, and the data processing module is further used for:

[0068] Establish the time correspondence between the input parameters and the process and output parameters;

[0069] Based on the time correspondence, a blast furnace database will be established using the collected data of relevant blast furnace parameters;

[0070] Data on the key parameters and important technical and economic parameters are obtained from the blast furnace database.

[0071] As a further improvement to one embodiment of the present invention, the data processing module is further configured to:

[0072] By dynamically monitoring the raw material testing data, arrival time, arrival quantity, finished product warehouse location changes, belt conveyor speed and transfer volume from the finished product warehouse to the blast furnace raw material warehouse, blast furnace raw material warehouse location, transfer speed and transfer volume after blast furnace raw material charging, and the smelting cycle of blast furnace raw materials in the blast furnace, the time correspondence between the blast furnace input parameters, process parameters, and output parameters can be calculated or obtained through tracer experiments.

[0073] As a further improvement of one embodiment of the present invention, the system further includes a data acquisition module, which is used to acquire data on blast furnace related parameters;

[0074] The data processing module is also used for: data cleaning, data mining, and data fusion of data in the blast furnace database; and for data analysis, monitoring, and early warning using the fused data in the blast furnace database. Specifically, data cleaning refers to removing outliers from the collected data; data mining refers to calculating indirect parameters based on the collected data using existing formulas; and data fusion refers to unifying the data frequency or data period of all parameters to obtain periodic data.

[0075] Compared with existing technologies, the blast furnace condition scoring method of this invention uses normalized interval analysis to scientifically calculate the influence weights of key blast furnace parameters on important technical and economic parameters, and determine the contribution of key parameters to the evaluation of blast furnace condition, thereby scientifically and quantitatively evaluating the blast furnace condition. Furthermore, the method of this invention can also score the blast furnace at different time periods, thereby determining the blast furnace condition at different times, effectively guiding blast furnace production, promoting the stability of blast furnace condition, and improving the economic efficiency of the blast furnace. Attached Figure Description

[0076] Figure 1 This is a flowchart illustrating the blast furnace condition scoring method of the present invention.

[0077] Figure 2 This is a schematic diagram of the normalized linear equation for the ratio of blast kinetic energy to fuel.

[0078] Figure 3This is a schematic diagram of the normalized linear equation relating blower kinetic energy and output.

[0079] Figure 4 This is a schematic diagram of the normalized linear equation that integrates the grade of fuel entering the furnace and the fuel ratio.

[0080] Figure 5 This is a schematic diagram of the normalized linear equation that integrates the grade of the furnace feed and the output.

[0081] Figure 6 This is a schematic diagram illustrating the linear regression relationship between wind temperature and yield.

[0082] Figure 7 This is a schematic diagram of the linear regression relationship between air temperature and fuel ratio.

[0083] Figure 8 This is a flowchart illustrating the interval analysis method of the present invention.

[0084] Figure 9 This is a flowchart illustrating the normalized interval analysis method of the present invention. Detailed Implementation

[0085] The present invention will now be described in detail with reference to the specific embodiments shown in the accompanying drawings. However, these embodiments do not limit the present invention, and any structural, methodological, or functional modifications made by those skilled in the art based on these embodiments are included within the scope of protection of the present invention.

[0086] Evaluation of blast furnace conditions is generally based on relevant blast furnace parameters. However, there are numerous relevant parameters for a blast furnace, including operational parameters during blast furnace operation, monitoring parameters of the blast furnace cooling system, raw material parameters, blast furnace charging matrix parameters, blast furnace feeding parameters, top gas temperature parameters, blast furnace gas composition parameters, molten iron weight, mass, and temperature parameters, and slag weight and mass parameters. Among these, the operational parameters during blast furnace operation include theoretical combustion temperature in the tuyere zone, blast energy, belly gas index, permeability resistance coefficient, tuyere zone wind velocity, tuyere zone air volume, tuyere zone blast temperature, tuyere zone blast pressure, humidification rate, oxygen enrichment rate, and pulverized coal injection rate. Monitoring parameters of the blast furnace cooling system include cooling wall temperature, cooling system flow rate, cooling water pressure, and cooling water temperature. Raw material parameters include the mass, bin location, and batching structure of the coke, sinter, lump ore, and pellets used in the blast furnace. The parameters for the furnace top gas temperature include furnace top gas temperature, furnace top gas pressure, cross-shaped temperature measurement, and furnace top Z / W ratio.

[0087] Historical data shows that among the numerous blast furnace-related parameters, linear relationships are rare; they are predominantly nonlinear, even chaotic. Various statistical methods have failed to simplify these relationships. Therefore, scientifically determining the contribution (weight) of each parameter to blast furnace condition evaluation is a significant challenge. After extensive research, the inventors developed an interval analysis method that can linearize these nonlinear and even chaotic data points related to blast furnace parameters, thereby simplifying the relationships between them.

[0088] like Figure 8 As shown, the interval analysis method includes the following steps:

[0089] Step S110: Obtain sample data of multiple parameters at different time points, and divide the fluctuation range of the sample data of the first parameter into intervals.

[0090] To facilitate the division, it is preferable to divide the fluctuation range of the sample data of the first parameter into intervals by means of average division.

[0091] The number of intervals can be large or small, but since the average value of each interval will be linearly regressed later, it is preferable to divide the intervals into 6-8 intervals. If the sample data is large, it can be divided into 8 intervals, and if it is small, it can be divided into 6 intervals, and so on.

[0092] Furthermore, after dividing the data into intervals, some intervals may have very small sample sizes, which are not helpful for subsequent processing. Therefore, in a preferred embodiment, after dividing the fluctuation range of the sample data of the first parameter into multiple intervals, the total sample size of the first parameter and the sample size in each interval are calculated, and the sample size percentage of each interval is calculated. Intervals with a sample size percentage less than a predetermined threshold are deleted to obtain the final interval division. The predetermined threshold can be 5%, that is, when the sample size of a certain interval is less than 5% of the total sample size, this interval is deleted or removed, so that the data in this interval is not included in subsequent processing.

[0093] Step S120: Based on the time correspondence between other parameters and the first parameter, divide the sample data of all other parameters into the same intervals, and calculate the average value of each parameter in each interval.

[0094] For example, the sample data of the first parameter is divided into M intervals. The first interval includes four sample data points of the first parameter at time points A, B, C, and D. Based on the time correspondence between the other parameters and the first parameter, the sample data of the other parameters at the corresponding time points A, B, C, and D are also divided into the first interval, and so on. In this way, the sample data of the other parameters are also divided into M intervals that are the same as those of the first parameter and have a corresponding relationship.

[0095] After the intervals are divided, the average value of each parameter in each interval is calculated, including the average value of the first parameter in M ​​intervals and the average value of each other parameter in M ​​intervals.

[0096] Step S130: Using the average values ​​of the first parameter and other parameters in each interval as the coordinate values ​​of the two coordinate axes, respectively, calculate the linear regression relationship between the first parameter and other parameters.

[0097] The two coordinate axes can be the horizontal axis and the vertical axis. The average value of the first parameter in each interval is used as the coordinate value of the horizontal axis / vertical axis, and the average value of another parameter in each interval is used as the coordinate value of the vertical axis / horizontal axis. The linear regression relationship between the first parameter and this other parameter is calculated.

[0098] By processing all the other parameters in the same way, we obtain multiple linear regression relationships between the first parameter and all the other parameters.

[0099] Interval analysis can yield a linear regression relationship between a parameter and other parameters, but it cannot determine the influence weights of other parameters on this parameter. Therefore, in order to scientifically calculate the influence weights of other parameters on a given parameter, the inventors, after research, combined the above-mentioned interval analysis method with the normalization method to obtain the normalized interval analysis method, which calculates the influence weights of other parameters on a given parameter.

[0100] like Figure 9 As shown, the normalized interval analysis method includes:

[0101] Step S210: Obtain sample data of multiple parameters at different time points, and divide the fluctuation range of the sample data of the first parameter into intervals.

[0102] Same as step S110.

[0103] Step S220: Based on the time correspondence between other parameters and the first parameter, divide the sample data of all other parameters into the same intervals.

[0104] Same as step S120.

[0105] Step S230: Calculate the average value of each parameter in each interval, and normalize the average values ​​of each parameter to obtain the normalized average values ​​of each parameter.

[0106] The following normalization formula is preferred for calculating the normalized average t of each parameter's average value T:

[0107]

[0108] in min and max Find the minimum and maximum values ​​for each parameter across all intervals.

[0109] Step S240: Using the normalized average values ​​of the first parameter and other parameters in each interval as the coordinate values ​​of the two coordinate axes, calculate the normalized linear equations with other parameters as independent variables and the first parameter as the dependent variable.

[0110] For example, by using the normalized average of the first parameter as the coordinate value of the vertical axis and the normalized average of another parameter as the coordinate value of the horizontal axis, a normalized linear equation can be obtained with the other parameter as the independent variable x and the first parameter as the dependent variable y:

[0111] y = ax + b

[0112] The absolute value of the coefficient a of the independent variable x represents the influence weight of the other parameters on the first parameter.

[0113] It should be noted that when using interval analysis or normalized interval analysis to analyze the linear regression relationship or normalized linear equation between parameters, the data of all parameters involved in the analysis have a time correspondence. However, for blast furnace-related parameters, we often cannot accurately know the parameter data of the raw materials that react in the blast furnace. That is, there is no time correspondence between the raw material data and the collected blast furnace condition data. Therefore, it is necessary to organize the blast furnace-related parameters, establish a time correspondence between the organized parameters, and then build a blast furnace database based on the time correspondence.

[0114] Specifically, the relevant parameters of the blast furnace are organized and divided into input parameters, process parameters, and output parameters. Among them:

[0115] The input parameters refer to raw material parameters, including the quality parameters, bin location parameters, and batching structure parameters of the coke, sinter, lump ore, and pellets used in the blast furnace, as shown in Table 1 below.

[0116] The process parameters include operating parameters, furnace condition characterization parameters, and furnace body management parameters, as shown in Table 2 below.

[0117] The output parameters refer to the technical and economic indicators of the blast furnace, including output, fuel ratio, etc., as shown in Table 3 below.

[0118]

[0119]

[0120] Table 1

[0121]

[0122] Table 2

[0123]

[0124] Table 3

[0125] As can be seen from Tables 1-3, the process parameters and output parameters are collected at the same time, or can be calculated based on the data collected at the same time. Only the input parameters are not collected at the same time, so it is necessary to establish a time correspondence between the input parameters and the process and output parameters.

[0126] By dynamically monitoring data such as raw material testing and analysis, arrival time, arrival quantity, changes in finished product storage location, conveyor belt speed and transfer volume from finished product storage to blast furnace raw material storage, blast furnace raw material storage location, transfer speed and transfer volume after blast furnace raw material charging, and smelting cycle of blast furnace raw materials in the blast furnace, the time correspondence between blast furnace input parameters, process parameters, and output parameters can be calculated or obtained through tracer experiments.

[0127] Specifically, the input parameters (including the quality parameters of coke, sinter, pellets and ore blocks) and the process parameters or output parameters have the following time difference: the time difference = in-furnace reaction time - blast furnace raw material sampling time = belt conveyor transfer time from the finished product warehouse to the blast furnace raw material warehouse after blast furnace raw material sampling + storage time of blast furnace raw material in the blast furnace raw material warehouse + transfer time after blast furnace raw material charging + smelting cycle of blast furnace raw material in the blast furnace.

[0128] In one specific implementation, a time-based correspondence is established between the input parameters (coke quality parameters) and process parameters. The sampling time T for collecting coke samples is... 取 Δt, the conveyor belt transfer time from the sampling point to the blast furnace coke bin 焦 Collect coke from the blast furnace coke bin at T 取 +Δt 焦 Storage capacity H, blast furnace coke charging speed V, and blast furnace charging and transfer time Δt at any given time. 炉 The smelting cycle Δt of the furnace charge in the blast furnace is collected. 冶炼 The acquisition time T of the process parameters 炉This allows us to determine the time-related relationship between coke quality parameters and process parameters, as follows:

[0129] T 炉 =T 取 +Δt 焦 +H / V+Δt 炉 +T 冶炼 .

[0130] After establishing the time correspondence between input parameters, process parameters, and output parameters, a blast furnace database is built based on the collected blast furnace-related parameter data according to the time correspondence. Then, interval analysis is used to analyze the data of each parameter in the blast furnace database to obtain the linear regression relationship between the blast furnace-related parameters.

[0131] It should be noted that the collected blast furnace-related parameter data can be from a specific period, such as all data collected in the last two years. After establishing a blast furnace database based on the aforementioned time correspondence, the data in the blast furnace database needs to be cleaned, mined, and merged before being used for data analysis, monitoring, and early warning. For example, interval analysis or normalized interval analysis can be used. Throughout this text, the data used in the blast furnace database refers to the merged data from the blast furnace database.

[0132] Data cleaning refers to removing abnormal or defective data and supplementing missing data. For example, data cleaning for thermocouple temperatures on cooling walls involves removing defective data. The temperature fluctuation range of each cooling wall layer in the blast furnace varies depending on its height within the furnace body and its material. Data outside this reasonable fluctuation range is removed. For instance, the upper 13 sections of cast iron cooling walls in the furnace body generally have a temperature between 70-300℃ due to the protection of cooling water. First, thermocouple data outside this range are removed. Finally, for data within the 70-300℃ range, if a point shows no fluctuation or change throughout the day, the thermocouple at that monitoring point is considered damaged and its temperature data is removed. Defective thermocouple data in the blast furnace is left blank after removal to prevent data distortion and misjudgment of furnace conditions. For inspection and testing data, abnormal data points are removed based on whether the data falls within the normal detection range. Missing data is determined based on the frequency of inspections and tests, and is automatically filled by the average of the last three inspection and testing data.

[0133] Data mining refers to the statistical analysis of various parameters based on collected data, including averages, maximums, minimums, data distribution, and standard deviations. Data mining also includes mining indirect parameters, which are parameters that cannot be directly obtained from collected data but must be calculated using existing formulas. Examples of indirect parameters include blast furnace blast kinetic energy, hearth activity index, radial distribution of the ore-coke ratio in the charging process, heat balance, theoretical combustion temperature, and the highest temperature achievable by the combustion of hot air and fuel in front of the tuyeres.

[0134] Data fusion refers to unifying the data frequency or data period of all parameters to obtain periodic data. Since the data acquisition frequencies of blast furnace-related parameters vary—for example, some parameters are collected once per second, some once per minute, and some once per hour or even daily—data fusion is necessary to unify the data frequency or data period of all parameters to obtain periodic data. For example, unifying the data frequency of all parameters to one data point per hour results in a one-hour data period. Because the amount of data from the blast furnace is relatively large and the overall period is long, a preferred data frequency is one data point per day, i.e., a daily data period. The method for obtaining periodic data for a parameter is to obtain the average or latest value of all data for that parameter within the data period, which is then used as one periodic data point for that parameter. Subsequent use of data for a specific parameter in the blast furnace database refers to the periodic data for that parameter.

[0135] The technical and economic parameters of a blast furnace are indicators that reflect its production technology and economic level. In particular, the blast furnace's output and fuel consumption (fuel consumption can be replaced by fuel ratio) are the ultimate indicators for evaluating the technical and economic level of a blast furnace.

[0136] Therefore, as Figure 1 As shown, this invention provides a scoring method for blast furnace conditions. The scoring method uses normalized interval analysis to scientifically calculate the influence weights of key blast furnace parameters on important technical and economic indicators (hereinafter referred to as important technical and economic parameters), determining the contribution of key parameters to the evaluation of blast furnace conditions, thereby scientifically quantifying the evaluation of blast furnace conditions. The method includes:

[0137] Step S310: Using the normalized interval analysis method, analyze the data of key parameters and important technical and economic parameters of the blast furnace, and obtain normalized linear equations with the key parameters as independent variables and the important technical and economic parameters as dependent variables.

[0138] Key parameters can be selected from blast furnace-related parameters as evaluation items for blast furnace conditions. The selection method can be based on experience or by analyzing the data of all blast furnace-related parameters and important technical and economic parameters using normalized interval analysis to obtain a normalized linear equation with blast furnace-related parameters as dependent variables and important technical and economic parameters as independent variables. Then, based on the magnitude of the absolute value of the coefficient of the dependent variable, the top N dependent variables are selected as key parameters.

[0139] Preferably, the key parameters include some input parameters and some process parameters. The input parameters may include coke M40, coke M10, sinter drum strength, ferrous content of sinter, and overall furnace feed grade, etc. The process parameters may include blast energy, air volume, top pressure, blast temperature, theoretical combustion temperature, furnace bottom center temperature, cooling wall temperature, and cooling wall temperature uniformity, etc. The above are just simple examples and are not limited to these.

[0140] The key technical parameters are one or more output parameters, which may include only output, only fuel ratio, or only one other technical parameter. Preferably, they include both output and fuel ratio. It should be noted that fuel ratio can also be replaced by fuel consumption, where fuel ratio over a period of time = fuel consumption over that period / output over that period.

[0141] After determining the key parameters and important technical and economic parameters, the corresponding data can be obtained from the aforementioned blast furnace database. Then, normalized interval analysis is used to analyze these data, yielding normalized linear equations with the key parameters as independent variables and the important technical and economic parameters as dependent variables. The absolute value of the coefficient of the dependent variable represents the influence weight of the key parameters on the important technical and economic parameters.

[0142] like Figures 2 to 5 As shown, Figures 2 to 5 These are the normalized linear equations for the relationship between blast furnace kinetic energy and fuel ratio, blast furnace kinetic energy and output, overall feed grade and fuel ratio, and overall feed grade and output. As can be seen from the figure, the weight of blast furnace kinetic energy on the fuel ratio is 1.66, the weight of blast furnace kinetic energy on output is 1.24, the weight of overall feed grade on the fuel ratio is 0.76, and the weight of overall feed grade on output is 0.70.

[0143] In a preferred embodiment, the step of "using normalized interval analysis to analyze the data of key parameters and important technical and economic parameters of the blast furnace, and obtaining normalized linear equations with the key parameters as independent variables and the important technical and economic parameters as dependent variables" specifically includes:

[0144] Obtain data for all the key parameters and important technical and economic parameters, and divide the fluctuation range of the important technical and economic parameters into intervals.

[0145] Based on the time correspondence between each key parameter and the important technical parameters, the data of all key parameters are divided into the same intervals.

[0146] Calculate the average value of each parameter in each interval, and normalize the average values ​​of each parameter to obtain the normalized average values ​​of each parameter.

[0147] Using the normalized average values ​​of the important technical and economic parameters and the key parameters in each interval as the coordinate values ​​of the two coordinate axes, normalized linear equations with the key parameters as independent variables and the important technical and economic parameters as dependent variables are calculated respectively.

[0148] Step S320: Determine the scoring weight of the corresponding key parameters on the blast furnace condition based on the magnitude of the absolute value of the dependent variable coefficient in the normalized linear equation.

[0149] When there is only one important technical and economic parameter, the absolute value of the dependent variable coefficient is the scoring weight of the corresponding dependent variable on the blast furnace condition. When there are multiple important technical and economic parameters, it is necessary to first determine the influence weight of multiple important technical and economic parameters on the blast furnace condition, and then combine the influence weight of the key parameter on the important technical and economic parameter (i.e., the absolute value of the corresponding dependent variable coefficient) to determine the scoring weight of the key parameter on the blast furnace condition.

[0150] Taking key technical parameters such as output and fuel ratio as examples, it is necessary to determine the weights of their influence on blast furnace conditions based on their importance to the blast furnace. For instance, when high blast furnace output is required but the fuel ratio is not critical, the weight of output is increased; when low blast furnace consumption is required but output is not critical, the weight of fuel ratio is increased; when there is no preference for either output or fuel ratio, the weights of both can be set to 0.5. After determining the weights of output and fuel ratio on blast furnace conditions (c and d respectively), the weights of the key parameters on output (e) and fuel ratio (f) are calculated. The scoring weight of the key parameters on the blast furnace is then the sum of the product of these two types of weights, i.e.:

[0151] The scoring weight is calculated as c*e + d*f.

[0152] Step S330: Quantitatively evaluate the blast furnace condition based on the scoring weights of all key parameters and the value level of each key parameter.

[0153] The steps specifically include:

[0154] Step S331: Calculate the total score for each key parameter based on the scoring weights of all key parameters.

[0155] First, set the total score for blast furnace condition, for example, 100 points. Then, add up the weights of all key parameters to get a total weight. Divide the weight of each individual key parameter by the total weight and multiply by the total blast furnace condition score to obtain the total score for each key parameter. Of course, the total score for the key parameters calculated in this way may not be an integer. For ease of calculation, the total score for the key parameters can be slightly adjusted to be the closest integer.

[0156] Step S332: Determine the reasonable range of each key parameter, and classify the value level of each key parameter according to the degree to which the value of each key parameter deviates from the reasonable range.

[0157] For example, after determining that the reasonable range of the blower kinetic energy is [15500, 16500] J / s, the values ​​in the range of [15500, 16500] J / s are divided into first class according to the degree to which the blower kinetic energy deviates from the reasonable range; the values ​​in the range of [15000, 15500) J / s and (16500, 17000] J / s are divided into second class; the values ​​in the range of [14500, 15000) J / s and (17000, 17500] J / s are divided into third class; and the values ​​in the range of [0, 14500) J / s and (17500, ∞) J / s are divided into fourth class.

[0158] Determining the reasonable range of key parameters can rely on experience or by using interval analysis to analyze the data of key parameters. This method is scientific and data-supported. Methods for determining the reasonable range of key parameters using interval analysis include:

[0159] Data on a key parameter and related parameters that are correlated with the key parameter can be obtained from the blast furnace database.

[0160] Interval analysis was used to analyze the data of the key parameters and correlation parameters to obtain the linear regression relationship between the key parameters and each correlation parameter.

[0161] Based on the linear regression relationship, and combined with one or more known target indicators of the correlation parameters, a reasonable range for the parameters is obtained.

[0162] The known target index refers to the existing target range or target attribute of the parameter. For example, if the target range for the output of a certain blast furnace is between 13,500 and 14,500 t / d, then an output between 13,500 and 14,500 t / d is a known target index for output. Alternatively, if within the target range for output, we consider higher output to be better, then higher output is a target attribute, which is also a known target index.

[0163] In one specific implementation, the linear regression relationship between the blower kinetic energy PI and the output Ke is obtained through interval analysis, satisfying the following equation:

[0164] Ke = 1.522 × PI - 10335.

[0165] When the output is between 13,500 and 14,500 t / d (the known target output), the reasonable range for the blower kinetic energy is between 15,600 and 16,300 J / s.

[0166] Step S333: Based on the total score and value level division of each key parameter, set the level score corresponding to each value level of each key parameter.

[0167] Assuming the total score for blast energy is 5 points, then we can set the score as follows: first-class is 5 points, second-class is 3 points, third-class is 1 point, and fourth-class is 0 points.

[0168] Step S334: Obtain data for all key parameters for a given time period, score each key parameter, and sum the scores for all key parameters to obtain the score for the blast furnace condition during that time period.

[0169] Obtaining data for all key parameters within a given time period involves: acquiring all data for all key parameters within that time period; and then merging all data for each key parameter into a single dataset by averaging or taking the latest value. This time period can be a day, an hour, a shift, etc. For example, if we need to calculate the daily blast furnace condition score, we would acquire all daily data for each key parameter and merge it into a single dataset (using methods such as averaging or taking the latest value). Similarly, if we need to calculate the score for each shift (8 hours per shift) within a day, we would acquire all data for each key parameter for each shift and merge it into a single dataset.

[0170] After obtaining the data for the key parameters corresponding to this period, find the value level that each key parameter falls into, and the corresponding level score, to obtain the score for each key parameter. The sum of the scores for all key parameters is the score of the blast furnace condition for this period.

[0171] The blast furnace condition scoring method of the present invention can score the blast furnace at different time periods, thereby determining the blast furnace condition at different time periods, effectively guiding blast furnace production, facilitating the stability of blast furnace condition, and improving the economic benefits of blast furnace.

[0172] In a preferred embodiment, the method further includes:

[0173] Different scoring ranges are set for the blast furnace condition, and different response plans are developed for different scoring ranges.

[0174] For example, for a blast furnace condition score of 100 points, [90,100] is set as the first scoring interval, [80,90) as the second scoring interval, [70,80) as the third scoring interval, and [0,70] as the fourth scoring interval. The response plans for the first to fourth scoring intervals can be as follows: (1) Do nothing; (2) Analyze the reasons for the changes in the scores of key parameters (mainly the reasons for the decrease), and rectify them accordingly; (3) Analyze the reasons for the loss of points in the top N key parameters of the lost items, and rectify them accordingly; (4) Analyze the reasons for the loss of points in the top N+M key parameters of the lost items, rectify them within a time limit, and formulate corresponding penalty measures. The above are just examples, but are not limited to this.

[0175] In another preferred embodiment, the method further includes:

[0176] When a key parameter loses points, the impact of the key parameter on the important technical and economic parameters is calculated through the linear regression relationship between the key parameter and the important technical and economic parameters.

[0177] The term "loss of points" refers to a key parameter not receiving full marks or receiving fewer than the total score. This implementation method is used to accurately calculate the impact of key parameters with lost points, especially those with excessively high loss of points, on important technical and economic parameters (such as production and fuel ratio).

[0178] For example, in the blast furnace performance evaluation results for a certain day's shift, it was found that the blast temperature score was too low. Using interval analysis, linear regression relationships between blast temperature and output, and between blast temperature and fuel ratio, were obtained, such as... Figure 6 and Figure 7 As shown, where:

[0179] Output = 10.59 × air temperature + 328.8;

[0180] Fuel ratio = -0.203 × air temperature + 761.9;

[0181] Substituting the wind temperature data for the day into the above linear regression relationship, it was calculated that the current wind temperature of 1187℃, compared to the target value of 1200℃, reduces daily output by 138t / d and increases fuel ratio by 3kg / t.

[0182] This method can be used to accurately calculate the impact of severe blast furnace defects on blast furnace output and fuel ratio.

[0183] In yet another preferred embodiment, the method further includes:

[0184] The key parameters include key operation process parameters. The score of each key operation process parameter is calculated for each shift. The highest score for each key operation process parameter in all shifts is obtained, and the operation corresponding to the highest score is selected as the standard operation.

[0185] In the blast furnace system, a day is divided into three shifts: day shift, afternoon shift, and night shift, each lasting 8 hours, and each shift corresponds to different workers. Because different workers operate differently, the scores for the corresponding critical operating parameters vary. Therefore, the worker operations corresponding to the shift with the highest-scoring critical operating parameters are selected as the standard operation to regulate the operation of these critical operating parameters and improve the stability of the blast furnace conditions.

[0186] Because blast furnace operation is complex and involves multiple shifts with different workers on each shift, each worker's actions affect the furnace condition. Therefore, managing the operators to reduce their negative impact on the blast furnace is a major challenge. In another preferred embodiment, the method further includes:

[0187] Calculate the score for each shift in the blast furnace within a time period (such as a month or a quarter) to obtain the overall score for each shift during that time period, and manage the workers corresponding to each shift based on the score.

[0188] Management methods include, but are not limited to, setting up reward and punishment measures for workers based on overall scores to motivate them.

[0189] The present invention also provides a blast furnace condition scoring system, the system comprising a data processing module, a scoring preprocessing module, and a scoring module, wherein:

[0190] The data processing module is used to analyze the data of key parameters and important technical and economic parameters of the blast furnace using the normalized interval analysis method, and obtain normalized linear equations with the key parameters as independent variables and the important technical and economic parameters as dependent variables.

[0191] The scoring preprocessing module is used to determine the scoring weight of the corresponding key parameters on the blast furnace condition based on the magnitude of the absolute value of the coefficient of the dependent variable in the normalized linear equation.

[0192] The scoring module is used to quantitatively evaluate the blast furnace condition based on the scoring weights of all key parameters and the value levels of each key parameter.

[0193] In a preferred embodiment, the data processing module is further configured to:

[0194] Obtain sample data of multiple parameters at different time points, and divide the fluctuation range of the sample data of the first parameter into intervals;

[0195] Based on the time correspondence between other parameters and the first parameter, the sample data of all other parameters are divided into the same intervals.

[0196] Calculate the average value of each parameter in each interval, and normalize the average values ​​of each parameter to obtain the normalized average values ​​of each parameter.

[0197] Using the normalized average values ​​of the first parameter and other parameters in each interval as the coordinate values ​​of the two coordinate axes, the normalized linear equations with other parameters as independent variables and the first parameter as the dependent variable are calculated respectively.

[0198] Furthermore, the data processing module is also used for:

[0199] Using a normalization formula, calculate the normalized average t of each parameter's average value T, where the normalization formula is:

[0200]

[0201] in min and max Find the minimum and maximum values ​​for each parameter across all intervals.

[0202] In a preferred embodiment, the scoring module is further configured to:

[0203] Calculate the total score for each key parameter based on the scoring weights of all key parameters;

[0204] Determine the reasonable range for each key parameter, and classify the value levels for each key parameter according to the degree to which the value deviates from the reasonable range;

[0205] Based on the total score and value level division of each key parameter, set the level score corresponding to each value level of each key parameter;

[0206] Data for all key parameters within a given time period is obtained, and each key parameter is scored. The sum of the scores for all key parameters is the score for the blast furnace condition during that time period.

[0207] Furthermore, the data processing module is also used to determine a reasonable range for a key parameter, which includes:

[0208] Obtain data on a key parameter and related parameters that are correlated with the key parameter;

[0209] Interval analysis was used to analyze the data of the key parameters and correlation parameters to obtain the linear regression relationship between the key parameters and each correlation parameter.

[0210] Based on the linear regression relationship, and combined with one or more known target indicators of the correlation parameters, a reasonable range for the parameters is obtained.

[0211] Furthermore, the data processing module is also used for:

[0212] Obtain sample data of multiple parameters at different time points, and divide the fluctuation range of the sample data of the first parameter into intervals;

[0213] Based on the time correspondence between other parameters and the first parameter, the sample data of all other parameters are divided into the same intervals, and the average value of each parameter in each interval is calculated.

[0214] Using the average values ​​of the first parameter and other parameters in each interval as the coordinate values ​​of the two axes, the linear regression relationship between the first parameter and other parameters is calculated.

[0215] In a preferred embodiment, the key technical parameters include blast furnace output and fuel ratio, and the scoring preprocessing module is further used for:

[0216] The weight of the influence of output on blast furnace condition is determined as c, and the weight of the influence of fuel ratio on blast furnace condition is determined as d.

[0217] Calculate the weight e of the impact of each key parameter on output and the weight f of the impact of each key parameter on fuel ratio;

[0218] The weight of each key parameter in the blast furnace condition score is calculated as c*e + d*f.

[0219] In another preferred embodiment, the system further includes a management module, which can be used to:

[0220] Different scoring ranges are set for the blast furnace condition, and different response plans are developed for different scoring ranges.

[0221] The management module can also be used for:

[0222] When a key parameter loses points, the impact of the key parameter on the important technical and economic parameters is calculated through the linear regression relationship between the key parameter and the important technical and economic parameters.

[0223] The management module can also be used for:

[0224] Calculate the score for each critical operation process parameter in each shift, obtain the highest score for each critical operation process parameter across all shifts, and select the operation corresponding to the highest score as the standard operation.

[0225] The management module can also be used for:

[0226] Calculate the score for each shift in the blast furnace within a time period to obtain the overall score for each shift during that time period, and manage the workers corresponding to each shift based on the overall score.

[0227] In a preferred embodiment, the key parameters include some input parameters and some process parameters, the important technical parameters include some output parameters, and the data processing module is further used for:

[0228] Establish the time correspondence between the input parameters and the process and output parameters;

[0229] Based on the time correspondence, a blast furnace database will be established using the collected data of relevant blast furnace parameters;

[0230] Data on the key parameters and important technical and economic parameters are obtained from the blast furnace database.

[0231] Furthermore, the data processing module is also used for:

[0232] By dynamically monitoring data such as raw material testing and analysis, arrival time, arrival quantity, changes in finished product storage location, conveyor belt speed and transfer volume from finished product storage to blast furnace raw material storage, blast furnace raw material storage location, transfer speed and transfer volume after blast furnace raw material charging, and smelting cycle of blast furnace raw materials in the blast furnace, the time correspondence between blast furnace input parameters, process parameters, and output parameters can be calculated or obtained through tracer experiments.

[0233] Furthermore, the system also includes a data acquisition module, which is used to collect data on blast furnace-related parameters;

[0234] The data processing module is also used for: data cleaning, data mining, and data fusion of data in the blast furnace database; and for data analysis, monitoring, and early warning using the fused data in the blast furnace database. Specifically, data cleaning refers to removing outliers from the collected data; data mining refers to calculating indirect parameters based on the collected data using existing formulas; and data fusion refers to unifying the data frequency or data period of all parameters to obtain periodic data.

[0235] It should be understood that although this specification describes embodiments, not every embodiment contains only one independent technical solution. This way of describing the specification is only for clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment can also be appropriately combined to form other embodiments that can be understood by those skilled in the art.

[0236] The detailed descriptions listed above are merely specific descriptions of feasible embodiments of the present invention, and are not intended to limit the scope of protection of the present invention. All equivalent embodiments or modifications made without departing from the spirit of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for evaluating blast furnace conditions, characterized in that, The method includes: The normalized interval analysis method was used to analyze the data of key parameters and important technical and economic parameters of the blast furnace, and normalized linear equations with the key parameters as independent variables and the important technical and economic parameters as dependent variables were obtained respectively. Based on the magnitude of the absolute value of the dependent variable coefficient in the normalized linear equation, the scoring weight of the corresponding key parameters on the blast furnace condition is determined. The blast furnace condition is quantitatively evaluated based on the scoring weights of all key parameters and the value levels of each key parameter. This includes: calculating the total score for each key parameter based on its scoring weights; determining the reasonable range for each key parameter; classifying each key parameter into value levels based on the degree to which its value deviates from the reasonable range; setting a grade score for each value level of each key parameter based on its total score and the value level classification; acquiring data for all key parameters over a given time period; scoring the data for each key parameter; and summing the scores for all key parameters to obtain the score for the blast furnace condition during that time period. The normalized interval analysis method includes: acquiring sample data of all key parameters and important technical and economic parameters at different time points; dividing the fluctuation range of the sample data of the important technical and economic parameters into intervals; dividing the sample data of all key parameters into the same intervals according to the time correspondence between each key parameter and the important technical and economic parameters; calculating the average value of each parameter in each interval; and using a normalization formula to obtain the normalized average value t of each parameter's average value T, wherein the normalization formula is: t The and Find the minimum and maximum values ​​of each parameter across all intervals; use the normalized average values ​​of the important technical parameters and key parameters in each interval as the coordinate values ​​of the two coordinate axes, and calculate the normalized linear equations with the key parameters as independent variables and the important technical parameters as dependent variables. Determining the reasonable range of a key parameter specifically includes: obtaining data on a key parameter and related parameters that are correlated with the key parameter; using interval analysis to analyze the data on the key parameter and related parameters to obtain the linear regression relationship between the key parameter and each related parameter; and based on the linear regression relationship, combined with one or more known target indicators of the related parameters, obtaining the reasonable range of the parameter.

2. The blast furnace condition scoring method according to claim 1, characterized in that, The key technical parameters include blast furnace output and fuel ratio. Determining the scoring weights of the corresponding key parameters for blast furnace conditions based on the absolute values ​​of the dependent variable coefficients in the normalized linear equation includes: The weight of the influence of output on blast furnace condition is determined as c, and the weight of the influence of fuel ratio on blast furnace condition is determined as d. Calculate the weight e of the impact of each key parameter on output and the weight f of the impact of each key parameter on fuel ratio; The weight of each key parameter in the blast furnace condition score is c. e+d f.

3. The blast furnace condition scoring method according to claim 1, characterized in that, The method further includes: Different scoring ranges are set for the blast furnace condition, and different response plans are developed for different scoring ranges.

4. The blast furnace condition scoring method according to claim 1, characterized in that, The method further includes: When a key parameter loses points, the impact of the key parameter on the important technical and economic parameters is calculated through the linear regression relationship between the key parameter and the important technical and economic parameters.

5. The blast furnace condition scoring method according to claim 1, characterized in that, The key parameters include key operational process parameters, and the method further includes: Calculate the score for each critical operation process parameter in each shift, obtain the highest score for each critical operation process parameter across all shifts, and select the operation corresponding to the highest score as the standard operation.

6. The blast furnace condition scoring method according to claim 1, characterized in that, The method further includes: Calculate the score for each shift in the blast furnace within a time period to obtain the overall score for each shift during that time period, and manage the workers corresponding to each shift based on the overall score.

7. The blast furnace condition scoring method according to claim 1, characterized in that, The key parameters include some input parameters and some process parameters, and the important technical and economic parameters include some output parameters. The specific data for obtaining the key parameters and important technical and economic parameters of the blast furnace includes: Establish the time correspondence between the input parameters and the process and output parameters; Based on the time correspondence, a blast furnace database will be established using the collected data of relevant blast furnace parameters; Data on the key parameters and important technical and economic parameters are obtained from the blast furnace database.

8. The blast furnace condition scoring method according to claim 7, characterized in that: The input parameters include coke M40, coke M10, sinter drum strength, ferrous content of sinter, and overall furnace feed grade. The process parameters include blast energy, air volume, top pressure, air temperature, theoretical combustion temperature, furnace bottom center temperature, cooling wall temperature, and cooling wall temperature uniformity.

9. The blast furnace condition scoring method according to claim 7, characterized in that, The establishment of the time correspondence between the input parameters, process parameters, and output parameters specifically includes: By dynamically monitoring the raw material testing data, arrival time, arrival quantity, finished product warehouse location changes, belt conveyor speed and transfer volume from the finished product warehouse to the blast furnace raw material warehouse, blast furnace raw material warehouse location, transfer speed and transfer volume after blast furnace raw material charging, and the smelting cycle of blast furnace raw materials in the blast furnace, the time correspondence between the blast furnace input parameters, process parameters, and output parameters can be calculated or obtained through tracer experiments.

10. The blast furnace condition scoring method according to claim 7, characterized in that, The process of establishing a blast furnace database from the collected blast furnace-related parameter data specifically includes: Data cleaning, data mining, and data fusion are performed on the data in the blast furnace database. The fused data in the blast furnace database is then used for data analysis, monitoring, and early warning. Specifically, data cleaning refers to removing outliers from the collected data; data mining refers to calculating indirect parameters based on the collected data using existing formulas; and data fusion refers to unifying the data frequency or data period of all parameters to obtain periodic data.

11. A blast furnace condition scoring system, characterized in that, The system includes: The data processing module is used to analyze the data of key parameters and important technical and economic parameters of the blast furnace using normalized interval analysis, and to obtain normalized linear equations with the key parameters as independent variables and the important technical and economic parameters as dependent variables. The data processing module is also used to determine the reasonable range of a key parameter, including: acquiring data of a key parameter and related parameters; using interval analysis to analyze the data of the key parameter and related parameters to obtain the linear regression relationship between the key parameter and each related parameter; and based on the linear regression relationship, combined with one or more known target indicators of the related parameters, to obtain the reasonable range of the parameter. The data processing module is also used to: acquire sample data of all key parameters and important technical and economic parameters at different time points, and divide the fluctuation range of the sample data of the important technical and economic parameters into intervals; divide the sample data of all key parameters into the same intervals according to the time correspondence between each key parameter and the important technical and economic parameters; calculate the average value of each parameter in each interval, and use a normalization formula to obtain the normalized average value t of each parameter's average value T, wherein the normalization formula is: t The and Find the minimum and maximum values ​​of each parameter across all intervals; use the normalized average values ​​of the important technical parameters and key parameters in each interval as the coordinate values ​​of the two coordinate axes, and calculate the normalized linear equations with the key parameters as independent variables and the important technical parameters as dependent variables. The scoring preprocessing module is used to determine the scoring weight of the corresponding key parameters on the blast furnace condition based on the magnitude of the absolute value of the coefficient of the dependent variable in the normalized linear equation. The scoring module is used to quantitatively evaluate the blast furnace condition based on the scoring weights of all key parameters and the value levels of each key parameter. The scoring module is also used to: calculate the total score for each key parameter based on its scoring weights; determine the reasonable range for each key parameter and classify each key parameter into value levels based on the degree to which its value deviates from the reasonable range; set a level score corresponding to each value level of each key parameter based on its total score and value level classification; acquire data for all key parameters over a given time period; score the data for each key parameter; and the sum of the scores for all key parameters is the score of the blast furnace condition during that time period.

12. The blast furnace condition scoring system according to claim 11, characterized in that, The key technical parameters include blast furnace output and fuel ratio. The scoring preprocessing module is also used for: The weight of the influence of output on blast furnace condition is determined as c, and the weight of the influence of fuel ratio on blast furnace condition is determined as d. Calculate the weight e of the impact of each key parameter on output and the weight f of the impact of each key parameter on fuel ratio; The weight of each key parameter in the blast furnace condition score is c. e+d f.

13. The blast furnace condition scoring system according to claim 11, characterized in that, The system also includes a management module, which is used for: Different scoring ranges are set for the blast furnace condition, and different response plans are developed for different scoring ranges.

14. The blast furnace condition scoring system according to claim 11, characterized in that, The system also includes a management module, which is used for: When a key parameter loses points, the impact of the key parameter on the important technical and economic parameters is calculated through the linear regression relationship between the key parameter and the important technical and economic parameters.

15. The blast furnace condition scoring system according to claim 11, characterized in that, The key parameters include key operating process parameters, and the system also includes a management module, which is used for: Calculate the score for each critical operation process parameter in each shift, obtain the highest score for each critical operation process parameter across all shifts, and select the operation corresponding to the highest score as the standard operation.

16. The blast furnace condition scoring system according to claim 11, characterized in that, The system also includes a management module, which is used for: Calculate the score for each shift in the blast furnace within a time period to obtain the overall score for each shift during that time period, and manage the workers corresponding to each shift based on the overall score.

17. The blast furnace condition scoring system according to claim 11, characterized in that, The key parameters include some input parameters and some process parameters, and the important technical parameters include some output parameters. The data processing module is also used for: Establish the time correspondence between the input parameters and the process and output parameters; Based on the time correspondence, a blast furnace database will be established using the collected data of relevant blast furnace parameters; Data on the key parameters and important technical and economic parameters are obtained from the blast furnace database.

18. The blast furnace condition scoring system according to claim 17, characterized in that, The data processing module is also used for: By dynamically monitoring the raw material testing data, arrival time, arrival quantity, finished product warehouse location changes, belt conveyor speed and transfer volume from the finished product warehouse to the blast furnace raw material warehouse, blast furnace raw material warehouse location, transfer speed and transfer volume after blast furnace raw material charging, and the smelting cycle of blast furnace raw materials in the blast furnace, the time correspondence between the blast furnace input parameters, process parameters, and output parameters can be calculated or obtained through tracer experiments.

19. The blast furnace condition scoring system according to claim 17, characterized in that: The system also includes a data acquisition module, which is used to collect data on relevant parameters of the blast furnace. The data processing module is also used for: data cleaning, data mining, and data fusion of data in the blast furnace database; and for data analysis, monitoring, and early warning using the fused data in the blast furnace database. Specifically, data cleaning refers to removing outliers from the collected data; data mining refers to calculating indirect parameters based on the collected data using existing formulas; and data fusion refers to unifying the data frequency or data period of all parameters to obtain periodic data.

Images